Agent Tools Directory

429 link-checked MCP servers, skills, hooks and Claude Code tools. Updated Oct 2026.

browserless/browserless-mcp — Headless browser automation and web scraping via the Browserless smart scraper API.

firecrawl/firecrawl-mcp-server — Firecrawl web scraping: search, scrape, crawl, map and extract structured data, with live browser interaction and website change monitoring.

SolveGate/solvegate-mcp — Detect and solve Cloudflare Turnstile challenges: inspect whether a page uses Turnstile or another CAPTCHA and get a solved token when needed.

4everland/4everland-hosting-mcp — Deploy AI-generated code to decentralized storage networks such as Greenfield, IPFS and Arweave via 4EVERLAND Hosting.

agentmetal/mcp — Provision, SSH into, run commands on and manage Linux VPSes, paying with USDC over x402 or by card.

aliyun/alibaba-cloud-ops-mcp-server — Operate Alibaba Cloud resources, including ECS, Cloud Monitor, OOS and other widely used cloud products.

awslabs/mcp — Suite of servers for integrating with AWS services and resources.

backblaze-labs/b2-mcp — Manage Backblaze B2 buckets, files, keys, Object Lock and S3-compatible storage.

BlazingCDN/BlazingCDN-MCP — Manage BlazingCDN zones, cache purge and warm-up, traffic metrics, custom domains, cloud storage and Video CDN; read-only by default.

cloudflare/mcp-server-cloudflare — Integration with Cloudflare services including Workers, KV, R2 and D1.

cyclops-ui/mcp-cyclops — Manage Kubernetes resources through the Cyclops abstraction.

espressif/esp-rainmaker-mcp — Manage and control ESP RainMaker devices.

gitayg/appcrane-mcp — Self-hosted, MCP-native deployment platform (AppCrane): AI agents deploy apps, manage secrets, read logs, and roll back on your own server. Enterprise SSO (SAML/OIDC/SCIM) and per-user audit.

hashicorp/terraform-mcp-server — Terraform ecosystem integration: provider discovery, module analysis and Terraform Registry API access for infrastructure-as-code workflows.

krovacloud/krova-node — Provision and manage Krova Cloud Cubes (Firecracker microVMs with root access), plus custom domains, TCP port mappings and snapshots.

Labs64/NetLicensing-MCP — Manage the software licensing lifecycle in Labs64 NetLicensing through natural language.

liveblocks/liveblocks-mcp-server — Create, modify and delete Liveblocks rooms, threads, comments, notifications and more, with read access to Storage and Yjs.

lizard-build/lizard-mcp — Deploy services on Lizard with managed Postgres, Redis and S3, logs and metrics, secrets, scaling and custom domains.

localstack/localstack-mcp-server — Manage LocalStack local AWS environments: lifecycle operations, infrastructure deployments, log analysis, fault injection and state management.

luno-cms/mcp — LUNO hosted backend platform: CMS, forms, auth and storage. Unrelated to the Luno cryptocurrency exchange.

oborseth/Porkbun-MCP — Official Porkbun server: domain availability and pricing, registration and renewals, DNS records, nameservers, DNSSEC, URL forwarding, DNS restore points, static hosting deploys and Cloudflare-connected domains. Also hos

openpouch/openpouch — App hosting for agents: deploy to a live URL, verify, view logs, inspect, roll back and delete, with human approval for production.

publee-dev/mcp — Publish AI-generated HTML or static files to a shareable URL, with optional permanent hosting, in-place updates and password or members-only access.

stevysmith/stacktree-mcp — Publish agent-made HTML to private, unguessable URLs with passcode or email-domain gating, expiry, burn-after-read and in-place updates.

Woobox/hatchable-mcp — Build and host full-stack web apps and sites on Hatchable, with per-project database, auth, storage, domains and cron.

xns-cloud/relayer-mcp — Install and manage a self-hosted XNS Relayer, S3-compatible object storage on a decentralized provider network: setup, health, configuration and backups.

fstandhartinger/sandbox-as-a-service-mcp — Dedicated Linux VM sandboxes for untrusted, model-generated code: run commands, move files, expose a preview URL and destroy the VM.

Reachpad/reachpad-mcp — Persistent cloud dev environments for coding agents: create, run commands, checkpoint and fork, with files, services and terminal state kept between calls.

yepcode/mcp-server-js — Run LLM-generated code in a YepCode sandbox and create custom MCP tools in JavaScript or Python with npm and PyPI packages.

plori-ai/plori — Create and drive hosted plori agents with persistent disk, tools and memory: invoke agents, manage the human-in-the-loop queue and schedule deferred runs.

churichard/fluxmail — Self-hosted email for Gmail, Microsoft 365, Outlook.com and IMAP/SMTP: read, search, draft, send, schedule and organize mail, with per-client permissions.

cometchat/docs-mcp — Search CometChat documentation and get curated implementation bundles for adding real-time chat, voice, video and moderation to apps.

dialgoodian/clawdcall-mcp — Place consent-based outbound phone calls and retrieve transcripts, summaries and outcomes.

discourse/discourse-mcp — Discourse forum integration: search topics, read posts, manage categories and tags, discover users and interact with communities.

FastAlertNow/mcp-server — List channels and send notifications through the FastAlert API.

iletimerkezi/iletimerkezi-mcp-server — Send SMS, query delivery reports, manage senders and blacklists, and register and check İYS (Turkish consent registry) records via the iletiMerkezi API.

Infobip/mcp — Infobip cloud communications: send and receive SMS and RCS, use WhatsApp and Viber, automate communication workflows and manage customer data.

sendchamp/ai — Read-only search over Sendchamp documentation for SMS, OTP verification and Africa-specific routing.

jamalofski/mailprobe-mcp — Email verification in real time, without sending anything: a valid, risky, invalid or unknown status with a score, disposable, role-based and catch-all detection, and typo suggestions. Remote server or local stdio packag

kudosity/mcp — Kudosity SMS, MMS and WhatsApp messaging: send messages, get delivery reports and replies, manage contacts and lists, configure webhooks and check balance.

LimzoCom/limzo-mcp — Read-only stats for public Telegram groups tracked by the Limzo anti-spam bot: leaderboards, activity trends, member levels and moderation summaries.

PhononX/cv-mcp-server — Create and manage Carbon Voice voice messages, conversations, direct messages, folders, voice memos and AI actions.

Pingfyr/mcp — Schedule reminders, notifications and webhooks with the Pingfyr scheduled delivery API.

sounny/sounnyforms-mcp — Serverless form backend, lead triage and contact form generator for static sites, React and JAMstack apps.

YS-projectcalc/agent-cold-email — Coldrig cold-email infrastructure run by your agent: buy domains, provision mailboxes, warm up, run sequences and handle replies.

Aiven-Open/mcp-aiven — Navigate Aiven projects and interact with PostgreSQL, Apache Kafka, ClickHouse and OpenSearch services.

appwrite/mcp — Manage Appwrite databases, auth, users, functions, storage, messaging and more.

ArcadeData/arcadedb — Built into ArcadeDB, a multi-model database (graph, document, key-value, time-series, vector) with SQL, Cypher, Gremlin and MongoDB QL support.

chroma-core/chroma-mcp — Access local and cloud Chroma instances for retrieval.

Couchbase-Ecosystem/mcp-server-couchbase — Unified access to Couchbase Capella and self-managed clusters for document operations, SQL++ queries and natural-language data analysis.

hydrolix/mcp-hydrolix — Hydrolix time-series datalake integration with schema exploration and query capabilities.

infino-ai/infino-mcp — Retrieval over your own data with Infino (BM25 full-text, vector, hybrid and SQL), an embedded engine on Apache Parquet over object storage.

InfluxData/influxdb3_mcp_server — Interact with InfluxDB 3 Core, Enterprise and Cloud Dedicated.

questdb/mcp-server-questdb — Drive the QuestDB Web Console: notebook cells, SQL queries and charts on live time-series data.

s2-streamstore/mcp — Interact with the S2 serverless stream platform.

schemacrawler/SchemaCrawler-MCP-Server-Usage — Connect to any relational database to get valid SQL and ask questions about the schema, such as what a column prefix means.

seedfast-ai/seedfast-mcp — Fill a PostgreSQL database with synthetic test data generated from its live schema: plan, run and track seeds without production data.

slotix/dbconvert-streams-public — Read-only SQL across PostgreSQL, MySQL, S3-compatible storage and Parquet/CSV/JSON files, with cross-source joins federated by DuckDB.

skysqlinc/skysql-mcp — Launch and delete serverless MariaDB Cloud databases, execute SQL and use database-level AI agents for text-to-SQL and conversations.

supabase-community/supabase-mcp — Connect to your Supabase project to manage tables, fetch config and query data.

