mcp_chatbot

Overview

MCPChatbot is a comprehensive implementation demonstrating how to integrate the Model Context Protocol with customized LLMs like Qwen. The project provides multiple interfaces including CLI chatbot, terminal chat with streaming responses, and a Streamlit web interface. It includes example scripts for single prompt processing in both regular and streaming modes, along with a custom MCP server for Markdown processing. The codebase is well-structured with clear separation of concerns for chat management, configuration handling, LLM client implementation, and MCP tool integration.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

• markdown_processor

  Processes markdown files through an MCP server

  Try:Process the markdown file in the example folderTry:Convert this markdown to HTMLTry:Summarize the contents of these markdown files

Note: Only one tool (markdown_processor) could be inferred from the MCP server configuration, though its specific functions are not well-documented in the README. The tool appears to be defined in mcp_servers/markdown_processor.py but the README

Comparable tools

Installation

git clone git@github.com:keli-wen/mcp_chatbot.git
cd mcp_chatbot

pip install uv
uv venv .venv --python=3.10
source .venv/bin/activate  # or .venv\Scripts\activate for Windows
uv pip install -r requirements.txt

cp .env.example .env
# Edit .env with your API keys and paths

{
  "mcpServers": {
    "mcp_chatbot": {
      "command": "python",
      "args": ["-m", "mcp_chatbot.server"]
    }
  }
}

FAQ

Which LLM providers are supported?

The implementation supports various LLM providers including Qwen and Ollama. You can configure any LLM API by setting the base_url and api_key in the .env file.

How do I add a new MCP server?

Add your new server implementation in the `mcp_servers/` directory and update the `servers_config.json` file to include your new server configuration with the appropriate command and arguments.

Compare mcp_chatbot with