ProbonoBonobo_sui-mcp-server

ProbonoBonobo_sui-mcp-server

0
communicationknowledge_and_memory

This project implements a Machine Conversation Protocol server for enhanced document retrieval in AI applications. It integrates with FAISS and GitHub to provide a complete RAG workflow. Key features include vector database integration and support for leveraging LLMs in querying.

MCP Server with FAISS for RAG

This project provides a proof-of-concept implementation of a Machine Conversation Protocol (MCP) server that enables an AI agent to query a vector database and retrieve relevant documents for Retrieval-Augmented Generation (RAG).

Features

  • FastAPI server with MCP endpoints
  • FAISS vector database integration
  • Document chunking and embedding
  • GitHub Move file extraction and processing
  • LLM integration for a complete RAG workflow
  • Simple client example
  • Sample documents available

Installation

Using pipx (Recommended)

  • Install pipx using homebrew on macOS or pip on Windows.
  • Install the MCP Server package directly from the project directory using pipx.

Manual Installation

  • Clone the repository and install dependencies.

Usage with pipx

  • Commands available for downloading and indexing Move files from GitHub, querying the vector database, and using RAG with LLM Integration.

Running the Server

  • Start the server with mcp-server or customize settings such as host and port.

Complete RAG Pipeline

  1. Search Query: The user submits a question.
  2. Retrieval: The system searches the vector database for relevant documents.
  3. Context Formation: Retrieved documents are formatted into a prompt.
  4. LLM Generation: The prompt is sent to an LLM with the retrieved context.
  5. Enhanced Response: The LLM provides an answer based on the retrieved information.

Extending the Project

  • Suggestions for extending the project include adding authentication, document processing, support for more document types, monitoring, logging, and more advanced Move language parsing.