VictoriaMetrics-Community/mcp-victorialogs — Integration with VictoriaLogs APIs and documentation for working with logs and debugging VictoriaLogs instances.

ydb/ydb-mcp — Interact with YDB databases.

sam1siam/astrofabric-mcp — Business intelligence: company and contact discovery, verification, enrichment, business signals, lists and governed delivery.

equinoxaifinance-rgb/civicdataforge-mcp — US government records (short-term rental permits, lodging licenses, property violations, healthcare exclusions, EPA ECHO) and Norwegian company data.

datanika-io/datanika-core — Datanika, the open-source ELT and dbt platform: browse connections, preview data, run dbt transforms, monitor runs and manage pipelines. Read-only by default.

dbt-labs/dbt-mcp — dbt integration: dbt Core and Cloud CLI, project metadata discovery, model information and semantic layer queries.

flowcore/mcp-flowcore-platform — Interact with Flowcore to perform actions, ingest data, and analyze and cross-reference data in your own or public data cores.

greencalculus/greencalculus-mcp — Greenhouse-gas emission factors and carbon calculations (activity, embodied EN 15978, PCAF financed emissions) with source references and data versions.

Sugra-Systems/sugra-api-mcp — World data from primary sources via the Sugra API: markets, macroeconomics, company fundamentals, government, news, climate, maritime and entity screening.

ARADIA-systems/aradia-mcp-server — On-premise private AI systems from ARADIA on NVIDIA DGX hardware: hardware sizing, ROI modeling, partner onboarding, procurement and order tracking.

Hyperiux-Immersion-Labs/hyperiux-components — Browse and search Hyperiux Vault React/Next.js animation and interaction effects, with dependencies, changelogs, install commands and source code.

2ools/mcp-server — Versioned projects from assistant-built work: shareable HTML previews, version comparison, delegated approvals, artifacts, work assignments and source export.

VerificateAI/verificate-mcp-quickstart — Merge gate for AI-written code: catches placeholder code, unfailable tests, unsupported completion claims and nonexistent API calls, then returns a fix plan.

dynatrace-oss/dynatrace-managed-mcp — Query problems, logs, events, SLOs, security insights and performance metrics from self-hosted Dynatrace Managed environments.

emailens/mcp — Lint HTML email with Emailens: rendering issues in Gmail, Outlook, Apple Mail and more, per-client CSS compatibility scores, dark mode simulation and fixes.

kucherenko/jscpd — Duplicate code detection with jscpd: check snippets and files for copy/paste duplication against a scanned project before committing.

m00nreport/mcp-server — Test management: author manual test cases, run executions, cut releases and link automated tests, with prompts for flaky-test triage and release readiness.

getnahook/nahook-mcp — Nahook webhook platform: trigger webhooks, inspect deliveries, retry failures and manage endpoints.

oddunits/pntr-cli — Register PNTR dev subdomains, manage DNS records, receive email in a disposable inbox and capture inbound HTTP requests for webhook debugging.

AIStoryHub/etincel — Deterministic local audit for AI writing tells (uniform paragraphs, stock transitions) plus a trainable voice layer so drafts sound closer to a real voice.

infino-ai/code-context — Local code search for coding agents: hybrid keyword and semantic search with SQL relevance ranking over a plain-file index.

api7/apisix-mcp — Query and manage all resources in Apache APISIX.

bitrise-io/bitrise-mcp — Bitrise API: app management, build operations, artifact management and more.

buildkite/buildkite-mcp-server — Buildkite: create pipelines, diagnose and fix failures, trigger builds, monitor job queues and more.

canopy-labs/featureflip-mcp — Manage Featureflip feature flags: create and toggle flags, edit targeting rules and find stale flags.

CodeLogicIncEngineering/codelogic-mcp-server — CodeLogic code dependency analytics, architectural risk analysis and impact assessment.

Comet-ML/Opik-MCP — Use natural language to explore LLM observability, traces, and monitoring data captured by Opik.

conan-io/conan-mcp — Conan C/C++ package manager: create projects, manage dependencies, check licenses and scan for security vulnerabilities.

ConfigCat/mcp-server — ConfigCat feature flag platform: manage feature flags, configs, environments, products and organizations.

currents-dev/currents-mcp — Fix Playwright test failures reported to Currents.

docker/hub-mcp — Interact with Docker Hub: repositories, search and Docker Hardened Images.

extentos/mcp-server — Build smart-glasses apps: scaffold, validate and simulate Meta smart glasses integrations (camera capture, voice, audio) in Android and iOS apps.

gitkraken/gk-cli — GitKraken CLI with an MCP server wrapping GitKraken APIs as well as Jira, GitHub, GitLab and more.

gofireflyio/firefly-mcp — Discover, manage and codify cloud resources with Firefly.

homespunapps/homespun — Deploy and operate multi-user web apps: magic-link sign-in, a shared realtime database, per-role permissions, email notifications and file uploads.

jetbrains/mcpProxy — Work with JetBrains IDEs such as IntelliJ, PyCharm, WebStorm and Android Studio.

jsdelivr/globalping-mcp-server — Run ping, traceroute, mtr, HTTP and DNS measurements from locations around the world via Globalping.

Jungle-Grid/mcp-server — Estimate, submit, monitor and fetch logs for GPU inference, training, fine-tuning and batch workloads on Jungle Grid.

logisky/logisheets-mcp — Local Excel-compatible spreadsheet engine based on LogiSheets: deterministic formulas, named blocks, column rules, scenario scans, goal-seek and .xlsx export.

PostHog/posthog — Interact with PostHog analytics, feature flags, error tracking and more.

reflagcom/mcp — Manage Reflag feature flags from chat in your IDE.

Rootly-AI-Labs/Rootly-MCP-server — Access Rootly, the incident management platform.

SuresoftTechnologies/dvera-plugin — Drives Controller Tester (CT) C/C++ verification: project setup, analysis, test generation and execution, statement/branch/MC-DC coverage and report export.

testdino-hq/testdino-mcp — Review TestDino test runs, debug failures and manage manual test cases using natural language.

x402node/x402-mcp — Exposes x402-paid APIs discovered from Coinbase Bazaar, handling USDC micropayments on Base.

vercel/next-devtools-mcp — Next.js runtime diagnostics, route inspection, dev server logs, docs search and upgrade guides for coding agents.

Webvizio/mcp — Converts website and web app feedback and bug reports into context-enriched developer tasks for coding agents via Webvizio.

drumst0ck/uploadkit — UploadKit's React upload components, Next.js route handler scaffolds, bring-your-own-storage setup (S3, R2, GCS, B2) and full-text docs search.

skyhook-io/radar — Query Kubernetes cluster topology, resources, events, logs and Helm/GitOps state across clusters via Radar, a Kubernetes visibility tool.

chrassy/klanex-mcp — Async execution for agent tool calls: payload schema checks, retries and circuit breakers, idempotency keys, approval gates, replay and signed-webhook results.

get-tmonier/argot — Checks agent-written code against the repo's git-history patterns, flagging foreign dependencies, reinvented functions, misplaced code and gamed tests.

WCAG-Compliance/wcagc-mcp — Accessibility scanning with axe-core (WCAG 2.1 AA, EN 301 549, PDF/UA) via wcagc: scan URLs and PDFs, crawl sites, replay journeys and read violation trends.

servelink-swyftlabs/serve-mcp — Public HTTPS links for local files, directories or dev servers, via a live tunnel or published copy, with password protection, TTLs and named subdomains.

Yocoolab/mcp-server — Pin visual feedback on live web pages with the Yocoolab extension and hand it to coding agents with the element, selector and screenshot attached.

JeanFrancoisGagne/crapkit — Read-only per-function CRAP scores (complexity and coverage) that point to the worst function to fix next, with uncovered lines and near-duplicates.

gba3124/anyhook-mcp — Create live webhook endpoints and read back the deliveries they receive; endpoints keep working after the session ends.

box/mcp-server-box-remote — Access Box content: search, ask questions about files and folders, and extract data.

jamalofski/conv2pdf-mcp — Convert Office documents, images and e-books on your computer to PDF, convert PDFs to Word or images, and merge, split, compress, protect or number PDFs via the conv2pdf API, hosted in France.

microsoft/markitdown — Convert many file formats, local or remote, to Markdown for LLMs using MarkItDown.

Regan-Milne/obsideo-mcp — Encrypted S3-compatible object storage with cryptographic possession proofs: put, get, list and delete objects, with optional client-side encryption.

soluai-spa/solucortex-mcp — Technical memory for AI agents: recall a project's approved decisions, conventions and risks at task start and record lessons at the end.

pinecone-io/assistant-mcp — Connect to your Pinecone Assistant and retrieve context from its knowledge engine.

SagaPeak/artifacta-mcp — Artifact store for agent outputs: persist, retrieve and share them across runs and sessions, with content-hash dedup and expiring share links.

