MCP Chat

MCP Chat is a command-line application that enables interactive chat with models via the OpenAI API. It supports document retrieval, command-based prompts, and extensible tools via the MCP (Model Control Protocol) architecture.

Requirements

• Python 3.10+
• OpenAI API Key

Setup

Step 1: Configure environment variables

1. Create or edit the .env file in the project root and ensure the following variables are defined:

OPENAI_API_KEY=""      # Your OpenAI key
OPENAI_MODEL="gpt-4o-mini"  # Optional: default model

Step 2: Install dependencies

Option 1: Setup with uv (recommended)

uv is a fast Python package installer and resolver.

1. Install uv if you don't have it:

pip install uv

2. Create and activate a virtual environment:

uv venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

3. Install dependencies:

uv pip install -e .

4. Run the project

uv run main.py

Option 2: Setup without uv

1. Create and activate a virtual environment:

python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

2. Install dependencies:

pip install openai python-dotenv prompt-toolkit "mcp[cli]==1.8.0"

3. Run the project

python main.py

Usage

Basic interaction

Type your message and press Enter to chat with the model.

Document retrieval

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

> Tell me about @deposition.md

Commands

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

> /summarize deposition.md

Commands support tab-completion.

Development

Add new documents

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

Implement MCP features

To fully implement MCP:

1. Complete the TODOs in mcp_server.py
2. Implement the missing functionality in mcp_client.py

Linting and type checking

No linting or type checking is implemented.