Crawlforge MCP Server

31 web scraping, crawling, deep-research & autonomous-extraction tools for Claude, Cursor & any MCP client. It runs locally over stdio via the published package.

People who work with crawler, data extraction and deep research and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in JavaScript.

VERIFIED ACTIVE

LAST COMMIT 2026-09-17 · ★ 2 · #12 OF 93 MAINTAINED WEB SCRAPING · VERIFIED 2026-09-18

MIT · JavaScript servers · how we verify → /methodology

01 · Install Crawlforge MCP Server

before you install - you'll need

Set CRAWLFORGE_API_KEY, CRAWLFORGE_API_URL, OLLAMA_API_KEY, DISABLE_OLLAMA, OPENAI_API_KEY, ANTHROPIC_API_KEY, CRAWLFORGE_TOOLS, CRAWLFORGE_TOOL_GROUPS before connecting. OLLAMA_BASE_URL, OLLAMA_DEFAULT_MODEL, OLLAMA_EMBEDDING_MODEL, RESEARCH_STEALTH_ENGINE are optional or environment-specific per the README.

Claude Code

claude mcp add mysleekdesigns-crawlforge-mcp -- npx -y crawlforge-mcp-server

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "mysleekdesigns-crawlforge-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "crawlforge-mcp-server"
      ]
    }
  }
}

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

license MIT - declared in the repository

npm package crawlforge-mcp-server - unscoped; check the name against the project README before installing

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

03 · What Crawlforge MCP Server can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

Latest releases

v6.6.2 · 2026-09-13

A second live round on browser_session, re-testing 6.6.1 across long articles, an SPA, a login app, concurrent sessions and a bot-protected site. Everything 6.6.1 fixed held. Three defects underneath it did not, and…

v6.6.1 · 2026-09-13

The first live test of browser_session since 6.6.0 shipped, across five kinds of site: a static news front page, a client-rendered SPA, a login app, an e-commerce catalog, and a real bot-protected commercial site. The…

v6.6.0 · 2026-09-13

Interactive browser sessions, and the observation primitive underneath them. · scrape_with_actions had to be handed every action up front, choosing CSS selectors for a page it had never seen, and the browser closed…

04 · Who maintains Crawlforge MCP Server

crawlforge-mcp-server is maintained by mysleekdesigns. It's the only MCP server we track from this author; the repo dates to Aug 2025.

05 · Facts

repository: github.com/mysleekdesigns/crawlforge-mcp
website: https://www.crawlforge.dev/
category: web scraping - ranked #12 of 93 actively-maintained web scraping servers as of 2026-09-18.
release cadence: 10+ releases in the last 90 days (latest 2026-09-13)
registry: io.github.mysleekdesigns/crawlforge-mcp-server (active, first published 2026-06-07 · 55 versions)
packages: npm:crawlforge-mcp-server

06 · Crawlforge MCP Server FAQ

What is Crawlforge MCP Server?

31 web scraping, crawling, deep-research & autonomous-extraction tools for Claude, Cursor & any MCP client. It runs locally over stdio via the published package.

Is Crawlforge MCP Server still maintained?

Yes - as of 2026-09-18, its last commit was 2026-09-17 and it shipped 10+ releases in the last 90 days. We re-verify nightly.

How do I install Crawlforge MCP Server?

Run `npx -y crawlforge-mcp-server`. The README documents 12 environment variables (CRAWLFORGE_API_KEY, CRAWLFORGE_API_URL, OLLAMA_BASE_URL…) to set first. Set CRAWLFORGE_API_KEY, CRAWLFORGE_API_URL, OLLAMA_API_KEY, DISABLE_OLLAMA, OPENAI_API_KEY, ANTHROPIC_API_KEY, CRAWLFORGE_TOOLS, CRAWLFORGE_TOOL_GROUPS before connecting. OLLAMA_BASE_URL, OLLAMA_DEFAULT_MODEL, OLLAMA_EMBEDDING_MODEL, RESEARCH_STEALTH_ENGINE are optional or environment-specific per the README. You can also paste the ready-made client config above.

Does Crawlforge MCP Server run locally?

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

07 · Alternatives to Crawlforge MCP Server

Alternatives to Crawlforge MCP Server

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

Pairs well with

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

More web scraping MCP servers · Wet MCP · Getregdata · Novada MCP · Proxy4agents MCP · Octen MCP

More JavaScript MCP servers · aikstockdata - Korean Stock Data · Pickanagency · Socialclaw · Chromeflow · Abapilot · see all