Mnemosyne-OS/Mnemosyne-Neural-OS — Human-governed memory in local, domain-separated vaults with hybrid retrieval; also reads other coding agents' output. Requires the Mnemosyne OS desktop app.

memokar/brainy — Self-hosted shared brain for multiple agents: Git-versioned Markdown knowledge plus a task queue with atomic claims, per-space ACL, audit log and human approval, so Claude, ChatGPT and other agents can hand work to each

bartekrutkowski/watchgoose-mcp — Monitor cron jobs, backups, Kubernetes jobs and other scheduled tasks in Watchgoose. Read-only by default; check changes require explicit consent.

edgedelta/edgedelta-mcp-server — Interact with Edge Delta anomalies, query logs, patterns and events, find root causes and optimize pipelines.

fclairamb/solidping — Uptime monitoring over MCP. List and create checks, read incidents and results, manage maintenance windows and status pages. Self-hosted single Go binary, 40 check types, probes in several regions.

grafana/mcp-grafana — Search dashboards, investigate incidents and query datasources in your Grafana instance.

HostTracker/mcp — Website uptime monitoring: instant HTTP, ping, port, DNS, WHOIS, blacklist and page-speed checks, plus monitors, webhooks, incidents and status pages.

tp322d/lastping-app — Dead man's switch monitoring for AI agents, cron jobs and CI/CD pipelines: alerts when runs go silent, stall, fail or loop, with incident details.

metoro-io/metoro-mcp-server — Query and interact with Kubernetes environments monitored by Metoro.

netdata/netdata#Netdata — Discovery, exploration, reporting and root cause analysis over Netdata metrics, logs, systems, containers, processes and network connections.

openITCOCKPIT/openITCOCKPIT-MCP-Server — Access openITCOCKPIT monitoring: host and service state, check history, logs, downtimes, acknowledgements, software inventory and pending security updates.

pydantic/logfire-mcp — Access OpenTelemetry traces and metrics through Logfire.

spanlens/Spanlens — Read-only access to Spanlens LLM observability: request logs, costs, agent traces, anomalies, model savings and per-user analytics.

uptybots/mcp-server — Uptime monitoring for websites, APIs, SSL certificates, domain expiry, ping and TCP/UDP ports: manage monitors and view incidents and uptime history.

VictoriaMetrics-Community/mcp-victoriametrics — Integration with VictoriaMetrics instance APIs and documentation for monitoring, observability and debugging tasks.

AIOProductOS/claude-plugin — Product management: link customer feedback to features, releases and objectives, with roadmap-drift detection and funnel, retention, NPS and NRR analytics.

mohamed-ashraf-elsaed/loupe — Turn Loupe visual feedback into a backlog: list pinned comments, read each with its element's HTML, computed styles and screenshot, and update its status.

gonnagetapower/kelvia-mcp — Operate the Kelvia task manager: boards, tasks, sprints, member roles, worklogs and a time-blocking day planner.

illodev/workfile — Backlog, docs, history and memory as Markdown in the repository, versioned with the code, with card claims so parallel agents don't edit the same card.

kenzotp/mcp-server-zuuna — Zuuna developer project management: read and update boards, cards and comments, with cards moved automatically by git activity when PRs merge.

fenbs-ai/fenbs-mcp — fenbs project board where people and AI assistants are members with roles: tasks, decisions with sign-off, testing notes and project rules, every change signed. Remote server at https://fenbs.ai/api/mcp or `npx -y fenbs-

usestring/string-ai-mcp — Search the web, fetch URLs and map sites as clean Markdown, getting past anti-bot blocks.

ToolTrace-io/mcp-server — Web page data: scrape to Markdown, extract metadata, links and JSON-LD, audit on-page SEO, detect tech stacks and validate XML sitemaps.

artemchuikin/youtube-mcp — YouTube transcripts (text, JSON, SRT, VTT, srv3), video and channel search, playlists and large batch jobs.

quantumproxies/quantumproxies-mcp — Residential-proxy web access: scrape pages to Markdown, SERP search, site mapping and crawling, ready-made collectors, and proxy endpoints from your plans.

eliottreich/crawdar-mcp — Evidence-backed business discovery and lead-list research: search by brief or criteria, inspect qualification evidence and exclusions, and export results.

devflowinc/trieve — Crawl, embed, chunk, search and retrieve information from datasets through Trieve.

pepabo/muumuu-domain-mcp — Search and register Muumuu Domain (GMO Pepabo) domains, manage owned domains and contracts, and configure DNS records.

Dumpling-AI/mcp-server-dumplingai — Access Dumpling AI's data, web scraping and document conversion APIs.

exa-labs/exa-mcp-server — Real-time web search using the Exa AI Search API.

fouradata/mcp — Web scraping that escalates from direct fetch to rotating proxy to full browser, solving anti-bot challenges and reporting which step worked and its cost.

VoxellInc/forge-mcp — Generate vector embeddings for semantic search and RAG with Forge, Voxell's text-embedding API, including Matryoshka truncation.

getrephonic/rephonic-mcp — Search Rephonic podcast and episode data: listener estimates, demographics, contacts, transcripts, chart rankings, sponsors, reviews and audience overlap.

keenableai/keenable-mcp — Live web search and clean Markdown page fetching over the Keenable web index.

Linked-API/linkedapi-mcp — Control LinkedIn accounts and retrieve real-time LinkedIn data.

litescrape/litescrape-mcp-server — Google Search, Bing, DuckDuckGo, Google Maps, Google AI Mode, AI Overview and Shopping results as JSON.

litportnet/free-proxy-mcp — Verified free HTTP, SOCKS4 and SOCKS5 proxy lists from Litport, filtered by country, anonymity, latency and uptime. Returns records only; no API key needed.

Marvy101/pod-mcp — Search firsthand observations agents recorded about products, APIs, services or places, as opposed to documentation claims, and write back new ones.

MKirovBG/scribefy-mcp — Extract timestamped YouTube transcripts, plus video search, metadata and related videos.

OctagonAI/octagon-deep-research-mcp — Deep research agent from Octagon.

opendatalab/MinerU-Ecosystem — Convert PDFs, Word and PowerPoint files, images and spreadsheets to Markdown via the MinerU document parsing API.

Pearch-ai/mcp_pearch — People search engine for talent discovery.

quantumproxies/quanticdata-mcp-server — Web data via residential proxies: page scraping to Markdown, SERP search, site crawl and map, ready-made collectors and datasets from plain-language prompts.

searchcraft-inc/searchcraft-mcp-server — Manage Searchcraft clusters, create search indexes, generate an index from a data file and import data from a feed or local JSON file.

serkan-ozal/driflyte-mcp-server — Query and retrieve topic-specific knowledge from recursively crawled and indexed web pages via Driflyte.

serpdive/serpdive-mcp — Web search returning extracted page content (URL, title, date, text) instead of links, with automatic localization and an optional synthesized answer.

shopsavvy/shopsavvy-mcp-server — ShopSavvy product and price data: search by barcode, ASIN or URL, get product details, compare retailer prices and track price history.

srezai-team/srezai-mcp — Web and image search, page reading as Markdown, browser-rendered screenshots, schema-based extraction and deep research, with strong Russian web coverage.

tinyfish-io/agentql-mcp — Data extraction with AgentQL.

us/crw — Self-hostable web crawler and search API (fastCRW): scraping, crawling, site mapping and SearXNG-backed search.

webscraping-ai/webscraping-ai-mcp-server — Web data extraction and scraping via WebScraping.ai.

ucsandman/DashClaw — Fail-closed approval layer for unattended agent runs: checks actions against org policy, requests human approval and logs every decision to a causal ledger.

kakunin-ai/kakunin-mcp — Agent compliance and identity: verify an agent's X.509 certificate scope, read its behavioral risk score and append to an immutable audit trail.

alexar76/aimarket-mcp — SSRF-hardened web gateway with web fetch, web search and Metis verification, sharing an audited security core with Metis and ARGUS.

alexar76/argus — Query ARGUS-3 and check its status; WARDEN vets third-party MCP servers with a scored firewall, tool-definition pinning and drift detection.

aeoess/agent-passport-mcp — Agent identity, scoped delegation and governance: issue passports, verify narrowing-only delegation chains, enforce gateway policy and emit signed records.

maxfain/basedagents — Agent identity registry (reputation, capability search, task marketplace, messaging) plus a local encrypted vault that leases provider keys to agents.

