# crawl4ai-mcp

> Use this tool when you need to automate web data extraction and crawling for AI agents, solving problems such as accessing dynamic web content and extracting specific data formats like markdown and HTML. It takes in URLs and other web page identifiers as input and outputs extracted data, screenshots, and generated PDFs. Ideal for use cases requiring universal web crawling and data extraction, such as data mining, monitoring, and research applications.

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

## Description

MCP server integrating Crawl4AI for universal web crawling and data extraction. Enables AI agents to crawl, extract markdown/HTML, take screenshots, generate PDFs, and execute JavaScript on web pages.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** browser-automation
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/czingh8x43)
- **Repository:** <https://github.com/stgmt/crawl4ai-mcp>

## 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": "stgmt-crawl4ai-mcp"
    }
  }
}
```

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