# Crawl4AI MCP Server

> Self-hosted web crawling and content extraction exposed as MCP tools, with depth control and clean markdown output.

- Skill: `agentskillexchange/crawl4ai-mcp-server` (Agent Skill)
- Install (CLI): `npx skillmds add agentskillexchange/crawl4ai-mcp-server`
- Raw SKILL.md: https://api.skillmd.com/api/skills/agentskillexchange/crawl4ai-mcp-server/raw
- Safety review: CAUTION (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML, Web & Frontend, Browser Automation, MCP Servers
- Tags: Content Extraction, Crawl4ai, Docker, Mcp, Playwright, Web Scraping
- Author: agentskillexchange (https://skillmd.com/u/agentskillexchange)
- Updated: 2026-08-22
- Page: https://skillmd.com/skills/agentskillexchange/crawl4ai-mcp-server

---


# Crawl4AI MCP Server

Self-hosted web crawling and content extraction exposed as MCP tools. Scrape pages, crawl sites with depth control, and extract clean markdown — all self-hosted and free.

## Prerequisites

MCP-compatible client, Python 3.10+ with Playwright or Docker

## Installation

Use the upstream install or setup path that matches your environment:
- Docker eliminates all setup complexity and provides a consistent environment:
- docker pull uysalsadi/crawl4ai-mcp-server:latest
- git clone https://github.com/uysalsadi/crawl4ai-mcp-server.git
- docker build -f Dockerfile.simple -t crawl4ai-mcp .

Requirements and caveats from upstream:
- Choose between **Docker** (recommended) or **manual installation**:
- ### Option A: Docker (Recommended) 🐳
- python test-config.py

Basic usage or getting-started notes:
- ## 🚀 Quick Start
- # No setup required! Just pull and run the published image

- Source: https://github.com/sadiuysal/crawl4ai-mcp-server
- Extracted from upstream docs: https://raw.githubusercontent.com/sadiuysal/crawl4ai-mcp-server/HEAD/README.md

## Documentation

- https://docs.crawl4ai.com/

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/crawl4ai-mcp-server/)