FoundryNet/mint-mcp — MINT Protocol work attestation for agents: cryptographically attest, verify, rate and discover agent work to build portable on-chain reputation.

dnsdoctor/claude-plugin — Scan and fix a domain's email authentication (SPF, DMARC, DKIM, MX), blacklist status and domain/SSL expiry, with deterministic, validated fix records.

echelongraph/echelongraph-mcp — Keyless, read-only CVE and internet-exposure intelligence: CVE lookup and search, CISA KEV, EPSS history, CWE, vendor advisories (MSRC, Red Hat, Cisco, GHSA and more), SBOM and manifest checks, and aggregate exposure rad

luiacuaniello/perspectivegraph — Attack-path engine for cloud and Kubernetes: list routes from internet exposure to sensitive assets, explain each hop, find choke points and simulate fixes.

mandarelabs/mandare — Accountability for AI agent fleets: verify a signed, hash-chained ledger, check budgets, kill an agent, and issue passports and mandates, all through the local CLI.

mobb-dev/mobb-vibe-shield-mcp — Mobb Vibe Shield identifies and remediates vulnerabilities in human and AI-written code.

panther-labs/mcp-panther — Use Panther's SIEM platform in natural language to write detections, query logs and manage alerts.

safedep/vet — Locally check npm and PyPI packages, such as those suggested by AI coding tools, for vulnerabilities and malicious code.

scalekit-inc/scalekit-mcp-server — Manage Scalekit organizations, users and SSO.

thyn-ai/algenta-sdk — Algenta decision engine: dataset discovery, exact queries, utility models, decision memory and governed agent runs with approvals and execution receipts.

sekera-radim/impri — Self-hostable human-in-the-loop approval inbox: humans approve, reject or edit proposed agent actions via web, mobile, Slack, Discord or Telegram.

semgrep/semgrep — Scan code for security vulnerabilities using Semgrep.

snyk/studio-mcp — Embeds Snyk's security engines into agentic workflows to secure AI-generated code in real time and work through vulnerability backlogs faster.

swnotmetal/Project-Koma — Classify input for prompt injection and out-of-scope content with Koma Gate's LLM-based classifier.

shieldly-io/mcp — Analyze AWS IAM policies and CloudFormation templates with Shieldly to flag privilege-escalation paths, wildcards and over-permissive access.

trustscoreagent/trustscoreagent — Check the reputation of AI microservices and public APIs before calling them and submit ratings afterward, via an open trust registry.

timescale/rsigma — Author, lint, validate and convert Sigma detection rules with RSigma, evaluate and explain detections against log events, and inspect correlation state.

Agent Skills — Anthropic's official repository for Agent Skills — the SKILL.md format, a skill template, and example skills, the same format Claude Code loads natively.

Building Effective Agents — Anthropic's foundational taxonomy of agent patterns — prompt chaining, routing, orchestrator-workers, and evaluator-optimizer — and when to use each.

Claude Code Best Practices — Anthropic's canonical guide to working effectively with Claude Code: the agentic-loop mental model, CLAUDE.md guidance, and workflow patterns.

Claude Code Cheatsheet — Anthropic's official Claude Code cheatsheet — a quick reference for the core vocabulary (session, context window, CLAUDE.md), built-in slash commands, and keyboard shortcuts.

Claude Code GitHub Action — The official GitHub Action for running Claude Code in CI: mention @claude in issues and pull requests to delegate code changes, reviews, and fixes.

Claude Code Security Review — An official AI-powered security-review GitHub Action that uses Claude to analyze pull-request diffs for vulnerabilities.

Effective Context Engineering for AI Agents — Anthropic's guide to curating the context window — compaction, just-in-time retrieval, and note-taking — the discipline underlying effective long-horizon agent use.

How Claude Code Works — The official conceptual explainer of Claude Code's agentic loop, tools, and context window, and how skills, hooks, and subagents layer on top.

How We Built Our Multi-Agent Research System — A practical account of orchestrator and subagent coordination, prompt design, and evaluation that maps directly to Claude Code's subagents and agent teams.

Official Plugin Directory — Anthropic's official, curated directory of high-quality Claude Code plugins, installable from within Claude Code.

Steering Claude Code: Skills, Hooks, Rules, Subagents and More — A framework for choosing which extension mechanism to reach for, organized around deterministic-versus-probabilistic control and context isolation.

Agent Skills for Knowledge Work — Skills for knowledge work rather than just coding, covering a variety of cognitive approaches to problem-solving: brainstorming, critical thinking, problem diagnosis, design thinking, market research, deep reading, Socra

Agentic Workflow Patterns — A comprehensive and well-documented collection of agentic patterns from Anthropic docs, with colorful Mermaid diagrams and code examples for each pattern. Covers Subagent Orchestration, Progressive Skills, Parallel Tool

Bloom — A self-contained Claude Code skill that turns Benjamin Bloom's "2-sigma" tutoring research into a personal AI tutor: it generates a structured syllabus, teaches one lesson at a time, and adapts each next lesson to the le

cc-thinking-skills — A collection of installable thinking-framework skills with a meta-router, notable for publishing a replication-gated evaluation instead of unsupported quality claims.

Claude Code Handbook — Collection of best practices, tips, and techniques for Claude Code development workflows, enhanced with distributable plugins

Claude Code Repos Index — This is either the work of a prolific genius, or a very clever bot (or both), although it hardly matters because the quality is so good - an index of 75+ Claude Code repositories published by the author - and I'm not tal

Claude Code System Prompts — All parts of Claude Code's system prompt, including builtin tool descriptions, sub agent prompts (Plan/Explore/Task), utility prompts (CLAUDE.md, compact, Bash cmd, security review, agent creation, etc.). Updated for eac

claude-code-android — A thorough, device-tested guide and toolkit for running Claude Code natively on Android via three paths (Termux, proot-Ubuntu, and the Android Virtualization Framework), with a verification harness and per-device results

claude-code-docs — A mirror of the Anthropic&copy; PBC documentation site for Claude/Code, but with bonus features like full-text search and query-time updates - up-to-the-minute, fully-indexed information so that Claude Code can read

Codebase to Course — A Claude Code skill that turns any codebase into a beautiful, interactive single-page HTML course for non-technical vibe coders.

cxpak — A code-intelligence Claude Code plugin and MCP server (Rust, single binary, 43 languages) that builds a typed dependency graph and packs token-budgeted, annotated context bundles for any task. Exceptionally engineered an

Dive into Claude Code — A research-lab systematic analysis of the Claude Code codebase whose headline finding — overwhelmingly infrastructure rather than model — reframes Claude Code as a harness.

Encyclopedia of Agentic Coding Patterns — A freely available reference covering 190+ patterns for AI-assisted software development (and actually a whole bunch of related technical topics) from foundational concepts through agentic construction patterns, governan

learn-faster-kit — A creative educational framework for Claude Code, inspired by the "FASTER" approach to self-teaching. Ships with a variety of agents, slash commands, and tools that enable Claude Code to help you progress at your own pac

MDXG Redline — A Claude Code skill plus single-file HTML tool that closes the human-review loop on AI-written docs: a person leaves inline comments in the browser, which export as structured JSON keyed by heading path and line, and the

NotebookLM MCP — A mature MCP server (plus a 33-endpoint REST API) that drives Google NotebookLM for citation-backed Q&A and full Studio generation (audio, video, infographics, reports), with multi-account TOTP re-auth. Notably well-

RAG Learning Academy — A multi-agent Claude Code learning environment for mastering Retrieval-Augmented Generation, with 20 specialist agents, 22 slash commands, and a 9-module hands-on curriculum that runs zero-config inside Claude Code. Qual

showreel — A Claude Code plugin that turns CSS selectors + text into finished visual documentation — annotated screenshots, flow GIFs/MP4s, terminal recordings, and before/after composites — placing every annotation deterministical

Universal Exam Cram Coach — A multimodal, grounded active-learning tutor engine for college textbooks. Mitigates AI hallucinations and diagram blindness with automated vector figure cropping, homework-solution auto-pairing, and cross-session persis

agentcairn — Long-term, cross-project memory for AI coding agents. Your own Obsidian vault as the source of truth. Daemonless and without opaque databases, your memory belongs to you.

Bedrock — A Claude Code plugin that turns an Obsidian vault into a structured second brain via 8 skills, building an entity-typed (actors/people/teams/topics…) Zettelkasten graph with bidirectional wikilinks and ingesting Confluen

claude-obsidian — Self-organizing AI second brain for Obsidian + Claude Code. Claude reads any source, links it, and files it into one connected knowledge graph of plain Markdown. Based on Karpathy's LLM Wiki pattern.

Librarian — A standalone MCP server that gives Claude a markdown second-brain over any Obsidian vault or folder of `.md` files, with trigram search, auto-wikilinks on write, and real graph analytics (Louvain communities, PageRank, s

vir — Distills the Claude Code transcripts already on your disk into typed markdown notes (decisions, gotchas, patterns). Serves them via MCP and a CLAUDE.md block. Integrates with Obsidian.

