Skip to content
MCP server

MCP

Scrape pages and map sites from an agent, processed on EU servers

Runs locallyStatus and history
Install
Pricing
Freemium
Platforms
CLI, API
Runs
Locally
Version
1.4.0
Listing updated
3 days ago

About MCP

MCP is a freemium MCP server for web search and scraping. It runs locally on your machine and is started by your AI client.

Every call goes through crawlbrulee's scraping API, so the server needs an API key in the CRAWLBRULEE_API_KEY environment variable. It reads the key on the first tool call rather than at startup, which means a mistyped key shows up as a clear tool error instead of a server that fails to start.

A single request can return clean markdown, cleaned or raw HTML, links, images, page metadata or a screenshot. Full-page screenshots can come back as tiles sized for an image model. Behind the call, the service tries a plain HTTP fetch first and steps up to headless Chrome or a stronger proxy tier only when a page needs it, and a repeat request for the same URL is served from cache.

The vendor is an EU-registered company and says fetching, rendering, caching and stored results stay on EU servers, with the proxy exit as the one hop you choose. Results are deleted within 90 days, and enterprise customers can ask for zero data retention. The server is a thin adapter over the vendor's SDK and runs over stdio via npx.

Install

Run in a terminal

claude mcp add mcp --env CRAWLBRULEE_API_KEY='<CRAWLBRULEE_API_KEY>' -- npx -y @crawlbrulee/mcp

Add to claude_desktop_config.json

{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@crawlbrulee/mcp"
      ],
      "env": {
        "CRAWLBRULEE_API_KEY": "<CRAWLBRULEE_API_KEY>"
      }
    }
  }
}

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@crawlbrulee/mcp"
      ],
      "env": {
        "CRAWLBRULEE_API_KEY": "<CRAWLBRULEE_API_KEY>"
      }
    }
  }
}

Add to .vscode/mcp.json

{
  "servers": {
    "mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@crawlbrulee/mcp"
      ],
      "env": {
        "CRAWLBRULEE_API_KEY": "<CRAWLBRULEE_API_KEY>"
      }
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@crawlbrulee/mcp"
      ],
      "env": {
        "CRAWLBRULEE_API_KEY": "<CRAWLBRULEE_API_KEY>"
      }
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@crawlbrulee/mcp"
      ],
      "env": {
        "CRAWLBRULEE_API_KEY": "<CRAWLBRULEE_API_KEY>"
      }
    }
  }
}

Configuration

  • CRAWLBRULEE_API_KEYyour crawlbrulee api key. get a free one at https://dashboard.crawlbrulee.comRequired

Tools this server provides (1)

Taken from the project documentation; the running server may differ.

scrape
Fetch a single URL and return markdown, HTML, links, images, a screenshot or page metadata.

What it does

Single-call scraping
One URL returns markdown, HTML, links, images, metadata or screenshots.
Site mapping
Discover the pages of a whole site, not just one URL.
Background jobs
Start longer scrapes as background jobs and check on them later.
Usage checks
Ask the server how many credits have been used.
EU proxy exit
Choose an EU proxy exit with one field so traffic stays in the EU.
Screenshot tiles
Full-page screenshots can be sliced into tiles an image model can read.

Good for

  • Feed clean page markdown into a RAG pipeline
  • Map every page of a documentation site before crawling it
  • Capture mobile or desktop screenshots for a vision model to inspect
  • Scrape pages for EU-based teams that need GDPR-aligned processing

Pricing

Freemium

Free plan with 750 credits a month; paid plans from EUR 29 a month, billed in euros

Prices change. Check crawlbrulee.com before you buy.

MCP FAQ

What do I need to run it?

A crawlbrulee API key in CRAWLBRULEE_API_KEY. The free plan needs no credit card.

How is scraping billed?

In credits: 1 for an HTTP scrape or map call, 3 for a browser scrape, 5 for a screenshot. A failed scrape or a full cache hit costs nothing, and the advanced proxy multiplies the price by five.

Which clients does it work with?

The README names Claude Code, Codex, Cursor and Claude Desktop, over stdio.

Where is data processed?

The vendor says fetch, render, cache and stored results stay on EU servers, with results deleted within 90 days.

Is MCP free?

MCP has a free plan, with paid plans for more usage or features.

How do I add MCP to Claude Code?

Run this command in your terminal: claude mcp add mcp --env CRAWLBRULEE_API_KEY='<CRAWLBRULEE_API_KEY>' -- npx -y @crawlbrulee/mcp

What are the best alternatives to MCP?

The closest alternatives to MCP are Scrapling MCP Server, Firecrawl MCP Server, SearXNG Search, NeuralVerge and AI-Powered directory.

Alternatives to MCP

  1. MCP server for AI clients to scrape sites with HTTP and stealth browser sessions

    Runs locally
    • 17 tools
    • Open source
    • 104K GitHub stars
    • Web search and scraping
  2. MCP server that lets AI agents search, scrape and interact with web pages

    • 3 tools
    • Remote
    • Freemium
    • 7.8K GitHub stars
    • Web search and scraping
  3. SearXNG Search

    MCP server

    MCP server for web search and page reading through a SearXNG instance

    Runs locally
    • 3 tools
    • Open source
    • 1.4K GitHub stars
    • Web search and scraping
  4. NeuralVerge

    MCP server

    Structured, source-tagged business and people data from 300+ sources for agents

    • 200 tools
    • Remote
    • Free trial
    • 1 GitHub star
    • Web search and scraping
  5. Search AI tools, agents and MCP servers and get install configs from inside your AI assistant.

    • 4 tools
    • Remote
    • Free
    • Developer tools
  6. Hosted MCP server that returns any Shopify store's products, prices and stock

    Not checked yet
    • 4 tools
    • Remote
    • Paid
    • E-commerce