search-engine-with-rag-and-mcp

search-engine-with-rag-and-mcp

3.3

If you are the rightful owner of search-engine-with-rag-and-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcpreview.com.

A powerful search engine that combines LangChain, Model Context Protocol (MCP), Retrieval-Augmented Generation (RAG), and Ollama to create an agentic AI system capable of searching the web, retrieving information, and providing relevant answers.

The Search Engine with RAG and MCP is an advanced AI system designed to enhance web search capabilities by integrating multiple technologies. It leverages LangChain for agent-based operations, MCP for standardized tool invocation, and RAG for improved information retrieval. The system supports both local and cloud-based LLMs, offering flexibility in deployment. It features a robust architecture that includes a search module using Exa API, a RAG module for document embedding and storage, and an MCP server for tool management. The engine is built with Python 3.13+, ensuring modern language features and type safety. It also supports asynchronous processing for efficient web operations, making it a comprehensive solution for advanced search needs.

Features

  • Web search capabilities using the Exa API
  • Web content retrieval using FireCrawl
  • RAG (Retrieval-Augmented Generation) for more relevant information extraction
  • MCP (Model Context Protocol) server for standardized tool invocation
  • Support for both local LLMs via Ollama and cloud-based LLMs via OpenAI

Tools