Archify — An Agent Skill for Claude Code that generates interactive architecture, workflow, sequence, data-flow, and lifecycle diagrams as standalone HTML. Typed JSON, local renderers, and delivery checks support source-linked nod

Netresearch Agentic Skills — Skills for assessing and enhancing software projects to meet enterprise-grade standards for security, quality, and automation. Strong collection covering a range of development frameworks, enterprise-readiness, security,

OSS Autopilot — End-to-end open source contribution manager. Discovers contributable issues across GitHub, tracks PRs across multiple repos, diagnoses CI failures, and drafts maintainer responses. Great collection of skills and agents f

AI Research Skills — A catalog of 15 Claude Code skills mapped to 8 research-workflow stages (literature → gap analysis → design → drafting → reviewer response), where each stage emits an explicit YAML/Markdown deliverable the next stage con

Claude Scientific Skills — "A set of ready-to-use Agent Skills for research, science, engineering, analysis, finance and writing." That's their description - modest, simple. That's how you can tell this is really one of the best skills repos on Gi

geo-sleuth — An agent skill that geolocates a photo with no readable text. Single-purpose Python scripts search and rank candidates using OpenStreetMap geometry, elevation skylines, satellite imagery and street view. The answer comes

My Claude Code Setup — A ready-to-fork Claude Code template for academics using LaTeX/Beamer + R. Multi-agent review, quality gates, adversarial QA, and replication protocols. Great use of orchestration patterns and great documentation.

Agents Can Communicate (ACC) — Local, multi-provider agent communication tool. Adds hooks and a skill to exchange questions and reviews, and saves decisions, verification results and handoffs for later sessions. Each session keeps its own client, mode

chrome-cdp-ex — A zero-dependency Claude Code skill (68 commands) that connects to your *real* Chrome — logged-in tabs, cookies, live page state — to give the agent a perception layer: layout, visible styles, per-action "what changed" e

Claude Code Local — Runs Claude Code fully on-device on Apple Silicon: a native MLX server speaks the Anthropic Messages API, so the unmodified claude CLI works against local Qwen, Gemma and Llama models with no cloud calls. Includes RAM-ba

Claude Codex Settings — A well-organized, well-written set of plugins covering core developer activities, such as working with common cloud platforms like GitHub, Azure, MongoDB, and popular services such as Tavily, Playwright, and more. Clear,

claude-code-wsl2-setup — A focused collection of documented scripts that fix the most painful Claude Code papercuts on WSL2 + Windows Terminal — clipboard screenshot paste via a Go daemon, Windows notifications on Stop/PermissionRequest hooks, L

Codex Skill — Enables users to prompt codex from claude code. Unlike the raw codex mcp server, this skill infers parameters such as model, reasoning effort, sandboxing from your prompt or asks you to specify them. It also simplifies c

Flue — A tiny bridge that lets Claude Code drive desktop software — Photoshop, Premiere, Blender, Unity, InDesign, Office, 13 apps total — by writing one-time scripts against each app's own automation runtime (COM / AppleScript

Fusion Harness — Fuses 2–5 frontier models instead of racing them — one architect, one primary builder, and up to three secondary builders — giving N-way opinions, debate, fusion, coordinated implementation, direct one-agent routing, and

llm-router — A local-first router that sits under Claude Code (and Codex/Gemini CLI) and sends each prompt to the cheapest capable model, with three-layer token compression and automatic provider fallback — protecting your premium qu

OpenWeb — An agent-native skill that accesses 90+ websites by calling their underlying APIs directly (typed JSON in, JSON out) instead of screenshotting and parsing the DOM, with auth auto-resolved locally from your existing brows

Repowire — A live mesh network that connects Claude Code and other providers so they can talk to each other in real time. Built for emergent coordination. Agents discover each other and share context across project boundaries. Uses

SPARDA — Converts a running Express or FastAPI app into an MCP server by AST-parsing its routes and injecting a marked, byte-for-byte-removable `/mcp` router, so the agent can operate your live application (real auth, real data)

anotifier — A zero-dependency, cross-platform notifier that fires a desktop toast and a free phone push (via ntfy) the moment Claude Code (or Codex/Cursor/Gemini) finishes a task or needs input, wired up by a one-command setup. The

Claude CLI ↔ Telegram — A feature-rich Telegram bot that turns your machine into a remote Claude Code terminal driven from your phone: streaming tool progress, voice input, a git panel, Mac remote control, and 30+ commands. Its standout is the

Claude Threads — Streams a locally-running Claude Code session live into a Slack or Mattermost thread so a whole team can watch, type, and approve actions together — "screen-sharing for AI pair programming, but everyone can type." Mature

Claudio — A no-frills little library that adds delightful OS-native sounds to Claude Code via simple hooks. It really sparks joy.

dictate — Local, offline voice-to-text for Claude Code on Linux built on faster-whisper, with a warm daemon for instant transcription, system-wide push-to-talk, a voice-enabled editor, and per-project vocabulary hints that fix tec

Lockpaw — A native-Swift macOS menu-bar app (10 MB, no Electron) that covers and input-locks your screen with one hotkey while your agents keep running, then makes the locked screen glow when Claude Code pauses for permission or f

WhatsApp Channel Plugin — Connects WhatsApp as a native Claude Code channel via Baileys linked-device (no bot token or API keys), with bidirectional messaging, full media, voice transcription, remote tool approval, access control, and per-group p

Agent Workbench — Local web UI that runs the unmodified Claude Code CLI in a pseudo-terminal and adds tabs, a browsable history of past sessions, conversations rendered as cards, a context meter, and the agent's multiple-choice questions

Cate — A cross-platform desktop IDE built on an infinite zoomable canvas, where editors, terminals, browsers, and docs float in freeform space instead of tabs — and ships skills that let Claude Code spawn agent terminals on the

Claude Overlay — A frameless, always-on-top floating chat window for Claude Code on Windows. It captures every monitor and lets Claude read the screen to answer questions in context, and drives the user's existing claude CLI login throug

CloudCLI (Claude Code UI) — A web and mobile PWA for driving Claude Code (and Cursor/Codex/Gemini) from any device — file explorer, git, integrated shell, and full session management that reads and writes your real `~/.claude` config rather than du

FlyCrys — A native Linux GUI for Claude Code agents built in Rust + GTK4 — single binary, no Electron, starts in under a second — with a file tree, syntax-highlighted viewer, markdown preview, embedded VTE4 terminal, streaming age

Happy Coder — Spawn and control multiple Claude Codes in parallel from your phone or desktop. Happy Coder runs Claude Code on your hardware, sends push notifications when Claude needs more input or permission, and costs nothing. End-t

Nimbalyst — A visual workspace for building with Claude Code (and Codex) where you and the agent co-edit *visually* — markdown, mockups, mermaid, Excalidraw, CSV, and data models — approving the agent's changes as red/green WYSIWYG

Sidekick for Max — A VS Code extension and standalone terminal dashboard that adds visibility and AI conveniences on top of your Claude Max subscription — inline completions, code transforms, AI commit messages, plus deep session observabi

Vibeyard — A cross-platform desktop IDE that wraps Claude Code sessions with a swarm mode (parallel agents in a grid), a real-time session inspector (cost, tokens, tool-usage, context), multiple isolated Claude profiles, a kanban b

CCometixLine — A high-performance Claude Code statusline tool written in Rust with Git integration, usage tracking, interactive TUI configuration, and Claude Code enhancement utilities.

ccstatusline — A highly customizable status line formatter for Claude Code CLI that displays model info, git branch, token usage, and other metrics in your terminal.

Claude HUD — A really stacked status line that exposes just about everything you might need - context usage, tools, agents, todos, etc. Highly configurable and actively maintained at the time of writing - code quality is strong.

claude-carbon — Tracks the carbon footprint of Claude Code sessions, feautring a live CO2 estimate in the status line, computed locally from token usage, next to the session cost.

claude-code-personalities — A delightfully different status line: 30+ kaomoji text-faces that react in real time to what Claude is doing — context-aware personas by file type, and a frustration-escalation system where mounting errors progress from

claude-powerline — A vim-style powerline statusline for Claude Code with real-time usage tracking, git integration, custom themes, and more.

claude-statusbar — The most complete Claude Code status line: 5-hour and 7-day rate-limit usage with reset countdowns and *learned* end-of-window projections, context window, prompt-cache-expiry countdown, per-session cost, plus live todo/

TermaGITchi — A Go CLI that gives each Claude Code session its own creature in the status line, derived by hashing the session id, with one den per git worktree. Where other status-line faces react to what the agent is doing, this one

tmux-claude-status-tabs — Shows each Claude Code session's state in the tmux tab bar, per window: an animated spinner while it works, amber when it waits on input, red on a permission request, green when done. Event-driven via hooks with no polli

atelier — Claude Code plugin with eight design-automation skills driven by one schema-validated brand.json: design tokens for CSS, Tailwind, TypeScript and Figma, social cards, favicon and app-icon sets, responsive AVIF and WebP i

bdg (Browser Debugger CLI) — A CLI and Claude Code skill for UI debugging in Chrome using the DevTools Protocol, including DOM inspection, browser events, rendered styles, and detailed layout information.

Dev Browser — A browser-automation plugin/skill that lets Claude Code drive a browser to test and verify its own work — full Playwright API plus pixel- and DOM-level computer-use toolsets, connecting to your running Chrome or a fresh

Diagram Design — Another welcome contribution to the domain of making Claude Code output look stylish, this collection of skills produces a variety of editorial diagrams in the form of self-contained HTML + SVG. Although I never thought

Logo Designer Skill — Create and evolve SVG logos with Claude Code. Turns a project brief into distinct concepts you can compare side by side, then guides refinement, checks favicon legibility, and exports production-ready PNGs.

