Crawl4AI
This MCP server provides AI assistants with advanced web crawling and RAG capabilities through the Crawl4AI library, built by Cole Medin using Python with comprehensive content extraction, semantic search, and knowledge graph integration. The implementation features multiple RAG strategies including contextual embeddings, hybrid search combining vector and keyword approaches, agentic RAG with code example extraction, cross-encoder reranking, and AI hallucination detection through Neo4j knowledge graphs. Built with Supabase for vector storage, OpenAI embeddings, configurable LLM support through OpenRouter, and Docker deployment options, it serves developers needing intelligent web content analysis, teams requiring automated documentation and code discovery from web sources, and organizations wanting to build knowledge bases from crawled web content with advanced retrieval and validation capabilities.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-02.
Scan details: Circle-IR · 2026-09-02 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Repository
- github.com/chillbruhhh/crawl4ai-mcp
- Author type
- human
- Last scanned
- 2026-09-02
- Updated
- 2026-09-02
Use via MCP
Resolve Crawl4AI 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.