Skip to content
MCP server

CRW Web Scraper

Open-source web scraper for agents with scrape, crawl, map and search tools

Runs locallyStatus and history
Pricing
Freemium
Platforms
CLI, API, self-hosted
Runs
Locally
Version
0.45.1
Listing updated
3 days ago

About CRW Web Scraper

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

CRW is a Rust engine that turns URLs into markdown, JSON, HTML or screenshots. The registry lists a stdio server run from the ghcr.io/fastcrw/crw container image, and the README also gives a one-command installer, npx -y crw-mcp@latest install, that sets up the skill and server in detected AI tools such as Claude Code, Cursor, Codex, Gemini CLI, OpenCode and Windsurf.

Operations are scrape, crawl, map, search and extract, with the same API in the managed cloud and the self-hosted binary. The site also lists monitoring for page changes and PDF parsing. Its README and site report benchmark numbers against Firecrawl, which are the project's own claims.

The engine is AGPL-3.0, a single binary of about 8 MB, free to self-host, with a commercial licence available. Cloud plans give 500 credits free, then Hobby at $11 a month billed yearly or $13 monthly; one credit buys one page and search costs 2.

Install

Run in a terminal

claude mcp add crw -- docker run -i --rm ghcr.io/fastcrw/crw:latest

Add to claude_desktop_config.json

{
  "mcpServers": {
    "crw": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/fastcrw/crw:latest"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "crw": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/fastcrw/crw:latest"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "crw": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/fastcrw/crw:latest"
      ]
    }
  }
}

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

{
  "mcpServers": {
    "crw": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/fastcrw/crw:latest"
      ]
    }
  }
}

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

{
  "mcpServers": {
    "crw": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/fastcrw/crw:latest"
      ]
    }
  }
}

Tools this server provides (3)

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

scrape
Scrape a URL into markdown or other formats
crawl
Crawl a site
map
Discover URLs on a domain

What it does

Scrape to markdown
Turns a URL into markdown, HTML, JSON, links or screenshots.
Crawl and map
Follow a bounded site crawl or list URLs without scraping each.
Search with content
Search the web and optionally scrape results.
Structured extract
Pull JSON fields using a prompt or schema.
Self-host or cloud
Same endpoints on a local binary or the managed API.
Agent installer
One command wires the skill and server into detected tools.

Good for

  • Give a coding agent web access for research
  • Crawl a docs site into markdown for RAG
  • Extract structured product data from pages
  • Monitor a page for changes

Pricing

Freemium, from $11 a month

Free self-hosting (AGPL-3.0); cloud free 500 credits, Hobby from $13/mo ($11 billed yearly)

Prices change. Check fastcrw.com before you buy.

CRW Web Scraper FAQ

Is it open source?

Yes, the engine is AGPL-3.0, and a commercial licence is available.

What does the cloud cost?

500 free credits, then plans from $13 a month monthly or $11 billed yearly.

Does the cloud API differ from self-hosting?

The scrape, crawl, map and search endpoints are identical.

How do I add it to my agent?

Run npx -y crw-mcp@latest install, or use the container image over stdio.

Is CRW Web Scraper free?

CRW Web Scraper has a free plan, with paid plans for more usage or features. Paid plans start at $11 a month.

How do I add CRW Web Scraper to Claude Code?

Run this command in your terminal: claude mcp add crw -- docker run -i --rm ghcr.io/fastcrw/crw:latest

What are the best alternatives to CRW Web Scraper?

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

Alternatives to CRW Web Scraper

  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