Pinpoint — Local MCP server, Claude Code hooks and a Chrome extension for marking up a running app: clicking an element (or one in the iOS Simulator) and typing a change delivers the comment to Claude Code with the selector, DOM pa

Snip — A visual whiteboard between you and your agent: Claude renders diagrams, HTML, or UI components through Snip instead of describing them in text, you approve or annotate directly on the output (circle, arrow, note), and t

StyleSeed — A design engine that takes a different tack from "feed the model more tokens": it teaches design *judgment* — ~74 rules pros carry but never write down ("the refined black isn't #000, it's #2A2A2A"; "one accent color, ev

UI Craft — A deep design-engineering skill that makes agents "design like they have taste" by default, layered so you can just install it, drive it with 22 single-lens commands, or wire its deterministic MCP gates and CLI into CI.

visual-explainer — Agent skill and plugin that turns complex terminal output into styled HTML pages or slide decks for diagrams, diff reviews, plan audits, data tables, and project recaps. Generates self-contained browser-readable artifact

Web Assets Generator Skill — Easily generate web assets from Claude Code including favicons, app icons (PWA), and social media meta images (Open Graph) for Facebook, Twitter, WhatsApp, and LinkedIn. Handles image resizing, text-to-image generation,

Avoid AI Writing — A portable writing skill that audits and rewrites prose to remove "AI-isms" — 49+ pattern categories and a tiered word-replacement vocabulary, with detect / rewrite / edit-in-place modes, content-type and voice profiles,

Book Factory — A comprehensive pipeline of Skills that replicates traditional publishing infrastructure for nonfiction book creation using specialized Claude skills.

Claude Style Patch — A CLAUDE.md section that constrains Claude's prose style. It bans specific habits, including announcing a point before making it, colon-hinged sentences where the left side labels the right, verbless fragment openers, an

naming — A Claude Code skill for naming products, SaaS tools, brands, and projects via a structured metaphor-driven process — naming brief, metaphor exploration, candidate generation, anti-slop filtering, a weighted evaluation ru

oh-my-patent — A plugin for turning technical ideas into patent disclosures.

Scientific Writing Skills — Six Agent Skills for scientific writing based on Stanford's Writing in the Sciences course: sentence-level prose editing, IMRaD manuscript structure, the writing process, peer review and publication, grants and recommend

Story Skills — Skills for planning and drafting fiction as markdown with YAML frontmatter: story bible, characters, worldbuilding, arcs, scenes, and chapters. Includes a dependency-free CLI whose continuity checker flags characters app

blender-kiln — A Claude Code plugin that drives Blender over an MCP server to turn a text brief or a reference photo into an optimized, validated GLB: scripted modeling measured against the photo, textures from CC0 scans, a joint-by-jo

capcut-cli — A zero-dependency Node CLI (and Claude Code plugin/skill) that lets the agent edit CapCut / JianYing video projects programmatically — inspect timelines, build drafts, add text/audio, word-level captions and Whisper tran

claude-replay — An outstanding, creative library that converts Claude Code session transcripts into self-contained, embeddable HTML replays - interactive playback with speed control, a local editor, collapsible tool-call and thinking bl

motion-skills — An open-source collection of ~50 motion-graphics, animation, and video skills across 14 installable packs — kinetic typography, data-driven charts, explainers, TikTok/Reels, web/WebGL animation, and Manim math animation

Vox director skill — Vox Director is an open-source skill that turns a one-line topic into a finished Vox-style paper-collage explainer or ad video. It automates the full pipeline — script, collage keyframes, motion, voice-over, music, and c

cc-devops-skills — Immensely detailed set of skills for DevOps Engineers (or anyone who has to deploy code, really). Works with validations, generators, shell scripts and CLI tools to create high quality IaC code for about any platform you

mirrord — Agent skills and a Claude Code plugin marketplace for mirrord, which runs a local process inside a live Kubernetes cluster's network, environment and traffic. Lets Claude verify changes against real services, databases a

otelcol-doctor — A focused, vendor-neutral skill that writes, fixes, and *validates* OpenTelemetry Collector configs — encoding the Collector's real footguns (memory_limiter/batch ordering, core-vs-contrib components, pull-vs-push export

pwa2play — Packages a PWA into a signed Play Store Android bundle with Bubblewrap and checks target API level, signing key reuse, assetlinks fingerprints and version codes before upload.

terraform-skill — A best-practices skill that teaches the agent to write safer Terraform and OpenTofu through a diagnose-first workflow, failure-mode routing, LLM-mistake checklists, and a feature-version guard table mapping features to t

Agent Guard — Real-time secret-leak guardrails for AI coding agents (Claude Code, Codex), Git hooks, and CI.

aicontainer — Sandboxed devcontainer for running Claude Code, Codex, and OpenCode in bypass / auto-approve mode.

Airut — Airut is a system for running Claude Code tasks from email and Slack. It handles workspace provisioning, container isolation, network sandboxing, session persistence, and cleanup — a secure foundation for autonomous agen

authsome — Credential gateway for AI agents. Log in once via Oauth2 or API Key. Every agent stays authenticated — headless, no SaaS, agents never see your credentials.

Brood Box — CLI tool for running coding agents inside hardware-isolated microVMs

Claude Code Safety Guard — 3-level override system for Claude Code - prevents destructive system operations. Born from a real incident.

Claude Code Safety Net — A coding agent CLI hook that acts as a safety net, catching destructive git and filesystem commands before they execute. Supports Codex, Claude Code, OpenCode, Gemini CLI, Copilot CLI, Kimi Code and Pi.

Cleat — Give the agent a cage, not your keys. One-command Docker sandbox for AI coding agents: full autonomous permissions, per-project isolation, your host stays untouched.

Code on Incus — Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats automatically..

compass — Developer-grade Claude Code + Codex configuration: cost-tiered subagents, workflow commands, guardrail hooks, MCP parity, and an installable plugin/marketplace.

Container Use — Containerized development environments for coding agents, from the Dagger team. Gives each agent its own isolated stack so several can work in parallel without reaching into your host or each other's workspaces.

Dippy — Auto-approve safe bash commands using AST-based parsing, while prompting for destructive operations. Solves permission fatigue without disabling safety. Supports Claude Code, Gemini CLI, and Cursor.

GouvernAI — Runtime guardrails for Claude Code. Auto-approve what's safe, gate what's risky, block what's dangerous. Dual enforcement, full audit trail. MIT.

Gryph — Gryph is a security layer for AI coding agents. It hooks into Claude Code and enforces YAML policy rules that block, warn, or guide actions in real time, then logs every event to a local SQLite database for review and au

machine — One isolated Lima VM per GitHub project — sandboxed Claude Code/Codex, Docker, Node, signed git

Node9 — The Execution Security Layer for the Agentic Era. Providing deterministic "Sudo" governance and audit logs for autonomous AI agents.

Parry-guard — Prompt injection scanner for AI coding tool hooks, written in Rust. Catches injection attacks, leaked secrets, and data exfiltration in tool inputs and outputs by running DeBERTa v3 and optionally Meta Llama Prompt Guard

SkilLock — Pin AI Skill behavior. Block unapproved drift in CI. See exactly what changed in every PR.

SkillSpector — Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks.

Trail of Bits Security Skills — A very professional collection of over a dozen security-focused skills for code auditing and vulnerability detection. Includes skills for static analysis with CodeQL and Semgrep, variant analysis across codebases, fix ve

AB Method — A principled, spec-driven workflow that transforms large problems into focused, incremental missions using Claude Code's specialized sub agents. Includes slash-commands, sub agents, and specialized workflows designed for

Agent 007 — A self-hosted office with a pleasing pixel-art UI where one manager agent, Billion, takes a mission, posts jobs to a board, and reviews and merges pull requests that Claude Code and Codex workers open from their own git

Agent Collab Skills — Claude Code marketplace for multi-agent collaboration — task splitter, output reconciler, adversarial debate, shared memory, acceptance gate. Composes with codex-delegate / gemini-delegate.

AgentSys — Workflow automation system for Claude with a group of useful plugins, agents, and skills. Automates task-to-production workflows, PR management, code cleanup, performance investigation, drift detection, and multi-agent c

Claude Code Harness — A Claude Code development harness that enables reliable high-quality development through an autonomous Plan -> Work -> Review cycle. Well documented and includes an Output Style.

Claude Code Hook Comms (HCOM) — Lightweight CLI tool for real-time communication between Claude Code sub agents using hooks. Enables multi-agent collaboration with @-mention targeting, live dashboard monitoring, and a zero-dependency implementation.

Claude Code PM — Really comprehensive and feature-packed project-management workflow for Claude Code. Numerous specialized agents, slash-commands, and strong documentation.

