MCP Chat

MCP Chat is a command-line interface application. The application supports document retrieval, command-based prompts, and extensible tool integrations via the MCP (Model Control Protocol) architecture.

Prerequisites

• Python 3.9+

• Any Chat Completions LLM API Key and Provider (i.e: Gemini)

Setup

Step 1: Configure the environment variables

1. Create or edit the .env file in the project root and verify that the following variables are set correctly:

Step 2: Install dependencies

uv is a fast Python package installer and resolver.

1. Install uv, if not already installed:

2. Create and activate a virtual environment:

3. Install dependencies:

4. Start MCP Server:

5. Run the project with ChatAgent in CLI

6. Optionally start inspector

Usage

Basic Interaction

Simply type your message and press Enter to chat with the model.

Document Retrieval

Use the @ symbol followed by a document ID to include document content in your query:

Commands

Use the / prefix to execute commands defined in the MCP server:

Commands will auto-complete when you press Tab.

Development

Adding New Documents

Edit the mcp_server.py file to add new documents to the docs dictionary.

Implementing MCP Features

To fully implement the MCP features:

1. Complete the TODOs in mcp_server.py

2. Implement the missing functionality in mcp_client.py

Linting and Typing Check

There are no lint or type checks implemented.