About MCP RAG
MCP RAG is an AI chat system for people who need to search local files, Slack, and the web in one place. It selects which connected MCP server to use based on each query.
Key features
- 01Connects filesystem, Slack, and Brave Search
- 02Chooses a server based on the query
- 03Searches and retrieves local files
- 04Accesses Slack conversations and shared resources
- 05Retrieves real-time web search results
Use cases
- 01Find information in local files
- 02Look up Slack channels and conversation history
- 03Search for current information on the web
MCP support
The system acts as an MCP client connected to filesystem, Slack, and Brave Search servers, selecting a server according to the query.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEAI-powered chat system with multiple MCP servers.
🌟 Overview
MCP is a powerful client-server architecture that enables host applications to connect with multiple AI servers seamlessly. This system offers enhanced capabilities through specialized MCP servers:
-
MCP Filesystem: Allows Claude to search and retrieve information from your specified local folders, making your documents and files accessible to the AI.
-
MCP Slack Server: Connects to your Slack workspace, enabling Claude to access and reference your conversations, channels, and shared resources.
-
MCP Brave-Search: Provides real-time web search capabilities, allowing Claude to find and incorporate the latest information from the internet.
The system intelligently determines which server to utilize based on your queries. Claude automatically analyzes your questions and decides whether to search your local files, check Slack history, or perform a web search - all without requiring explicit instructions from you.
General Architecture 🛠️
At its core, MCP follows a client-server architecture where a host application can connect to multiple servers:
Getting Started! 🚀
Prerequisites 🤝
You need to install uv to run this project.
# MacOS/Linux
curl -LsSf https://astral.sh/uv/install.sh | sh
# Windows
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
Setup ⚙️
- Clone the repository.
git clone https://github.com/kira1228/mcp-chat-bot.git
cd mcp-chat-bot
- Create a
.envfile with your API keys:
# Create the .env file
touch .env
# Add your API credentials
# ANTHROPIC_API_KEY: Used for Claude AI integration
echo "ANTHROPIC_API_KEY=<your api key>" >> .env
# SLACK_BOT_TOKEN & SLACK_TEAM_ID: Required for Slack integration
echo "SLACK_BOT_TOKEN=<your api key>" >> .env
echo "SLACK_TEAM_ID=<your api key>" >> .env
# BRAVE_API_KEY: Used for Brave search capabilities
echo "BRAVE_API_KEY=<your api key>" >> .env
- Create a virtual environment and install the dependencies.
# MacOS/Linux
uv venv
source .venv/bin/activate
uv sync
# Windows
uv venv
.venv\Scripts\activate
uv sync
Usage 💻
Run the client with arguments for the server.
uv run client.py path/to/dir/you/want/to/use
References 📚
License 🔑
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.