Claude Code Workflows — Three review workflows developed at an AI-native startup: automated PR code review (dual-loop, GitHub Actions plus slash command), security review against OWASP Top 10 with severity-classified findings, and the widely-co

Claude Squad — A terminal app that manages multiple Claude Code, Codex, and other local agents (including Aider) in separate workspaces, allowing you to work on multiple tasks simultaneously.

claude-intercom — Relays messages between two Claude Code sessions on separate machines using the Channels API, with delivery tracking and per-message reply budget. Pairs sessions belonging to different accounts, which native cross-sessio

Compound Engineering Plugin — A very pragmatic set of well-designed agents, skills, and commands, built around a discipline of turning past mistakes and errors into lessons and opportunities for future growth and improvement. Good documentation.

Consort — Spec-first, test-driven agent framework: runs the build loop against live Lakebase Postgres branches under a deterministic orchestrator, with human-approval gates.

gstack — Garry Tan's (Y Combinator) Claude Code setup and "open source software factory" for managing the development lifecycle end-to-end. Includes a set of agents and in-depth skills/tools along with workflows for advancing a p

Harness — A meta-skill that designs domain-specific agent teams, defines specialized agents, and generates the skills they use. Resources are in Korean but can produce high-quality English-language output.

OpenRig — Combines Claude Code, Codex, and Pi terminal sessions into persistent long-running teams. Agents message each other directly over tmux and queue work to each other, instead of the user relaying messages. Teams and agents

Plannotator — Interactive review UI that intercepts ExitPlanMode via hooks, letting you visually annotate plans with comments, deletions, and replacements before approving or denying with detailed feedback. Has since grown to cover co

Project Workflow System — A set of commands that provide a comprehensive workflow system for managing projects, including task management, code review, and deployment processes.

RIPER Workflow — Structured development workflow enforcing separation between Research, Innovate, Plan, Execute, and Review phases. Features consolidated subagents for context-efficiency, branch-aware memory bank, and strict mode enforce

SuperClaude — A versatile configuration framework that enhances Claude Code with specialized commands, cognitive personas, and development methodologies, such as "Introspection" and "Orchestration".

awesome-ralph — A curated list of resources about Ralph, the AI coding technique that runs AI coding agents in automated loops until specifications are fulfilled.

Ralph for Claude Code — An autonomous AI development framework that enables Claude Code to work iteratively on projects until completion. Features intelligent exit detection, rate limiting, circuit breaker patterns, and comprehensive safety gua

Ralph Wiggum Marketer — A Claude Code plugin that provides an autonomous AI copywriter, integrating the Ralph loop with customized knowledge bases for market research agents. The agents do the research, Ralph writes the copy, you stay in bed.

Ralph Wiggum Plugin — The official Anthropic implementation of the Ralph Wiggum technique for iterative, self-referential AI development loops in Claude Code.

ralph-harness — A CLI that runs Claude Code in a loop, with a fresh `claude -p` process for each iteration in a harness-owned git worktree.

ralph-orchestrator — Ralph Orchestrator implements the simple but effective "Ralph Wiggum" technique for autonomous task completion, continuously running an AI agent against a prompt file until the task is marked as complete or limits are re

The Ralph Playbook — A remarkably detailed and comprehensive guide to the Ralph Wiggum technique, featuring well-written theoretical commentary paired with practical guidelines and advice.

Dynamic Workflow Design Patterns — A Skill based on this extremely well authored article about dynamic workflows. Detailed explanations regarding the Workflow tool and sensible advice covering a range of patterns and anti-patterns.

Charrette — A Claude Code plugin with agent skills for designing software before code is written: brainstorm boards, plans cut into slices and run by subagents, working HTML mockups, development workbenches and layered pull request

napkin-to-blueprint — A five-stage pipeline of Claude Code slash commands and specialized subagents that turns a raw product idea into a build-ready blueprint: an interview-driven brief, researched feature definitions, per-feature specs with

OctoShell — Terminal workspace for Windows and macOS, built on command blocks, that runs Claude Code in git worktrees, one per task, each with its own shell and dev server. Features include Strategy Mode (several agents plan a chang

Caveman — A plugin that conserves message tokens by communicating in fragmented "caveman speak" - sort of a clever form of compression. Now accompanied by a whole caveman ecosystem including a memory system, caveman spec kit, and

Claude Code Infrastructure Showcase — A remarkably innovative approach to working with Skills, the centerpiece of which being a technique that leverages hooks to ensure that Claude intelligently selects and activates the appropriate Skill given the current c

Cooklang skills — Skills and an MCP server that let AI agents work with Cooklang recipes: plain-text .cook recipes and .menu meal plans in a folder you own.

daily.dev — Useful skills and plugins based on daily.dev platform which contains daily curated news from trusted sources. Your agent can pull from curated list of news and real developer insights from 1M+ community.

fable-mode — A Claude skill that activates Fable-style agentic behavior: explicit multi-stage planning, sub-agent delegation, and self-verification.

LinkedIn Skills — A set of skills for LinkedIn marketing: drafting posts, comments and replies, extracting the hook formula from a viral post, planning a week of content, rewriting a profile, and segmenting the people who engaged. Posts a

localpr — Reviews Claude's uncommitted changes in a local GitHub-style pull request page: comment on any line, send comments in batches while Claude keeps working, ask Claude questions answered inline in the thread, and get each c

mcu-skills — A collection of board-specific Claude Code skills for microcontrollers firmware development, one per board, covering STM32, ESP32, ESP8266, RP2040/RP2350, nRF52840 and AVR.Each skill documents pin mapping, clock and peri

Superpowers — A strong bundle of core competencies for software engineering, with good coverage of a large portion of the SDLC - from planning, reviewing, testing, debugging... Well written, well organized, and adaptable. The author r

SuperSEO Skills — A nice package of Claude Skills focused on SEO workflows: page audits, content briefs, article writing, E-E-A-T audits, semantic gap analysis, and more. Each skill fetches the target page and reads the top-ranking compet

Callimachus — One local, searchable index of your AI coding-agent history Claude Code, Codex, Cursor, Gemini & more. Keyword + semantic search, MCP server, CLI & VS Code extension.

capy — 🦫 Privacy-first virtualization layer for LLM context with MCP protocol for tool access.

Claude Mnemonic — Memory management and retrieval for Claude Code

claude-context-optimizer — Claude Code plugin that tracks token usage, identifies wasted context, and saves money on unnecessary API costs, by tracking which information is actually being reused later. Visuals include heatmaps, ROI reports, budget

Context Engineering Kit — Hand-crafted collection of advanced context engineering techniques and patterns with minimal token footprint focused on improving agent result quality.

fable — High-fidelity transcript memory for Claude Code — index every session, recall byte-identical, search, prune, compose. Local-first, stdlib-only, MCP.

faf-cli — Authors and versions CLAUDE.md and AGENTS.md from a repository's actual detected stack, so Claude Code's project context stays in sync with the code instead of drifting. One typed source file (project.faf, an IANA-regist

Hivemind — Hivemind turns your traces into reusable skills across agents

MAMA — Always-on companion for Claude that remembers your decisions and their evolution. Local-first memory using SQLite + transformers.js embeddings.

PLUR — Open, local-first engram memory for Claude Code. Engrams are plain-text YAML you can read, correct, and delete. The same memory is shared across MCP tools and multiple providers.

presence — Per-repo memory, outcome telemetry, and a calibrated-confidence gate for Claude Code, with MCP and AGENTS.md projections so other AI coding tools can read its context. Notes survive sessions; success claims need test evi

roampal-core — Outcome-based persistent memory MCP server for Claude Code and OpenCode. Good advice promoted, bad advice demoted. pip install roampal.

