Provides secure management of API keys and sensitive credentials
Powers the local MCP server to expose tools and functionality to client applications
Repository hosting for the MCP server code, accessible via git clone
Integrates with ChatGPT for intelligent search capabilities, allowing it to leverage knowledge bases for domain-specific queries
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP AI Serversearch for recent updates to our API documentation"
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.
🧠 MCP AI Server — Modular Context Protocol for Intelligent Search
Welcome to the MCP AI Server, a powerful and modular tool that uses RAG-based retrieval, Pinecone vector storage, and MCP (Model Context Protocol) to create intelligent assistants capable of answering domain-specific questions from your own knowledge base.
🚀 Features
✅ Local MCP server with FastAPI + Claude/ChatGPT integration
✅ Embedding using intfloat/multilingual-e5-large (via SentenceTransformer)
✅ Fast vector search with Pinecone
✅ Documented tools exposed to clients like Claude and Cursor IDE
✅ Secure .env usage for managing API keys
✅ Clean, extensible architecture
Related MCP server: Model Context Protocol Server