MCP Chat

MCP Chat is a command-line interface application that enables interactive chat capabilities with AI models through the Anthropic API. The application supports document retrieval, command-based prompts, and extensible tool integrations via the MCP (Model Control Protocol) architecture.

Prerequisites

• Python 3.9+

• Anthropic API Key

Related MCP server: MCP Chat

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:

ANTHROPIC_API_KEY=""  # Enter your Anthropic API secret key

See if u have python installed Step 1 — Get an API key:

Go to console.anthropic.com Sign in (or create an account) Go to API Keys in the left sidebar Click Create Key, give it a name, and copy it Step 2 — Paste it in .env open the .env file at /Users/akritiagrawal/Downloads/cli_project/.env and replace the empty quotes on line 2 with your key. It should look like: env:\ANTHROPIC_API_KEY="sk-ant-api03-xxxxxxxxxxxxx"

Step 2: Install dependencies

Option 1: Setup with uv (Recommended)

uv is a fast Python package installer and resolver.

1. Install uv, if not already installed:

brew install uv

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 anthropic python-dotenv prompt-toolkit "mcp[cli]==1.8.0"

3. Run the project

python main.py

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:

> Tell me about @deposition.md

Commands

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

> /summarize deposition.md

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.

To run MCP Inspector server: run

mcp dev mcp_server.py

The mcp dev command launches the MCP Inspector — a web-based testing UI where you can interact with your MCP server without needing API credits. It lets you test your tools, resources, and prompts visually.

To run it:

uv run mcp dev mcp_server.py

Note the uv run prefix — you need it so the dependencies are available.

This will open a browser UI (usually at http://localhost:5173) where you can:

See all your tools and call them manually Browse your resources Test your prompts

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.