Selvedge — Long-term memory for AI-coded codebases. A git blame for AI agents — but for the why. MCP server that captures the agent's reasoning live, in context, as each change is made. Local SQLite, zero deps.

bough — Reads Claude Code JSONL session transcripts and draws a project's history as a creatively-styled diagram: a day, the tasks inside it, and every prompt, with the ones that ended in a commit marked. Segments work from paus

CC Harness — Desktop workbench that reads Claude Code session files locally and renders the subagent and workflow topology as a live graph, with per-node latency, token cost, and nesting depth. Token spend is broken down by source (b

seedeep — Reads the JSONL session logs Claude Code already writes and shows, live during a turn, what the session is doing: each model call and tool, the context window filling, every subagent on its own window and its own model,

c9watch — A macOS menu-bar app (and companion JSON CLI, built from one Rust/Tauri binary) that auto-discovers running Claude Code sessions by scanning OS processes and shows live working / needs-attention / idle status, plus sessi

cc-semaphore — A lightweight session monitor for parallel Claude Code sessions. Aggregates running/waiting/idle status across sessions into the OS status bar or system tray, with the same experience on native Linux (GNOME Shell extensi

cctop — A live top-style terminal TUI that lists every running Claude Code session with process stats, busy/idle state, context size, model, and git branch, plus a live sub-agent and sub-process tree with open and orphaned ports

Claude Code Agent Monitor — A self-hosted real-time dashboard that monitors Claude Code agent activity via its native hooks — live sessions, subagent orchestration trees, tool-call timelines, and per-session status — keeping data local (loopback-on

Claude Status — A native macOS menu-bar app with desktop widgets showing the live state of every running Claude Code session — active, waiting-for-input, compacting, or idle — across many terminals and IDEs, with one-click focus to any

claude-control — A native macOS Electron dashboard that auto-discovers running Claude Code CLI sessions and shows live per-session status, git changes, PR checks, and conversation previews across repos and worktrees — and can focus, send

claude-status-bar — A tiny, hook-driven macOS menu-bar indicator of Claude Code's live turn status — an animated icon while thinking or running a tool, a dot when awaiting permission, and an elapsed-turn timer — aggregated across concurrent

Clawd on Desk — A desktop pet that reacts to your Claude Code sessions in real-time — thinking, typing, juggling, sleeping, and more. Yep. It's undeniably endearing. And at the end of the day, isn't that what Claude Code is all about?

so-agentbar — A native macOS menu-bar app that watches Claude Code and OpenAI Codex CLI session logs in real time and shows each running session's live status, tokens, and cost, with subagent grouping and an optional animated pixel-ar

wattop — Terminal monitor for Apple Silicon Macs that shows live Claude Code and Codex sessions, including subagent and workflow trees, with output tokens/s, context fill and estimated cost beside CPU/GPU power, temperatures and

AgentWatch — Local-only observability for AI agents on your machine. One timeline across coding and non-coding agents.

better-ccflare — A well-maintained and feature-enhanced fork of the glorious `ccflare` usage dashboard by @snipeship. `better-ccflare` builds on that foundation with performance enhancements, extended provider support, bug fixes, Docker

cc-costline — Enhanced statusline for Claude Code — see your 7d/30d spend at a glance

cc-probeline — See where it leaks, stop paying for it — a live Claude Code status line that prices every turn, your subagents, cache rebuilds, plus limits, context and git.

CCDash — Open-source unified usage dashboard for Claude — track tokens, quota, costs across Claude Code, claude.ai & API in one panel. 开源 Claude 全平台用量监控面板，聚合 Claude Code / claude.ai / API 数据，适用于 Pro/Max 订阅用户与开发者。https://dyp23

ccusage — A zero-install CLI (npx ccusage) that analyzes Claude Code token usage and cost from local JSONL logs — daily, monthly, per-session, and 5-hour-block breakdowns, a live monitoring mode, and per-model cost estimates. Runs

ccvitals — The prettiest statusline for Claude Code — pure bash, never blocks your prompt. Usage quota, context window, git status & more.

ccxray — A transparent HTTP proxy and real-time dashboard that sits between Claude Code and the Anthropic API. Captures every request and response without configuration, presenting them in a Miller-column interface with session g

claude-code-status-bar — Configurable status bar for Claude Code: usage limits with pacing markers, context window, git state, live activity, session cost, and 8 colour themes. Pure bash, zero dependencies.

ClaudeBar — A macOS menu-bar app that surfaces remaining usage quota for Claude, Codex, Gemini, Copilot, and other AI coding providers at a glance, with burn-rate, dollar-balance, and reset-countdown indicators plus a lightweight li

Claumon — Claude Code dashboard for Pro/Max users: live rate-limit gauges, calibrated usage forecasts, session costs, memory browser. Single binary, zero config.

Codeburn — Breakdown of local spend down by project, model, git branch and task. Tracks plan quotas, and identifies token waste, including unused MCP servers, verbose CLAUDE.md, repeated file reads, and more.

context-tax — A zero-dependency CLI (npx context-tax) that reads Claude Code session transcripts to measure what is sent on every turn before the first prompt: system prompt, MCP tool names, the skill listing and instruction files. It

goccc — Fast, zero-dependency cost calculator and customizable statusline for Claude Code. Breakdowns by model, day, project, and branch. Lightweight, single binary, no runtime needed.

Pacer — Native macOS app for tracking Claude Code usage — tokens, cost, rate-limit pacing, per-project breakdowns. SwiftUI + SwiftData.

toktrack — Ultra-fast token & cost tracker for LLM Token Usage (e.g. Claude Code)

agents-observe — A real-time Claude Code observability dashboard installed as a plugin: it registers hooks across the full session lifecycle (tool calls, subagent start/stop, task and permission events) and streams them to a local React

Claude Code Observability Stack — A Dockerized OpenTelemetry-to-Grafana observability stack for Claude Code that implements Anthropic's observability guidance, surfacing session activity, performance, token usage, and cost in prebuilt dashboards.

claude-esp — Go-based TUI that streams Claude Code hidden output (thinking, tool calls, subagents) to a separate terminal. Watch multiple sessions simultaneously, filter by content type, and track background tasks. Ideal for debuggin

Multi-Agent Observability — A real-time dashboard that captures Claude Code hook events across concurrent agents — tracing every tool call, task handoff, and lifecycle event through a Bun/SQLite/WebSocket/Vue stack, with session tracking and live f

OrcaReplay — Records a Claude Code run through a local proxy and replays it offline, reproducing it byte-for-byte with the network off, or forking it from any checkpoint onto a different model. Capture happens below the harness, so s

claude-code-zsh-completion — Zsh completion for the Claude Code CLI. Dynamically completes sessions, MCP servers, agents, models and plugins from the user's configuration.

clausona — A CLI and TUI for running several Claude Code accounts on one machine. Each account gets its own config directory through a shell hook, keeping its own sign-in and history, while plugins, settings, skills, commands and a

Fixing Opus 5 — A single appendable system prompt that retunes Opus 5's communication channel — cutting verbal tics, heading theater, and output-token bloat — passed via `--append-system-prompt-file` with no build step or dependencies.

Rulesync — A Node.js CLI tool that automatically generates configs (rules, ignore files, MCP servers, commands, and subagents) for various AI coding agents. Rulesync can convert configs between Claude Code and other AI agents in bo

tweakcc — Command-line tool to customize your Claude Code installation: themes, thinking verbs, spinners, and input-box styling, plus deeper tweaks like custom toolsets, system-prompt edits, input pattern highlighters, and AGENTS.

Claude Code Agents — Comprehensive E2E development workflow with helpful Claude Code subagent prompts for solo devs. Run multiple auditors in parallel, automate fix cycles with micro-checkpoint protocols, and do browser-based QA. Includes st

TDD Guard — A hooks-driven system that monitors file operations in real-time and blocks changes that violate TDD principles.

agents-md-cookbook — The tested, tool-agnostic AGENTS.md kit — verified templates, a CI linter, and migrators from .cursorrules/CLAUDE.md/Copilot/Windsurf/Cline/Aider.

agnix — The linter and LSP for AI coding assistants — validates CLAUDE.md, AGENTS.md, SKILL.md, hooks, and MCP config, with autofixes and IDE plugins.

BlockWatch — A language-agnostic linter (Rust) that keeps co-dependent code, docs, and config in sync, with a Claude Code plugin skill.

Ctxlint — A CLI linter for AI agent context files that catches stale references, dead commands, and hardcoded secrets, with a modular tested rule set.

Schliff — Deterministic quality scorer for AI agent instruction files — 8-dimension scoring with security, multi-format (SKILL.md, CLAUDE.md, .cursorrules, AGENTS.md), anti-gaming detection, zero dependencies

Upkeep — Upkeep — an AI audit crew for your repo. Catches docs/spec/asset drift with evidence; output-only. Claude Code plugin/skill + reusable CI workflow.

Claude CodePro — Professional development environment for Claude Code with spec-driven workflow, TDD enforcement, cross-session memory, semantic search, quality hooks, and modular rules integration. A bit "heavyweight" but feature-packed

claude-code-tools — Well-crafted toolset for session continuity, featuring skills/commands to avoid compaction and recover context across sessions with cross-agent handoff between Claude Code and Codex CLI. Includes a fast Rust/Tantivy-powe

Everything Claude Code (ECC) — Top-notch, well-written resources covering "just about everything" from core engineering domains. What's nice about this "everything-" store is most of the resources have significant standalone value and unlike some all-

Fullstack Dev Skills — A comprehensive Claude Code plugin with 65 specialized skills covering full-stack development across a wide range of specific frameworks. Features 9 project workflow commands for Jira/Confluence integration and, notably,

TÂCHES Claude Code Resources — A well-balanced, "down-to-Earth" set of sub agents, skills, and commands, that are well-organized, easy to read, and a healthy focus on "meta"-skills/agents, like "skill-auditor", hook creation, etc. - the kind of thing

Browse by category

by buildlog · AGENTS.md generator

Get one practical AI/dev tip a week

Free. No spam. Unsubscribe anytime.

Browse 31 MCP server install guides →