Crawlberg
Crawlberg is an MCP server that adds web browsing tools to AI assistants such as Claude Desktop, Claude Code and Cursor. Scrape, crawl, and map websites to Markdown or JSON via local CLI. It has 182 GitHub stars, is released under the MIT license and runs locally with docker run -i --rm ghcr.io/xberg-io/crawlberg:1.10.2.
- Web & browsing
- MIT
- Actively maintained
Install Crawlberg
Generated from the server's MCP registry entry. Replace your-value with your own values.
Claude Desktop
{
"mcpServers": {
"crawlberg": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/xberg-io/crawlberg:1.10.2"
]
}
}
}Settings > Developer > Edit Config. macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\. Restart Claude Desktop afterwards.
Claude Code
claude mcp add --transport stdio crawlberg -- docker run -i --rm ghcr.io/xberg-io/crawlberg:1.10.2Cursor
{
"mcpServers": {
"crawlberg": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/xberg-io/crawlberg:1.10.2"
]
}
}
}Project file; use ~/.cursor/mcp.json to enable it in every project.
VS Code
{
"servers": {
"crawlberg": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/xberg-io/crawlberg:1.10.2"
]
}
}
}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 Crawlberg
Turn any website into clean, structured data. Point Crawlberg at a URL and get back Markdown, metadata, and links — from a single page or a whole site — in the language you already use.
- crawling
- csharp
- elixir
- ffi
- golang
- java
- mcp
- php
- python
- ruby
Similar MCP servers
More web & browsing MCP servers
Browser Use
browser-use/browser-use
Control a real Chrome browser to complete any task: fill forms, extract data, book flights.
OfficialWeb & browsingPythonScrapling MCP Server
D4Vinci/Scrapling
Web scraping with stealth HTTP, real browsers, and Cloudflare bypass.
Web & browsingPythonChrome DevTools MCP
ChromeDevTools/chrome-devtools-mcp
MCP server for Chrome DevTools.
Web & browsingTypeScriptBytedance Browser
bytedance/UI-TARS-desktop
MCP server for browser use access.
Web & browsingTypeScriptBytedance Commands
bytedance/UI-TARS-desktop
An MCP server to run arbitrary commands.
Web & browsingTypeScriptBytedance Search
bytedance/UI-TARS-desktop
MCP server for web search operations.
Web & browsingTypeScript
What is Crawlberg?
Crawlberg is an MCP server that adds web browsing tools to AI assistants such as Claude Desktop, Claude Code and Cursor. Scrape, crawl, and map websites to Markdown or JSON via local CLI. It has 182 GitHub stars, is released under the MIT license and runs locally with docker run -i --rm ghcr.io/xberg-io/crawlberg:1.10.2. The source code is at github.com/xberg-io/crawlberg.
How do I install the Crawlberg MCP server?
Add the command docker run -i --rm ghcr.io/xberg-io/crawlberg:1.10.2 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 Crawlberg free?
The server is open source under the MIT license, so running it is free. It does not declare any required API key.
Is Crawlberg actively maintained?
The most recent commit was on Oct 6, 2026. The latest release is v1.10.2, published Oct 6, 2026. appsgit only lists MCP servers with a commit in the last six months and re-checks every server daily.