crw-mcp
MCP (Model Context Protocol) stdio proxy for the CRW web scraper.
Overview
crw-mcp is a lightweight stdio binary that bridges MCP-compatible AI clients (Claude Code, Claude Desktop, Cursor, Windsurf, Cline, Continue.dev) to a running CRW server. It reads JSON-RPC requests from stdin, forwards them to the CRW HTTP API, and writes responses to stdout.
4 MCP tools:
| Tool | Description |
|---|---|
crw_scrape |
Scrape a single URL → markdown, HTML, JSON, links |
crw_crawl |
Start an async BFS crawl (returns job ID) |
crw_check_crawl_status |
Poll crawl job status and retrieve results |
crw_map |
Discover all URLs on a website |
Installation
Prerequisites
A running CRW server instance:
Environment variables
| Variable | Default | Description |
|---|---|---|
CRW_API_URL |
http://localhost:3000 |
CRW server base URL |
CRW_API_KEY |
(none) | Optional Bearer token for authenticated servers |
Setup by client
Claude Code
Or use the HTTP transport directly (no binary needed):
Claude Desktop
Edit your config file:
| OS | Path |
|---|---|
| macOS | ~/Library/Application Support/Claude/claude_desktop_config.json |
| Windows | %APPDATA%\Claude\claude_desktop_config.json |
| Linux | ~/.config/Claude/claude_desktop_config.json |
Cursor
Edit ~/.cursor/mcp.json (global) or .cursor/mcp.json (project):
Windsurf
Edit ~/.codeium/windsurf/mcp_config.json:
Cline (VS Code)
Continue.dev (VS Code / JetBrains)
Edit ~/.continue/config.yaml:
mcpServers:
- name: crw
command: crw-mcp
env:
CRW_API_URL: http://localhost:3000
OpenAI Codex CLI
Edit ~/.codex/config.toml:
[]
= "crw-mcp"
[]
= "http://localhost:3000"
Any MCP client
Tip: For clients that support HTTP transport, use
http://localhost:3000/mcpdirectly — no stdio binary needed.
With authentication
If your CRW server requires auth:
With remote / cloud server
Point to fastcrw.com or any remote CRW instance:
Part of CRW
This crate is part of the CRW workspace — a fast, lightweight, Firecrawl-compatible web scraper built in Rust.
| Crate | Description |
|---|---|
| crw-core | Core types, config, and error handling |
| crw-renderer | HTTP + CDP browser rendering engine |
| crw-extract | HTML → markdown/plaintext extraction |
| crw-crawl | Async BFS crawler with robots.txt & sitemap |
| crw-server | Firecrawl-compatible API server |
| crw-cli | Standalone CLI (crw binary) |
| crw-mcp | MCP stdio proxy binary (this crate) |
License
AGPL-3.0 — see LICENSE.