CRW Web Scraper
CRW Web Scraper is an MCP server that adds web browsing tools to AI assistants such as Claude Desktop, Claude Code and Cursor. Open-source web scraper for AI agents with scrape, crawl, and map tools. It has 1,261 GitHub stars, is released under the AGPL-3.0 license and runs locally with docker run -i --rm ghcr.io/fastcrw/crw:latest.
github.com/fastcrw/crw (opens in a new tab)
Data as of from the GitHub API and the official MCP registry; description from the project's repository. Report an error
Install CRW Web Scraper
Generated from the server's MCP registry entry. Replace your-value with your own values.
Claude Desktop
{
"mcpServers": {
"crw-web-scraper": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/fastcrw/crw:latest"
]
}
}
}Settings > Developer > Edit Config. macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\. Restart Claude Desktop afterwards.
Claude Code
claude mcp add --transport stdio crw-web-scraper -- docker run -i --rm ghcr.io/fastcrw/crw:latestCursor
{
"mcpServers": {
"crw-web-scraper": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/fastcrw/crw:latest"
]
}
}
}Project file; use ~/.cursor/mcp.json to enable it in every project.
VS Code
{
"servers": {
"crw-web-scraper": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/fastcrw/crw:latest"
]
}
}
}Config formats checked against the official docs on Oct 7, 2026: modelcontextprotocol.io (opens in a new tab), code.claude.com (opens in a new tab), cursor.com (opens in a new tab), code.visualstudio.com (opens in a new tab).
About CRW Web Scraper
Turn URLs into clean markdown or structured JSON with one engine for search, scrape, map, crawl, and extract. Run it locally as a small Rust binary or use the managed API.
- ai
- ai-agents
- crawler
- data-extraction
- docker
- html-to-markdown
- llm
- markdown
- mcp
- rust
Similar MCP servers
More web & browsing MCP servers
AutoTS
winedarksea/AutoTS
Automated time series forecasting with model search, anomaly detection, and event risk analysis.
Active · last commit Nov 9, 2026
Web & browsingPythonAgent Mesh
google/agentmesh
Discover and call remote MCP tools as your own authenticated Agent Mesh member.
Active · last commit Nov 11, 2026
OfficialWeb & browsingGoWebPerf Snippets
nucliweb/webperf-snippets
Measure Core Web Vitals and debug web performance with 56 snippets in a headless Chromium.
Active · last commit Nov 15, 2026
Web & browsingJavaScriptFetcher MCP
jae-jae/fetcher-mcp
MCP server for fetch web page content using Playwright headless browser.
Maintained · last commit Nov 5, 2026
Web & browsingTypeScriptActionbook
actionbook/actionbook
Let your AI agent operate any website through a real, logged-in browser session.
Active · last commit Oct 19, 2026
OfficialWeb & browsingRustUnbrowse
unbrowse-ai/unbrowse
Websites as APIs: read pages, run site tasks via learned APIs, cloud browser with saved logins.
Active · last commit Nov 13, 2026
Web & browsingTypeScript
How do I install the CRW Web Scraper MCP server?
Add the command docker run -i --rm ghcr.io/fastcrw/crw:latest to your MCP client: put it in claude_desktop_config.json for Claude Desktop, run claude mcp add for Claude Code, or add it to .cursor/mcp.json (Cursor) or .vscode/mcp.json (VS Code). The snippets on this page are ready to paste.
Is CRW Web Scraper free?
The server is open source under the AGPL-3.0 license, so running it is free. It does not declare any required API key.
Is CRW Web Scraper actively maintained?
The most recent commit was on Nov 16, 2026. The latest release is v0.45.0, published Nov 16, 2026. appsgit only lists MCP servers with a commit in the last six months.