mcpserver.so LogoMCPFly
Submit
mcp-chat-bot logo

mcp-chat-bot

by kira1228

AI/Chatbots & AssistantsChatbotClaudeSlackBrave SearchFilesystem

An AI-powered chat system that leverages multiple MCP servers to enhance its capabilities. It intelligently routes queries to the appropriate server (Filesystem, Slack, Brave Search) based on the content of the query.

View on GitHub

Last updated: N/A

What is mcp-chat-bot?

This is an AI-powered chat system built using the Model Context Protocol (MCP) architecture. It connects to multiple specialized MCP servers to provide enhanced functionality, such as accessing local files, Slack conversations, and performing web searches.

How to use mcp-chat-bot?

  1. Clone the repository. 2. Create a .env file with your API keys (ANTHROPIC_API_KEY, SLACK_BOT_TOKEN, SLACK_TEAM_ID, BRAVE_API_KEY). 3. Create a virtual environment and install dependencies using uv. 4. Run the client with arguments for the server using uv run client.py path/to/dir/you/want/to/use.

Key features of mcp-chat-bot

  • Connects to multiple MCP servers

  • Intelligent query routing

  • Access to local files via MCP Filesystem

  • Slack integration via MCP Slack Server

  • Real-time web search via MCP Brave-Search

  • Uses Claude AI

Use cases of mcp-chat-bot

  • Searching local documents using AI

  • Accessing and summarizing Slack conversations

  • Performing web searches within a chat interface

  • Integrating AI with existing workflows

FAQ from mcp-chat-bot

What is MCP?

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

What API keys do I need?

You need ANTHROPIC_API_KEY for Claude AI, SLACK_BOT_TOKEN and SLACK_TEAM_ID for Slack integration, and BRAVE_API_KEY for Brave search.

How does the system know which server to use?

The system intelligently analyzes your queries and decides whether to search your local files, check Slack history, or perform a web search.

What is uv?

uv is a fast, modern Python package installer and resolver, designed as a drop-in replacement for pip and pip-tools.

Where can I find more information about MCP servers?

You can find more information and open-source MCP servers at https://github.com/modelcontextprotocol/servers