# Crawl4AI

> Use this tool when you need to systematically extract and analyze web content at scale, from simple page scraping to complex multi-page site analysis workflows. It provides web crawling and content extraction capabilities through 11 specialized tools, including page crawling, screenshot capture, and PDF generation. With flexible filtering options and advanced features like recursive crawling, it solves problems related to content extraction, data analysis, and automation, taking in URLs and keywords as input and outputting extracted content and metadata.

Canonical page: https://skillsregistry.net/skills/crawl4ai  
JSON: https://api.skillsregistry.net/v1/skills/crawl4ai

## Description

TypeScript MCP server that provides web crawling and content extraction capabilities through integration with Crawl4AI, a Python-based web crawling service. The implementation offers 11 specialized tools including basic page crawling with markdown extraction, screenshot capture, PDF generation, JavaScript execution, batch processing, and intelligent content type detection for sitemaps and RSS feeds. Built with comprehensive error handling, flexible filtering options, and advanced features like recursive crawling with depth control and custom header support, it's designed for AI assistants that need to systematically extract and analyze web content at scale, from simple page scraping to complex multi-page site analysis workflows.

## Trust

- **Trust score (0–1):** 0.96
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** browser-automation
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/crawl4ai)
- **Repository:** <https://github.com/omgwtfwow/mcp-crawl4ai-ts>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "crawl4ai"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/crawl4ai` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/crawl4ai/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt