CrawlEyes MCP Server

CrawlEyes gives AI agents reliable full-text extraction (web_extract) and robust search (web_search) backends - the "eyes" that let agents see and read the web. Built and tested against Hermes Agent. It runs locally over stdio via the published package.

People who work with crawl4ai, rag and scraper and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-09-09 · ★ 2 · #50 OF 93 MAINTAINED WEB SCRAPING · VERIFIED 2026-09-18

MIT · Python servers · how we verify → /methodology

01 · Install CrawlEyes MCP Server

before you install - you'll need

Set PLAYWRIGHT_DOWNLOAD_HOST, SEARXNG_URL before connecting.

Claude Code

claude mcp add waiky-github-crawleyes -- uvx crawleyes

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "waiky-github-crawleyes": {
      "command": "uvx",
      "args": [
        "crawleyes"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

repo age created 2026-08-31 - young repo, little track record yet

license MIT - declared in the repository

pypi package crawleyes - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.waiky-github is GitHub-verified and matches the repo owner

03 · Who maintains CrawlEyes MCP Server

CrawlEyes MCP Server is maintained by waiky-github. It's the only MCP server we track from this author; the repo dates to Aug 2026.

04 · Facts

repository: github.com/waiky-github/crawleyes
website: https://github.com/waiky-github/CrawlEyes
category: web scraping - ranked #50 of 93 actively-maintained web scraping servers as of 2026-09-18.
registry: io.github.waiky-github/CrawlEyes (active, first published 2026-08-31 · 2 versions)
packages: pypi:crawleyes

05 · CrawlEyes MCP Server FAQ

What is CrawlEyes MCP Server?

Is CrawlEyes MCP Server still maintained?

Yes - as of 2026-09-18, its last commit was 2026-09-09. We re-verify nightly.

How do I install CrawlEyes MCP Server?

Run `uvx crawleyes`. The README documents 2 environment variables (PLAYWRIGHT_DOWNLOAD_HOST, SEARXNG_URL) to set first. Set PLAYWRIGHT_DOWNLOAD_HOST, SEARXNG_URL before connecting. You can also paste the ready-made client config above.

Does CrawlEyes MCP Server run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

06 · Alternatives to CrawlEyes MCP Server

Alternatives to CrawlEyes MCP Server

Maintained web scraping servers if CrawlEyes MCP Server isn't the fit.

Pairs well with

Servers that cover what CrawlEyes MCP Server doesn't - only shown when the pairing reason fits the companion.

More web scraping MCP servers · Web Scraping AI · Wopee MCP · Crawlberg · Xquik MCP Server · AI-First Scraper

More Python MCP servers · Quarry · Wechat Devtools MCP · Wattcoin MCP Server · Wavix · Wayforth · see all