crw MCP server

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

Category: Search & Data Extraction · Source: us/crw

Install in Claude Code

claude mcp add crw-mcp -- npx -y crw-mcp@latest

Add to .cursor/mcp.json (project) or ~/.cursor/mcp.json (global):

{
  "mcpServers": {
    "crw-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "crw-mcp@latest"
      ]
    }
  }
}

Add to .vscode/mcp.json:

{
  "servers": {
    "crw-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "crw-mcp@latest"
      ]
    }
  }
}

The same mcpServers block works in Claude Desktop (claude_desktop_config.json), Windsurf and most other MCP clients.

Config taken from the project README. Check the repository for the latest options before running third-party code.

string-ai-mcp — Search the web, fetch URLs and map sites as clean Markdown, getting past anti-bot blocks.
mcp-server — Web page data: scrape to Markdown, extract metadata, links and JSON-LD, audit on-page SEO, detect tech stacks
youtube-mcp — YouTube transcripts (text, JSON, SRT, VTT, srv3), video and channel search, playlists and large batch jobs.
quantumproxies-mcp — Residential-proxy web access: scrape pages to Markdown, SERP search, site mapping and crawling, ready-made col
crawdar-mcp — Evidence-backed business discovery and lead-list research: search by brief or criteria, inspect qualification
muumuu-domain-mcp — Search and register Muumuu Domain (GMO Pepabo) domains, manage owned domains and contracts, and configure DNS
mcp-server-dumplingai — Access Dumpling AI's data, web scraping and document conversion APIs.
mcp — Web scraping that escalates from direct fetch to rotating proxy to full browser, solving anti-bot challenges a