mcpserver.so LogoMCPFly
Submit
MCP-RAG logo

MCP-RAG

by kira1228

AI/Chatbots & AssistantsChatbotRAGClaudeSlackBrave Search

An AI-powered chat system leveraging multiple MCP servers to enhance Claude's capabilities. It allows Claude to access local files, Slack conversations, and perform web searches based on user queries.

View on GitHub

Last updated: N/A

What is MCP-RAG?

This is an AI-powered chat system that utilizes the Model Context Protocol (MCP) to connect a host application (like a chatbot) to multiple specialized servers. These servers provide Claude with access to various data sources, enabling more informed and context-aware responses.

How to use MCP-RAG?

  1. Clone the repository. 2. Create a .env file and add your API keys for Anthropic, Slack, and Brave Search. 3. Create a virtual environment and install the dependencies using uv. 4. Run the client with arguments specifying the path to the directory you want to use with the filesystem server.

Key features of MCP-RAG

  • Connects to multiple MCP servers

  • Integrates with Claude AI

  • Supports filesystem access for local documents

  • Enables access to Slack conversations and resources

  • Provides real-time web search capabilities via Brave Search

  • Intelligently selects the appropriate server based on the query

Use cases of MCP-RAG

  • Enhanced chatbot interactions with access to diverse data sources

  • Improved information retrieval and summarization

  • Context-aware responses based on local files, Slack conversations, and web search results

  • Automated research and data analysis

FAQ from MCP-RAG

What is MCP?

MCP (Model Context Protocol) is a client-server architecture that allows host applications to connect with multiple AI servers seamlessly.

What API keys do I need?

You need API keys for Anthropic (Claude), Slack, and Brave Search.

How do I install the dependencies?

Use uv venv to create a virtual environment, activate it, and then use uv sync to install the required packages.

How does the system decide which server to use?

The system intelligently analyzes your queries and determines which server is most relevant based on the context of the question.

What license is this project under?

This project is licensed under the MIT License.