Advertise
MCP.so
Sign In

MCP RAG

@kira1228

Repository

Basic information

Category

Memory & Knowledge

License

MIT

Transports

stdio

Author

kira1228

About MCP RAG

AI-powered Chat System with multiple MCP servers.

MCP RAG config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "MCP-RAG": {
      "command": "uv",
      "args": [
        "venv"
      ]
    }
  }
}

MCP RAG tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is MCP RAG?

MCP RAG is an AI-powered chat system built on the Model Context Protocol (MCP) client-server architecture. It connects to multiple specialized MCP servers—Filesystem, Slack, and Brave Search—to give Claude access to local files, Slack conversations, and real-time web search. This system is for users who want a single interface that automatically retrieves context from diverse sources without manual server selection.

How to use MCP RAG?

First, install uv (see README for commands). Then clone the repository, create a .env file with your ANTHROPIC_API_KEY, SLACK_BOT_TOKEN, SLACK_TEAM_ID, and BRAVE_API_KEY. Create a virtual environment and install dependencies using uv venv and uv sync. Finally, run the client with uv run client.py path/to/dir/you/want/to/use.

Key features of MCP RAG

  • Integrates with local filesystem, Slack, and Brave Search servers.
  • Automatically selects the right server based on user query.
  • Powered by Claude AI (Anthropic API).
  • Built on standard MCP client-server architecture.
  • Open source under MIT License.
  • Dependencies managed via uv.

Use cases of MCP RAG

  • Search and retrieve information from local folders via Filesystem server.
  • Query Slack workspace history for conversations and shared resources.
  • Perform real-time web searches to fetch latest information.
  • Combine multiple data sources seamlessly without explicit instructions.

Frequently asked questions

1

What dependencies are required to run MCP RAG?

The system requires `uv` for package and environment management, plus API keys for Anthropic, Slack, and Brave Search.

2

How do I configure the API keys?

Create a `.env` file in the project root and add `ANTHROPIC_API_KEY`, `SLACK_BOT_TOKEN`, `SLACK_TEAM_ID`, and `BRAVE_API_KEY` with your credentials.

3

What data sources does MCP RAG support?

MCP RAG uses three MCP servers: Filesystem (local folders), Slack (workspace conversations), and Brave Search (web). The system intelligently chooses which to query.

4

Is MCP RAG open source?

Yes, it is licensed under the MIT License, allowing free use, modification, and distribution.

5

How does MCP RAG decide which server to use?

Claude analyzes the question and automatically selects the appropriate MCP server (Filesystem, Slack, or Brave Search) without requiring explicit user instructions.

Comments

More Memory & Knowledge MCP servers

server-noonien - shared memory MCP

sequico

Shared, serverless, conflict-free memory for AI agents: a multi-machine drop-in for the MCP memory knowledge graph.

Snipara

alopez3006

MCP connector for Snipara, the Project Brain for AI coding agents

1

Azquo

Azquo Holdings Ltd

Exact, shared memory for AI agents: a hierarchical database where totals always add up, every write is attributed to the agent and person behind it, and any figure traces back to its source file. Agents create databases,

Sensefold

SenseFold Labs

Personal context for every AI: search, read, and write back to your private Markdown library of articles, threads, PDFs, notes, and captured ChatGPT/Claude/Gemini/Grok conversations. Remote server, OAuth 2.1 paste-and-au

Groundwork

Rarefied-Earth

Groundwork: company memory for your AI tools. Docs public. Source closed. Public proof needs no account.

1
Advertise