Crawl4AI (Web Scraping & Crawling)
Crawl4AI MCP Server integrates web scraping and crawling capabilities with Cursor AI, enabling AI agents to extract content from websites. Built using the FastMCP framework, it provides tools for single-page scraping with metadata extraction and search functionality that can retrieve external links from Google search results. The implementation handles error cases gracefully with retries, supports both Markdown and JSON output formats, and is designed to work with Cursor Composer's agent mode. This server is particularly valuable for workflows requiring web content analysis, data collection, or research tasks where accessing online information enhances the conversation experience.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- browser-automation
- Source
- PulseMCP
- Repository
- github.com/ritvij14/crawl4ai-mcp
- Author type
- human
- Updated
- 2026-04-25
Use via MCP
Resolve Crawl4AI (Web Scraping & Crawling) from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.