Crawl4AI RAG
MCP server that integrates web crawling capabilities with RAG (Retrieval-Augmented Generation) functionality, built by Jason Guo to enable AI agents and coding assistants to crawl websites, extract content, and perform semantic search over the collected data. The implementation combines Crawl4AI for web scraping with Supabase for vector storage, supporting advanced features like contextual embeddings, hybrid search, code example extraction, and AI hallucination detection through Neo4j knowledge graphs. Designed for AI coding workflows where assistants need to gather, index, and query web-based documentation or code repositories, with Docker deployment and SearXNG integration for enhanced search 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 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · 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/tokidoo/crawl4ai-rag-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Crawl4AI RAG 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.