AI Plugin Index
Crawlberg
CommunityMCP server by xberg-io · updated · ★ 186
Scrape, crawl, and map websites to Markdown or JSON via local CLI. Crawlberg is a community project by xberg-io, not verified by a company domain.
Last commit 2 days ago
MIT: permissive, fine for commercial use
Clear description, published package or server URL, 186 stars, original repository
Not checked yet. What we check
Install Crawlberg
Built from the published package, never by AIclaude mcp add crawlberg -- docker run -i --rm ghcr.io/xberg-io/crawlberg:1.11.0Run in your terminal. Add --scope user to use it in every project.
{
"mcpServers": {
"crawlberg": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/xberg-io/crawlberg:1.11.0"
]
}
}
}Settings, Developer, Edit config. Paste into claude_desktop_config.json and restart.
{
"mcpServers": {
"crawlberg": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/xberg-io/crawlberg:1.11.0"
]
}
}
}Add to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project).
{
"servers": {
"crawlberg": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/xberg-io/crawlberg:1.11.0"
]
}
}
}Add to .vscode/mcp.json. VS Code uses "servers", not "mcpServers".
codex mcp add crawlberg -- docker run -i --rm ghcr.io/xberg-io/crawlberg:1.11.0{
"mcpServers": {
"crawlberg": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/xberg-io/crawlberg:1.11.0"
]
}
}
}Add to ~/.gemini/config/mcp_config.json (all projects) or .agents/mcp_config.json (this project).
gemini mcp add crawlberg docker run -i --rm ghcr.io/xberg-io/crawlberg:1.11.0Gemini CLI was replaced by Antigravity CLI in June 2026 and remains only for enterprise licences and paid API keys.
MCP servers run with your permissions and can read what you give them access to. Some need an API key: check the README and add it under env in the crawlberg block.
Alternatives to Crawlberg
All alternatives →
Control a real Chrome browser to complete any task: fill forms, extract data, book flights.
Let your AI agent operate any website through a real, logged-in browser session.
Dark web OSINT over Tor: search onion engines, scrape pages, report with your own model.
Web scraping with stealth HTTP, real browsers, and Cloudflare bypass. CSS selectors supported.
draw.io diagrams your AI agent draws on a live browser canvas that you can also edit by hand
AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.
Crawlberg: common questions
How do I install Crawlberg?
In Claude Code run claude mcp add crawlberg -- docker run -i --rm ghcr.io/xberg-io/crawlberg:1.11.0. For Claude Desktop, Cursor and VS Code, paste the config shown above and restart. See the install guides.
Is Crawlberg the official server?
Crawlberg is a community project by xberg-io, not verified by a company domain.
Is Crawlberg free?
The code is published under the MIT licence. The service it connects to may have its own pricing.
Is Crawlberg safe to use?
It scores 80 of 100. Grades: maintenance A, licence A, quality B. The security check has not run for it yet. Review the code before you install. How grades work.
What are alternatives to Crawlberg?
Similar MCP servers: browser-use, Actionbook, Robin: AI-Powered Dark Web OSINT, Scrapling MCP Server.
Does Crawlberg work with ChatGPT?
Not directly. It runs locally, and ChatGPT only connects to remote servers with a URL. Use it in Claude Code, Claude Desktop, Cursor, VS Code or Codex.