Crawl4AI RAG MCP Server

Enables crawling GitHub repositories to process content and build knowledge graphs for code validation

Integrates with Google Gemini API for generating embeddings and responses, configurable as the primary AI provider

Leverages Neo4j to build knowledge graphs of code repositories for validating AI-generated code and detecting hallucinations

Allows switching to OpenAI as the primary AI provider for generating embeddings and responses

Uses Supabase with pgvector to store and search through crawled content, enabling vector and hybrid search capabilities

1. Click on "Install Server".

2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.

3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Crawl4AI RAG MCP Server crawl the OpenAI blog and summarize the latest AI safety research"

That's it! The server will respond to your query, and you can continue using it as needed.

Here is a step-by-step guide with screenshots.