Add API key to .env file

What is Add API key to .env file?

A minimal MCP (Model Context Protocol) project that demonstrates how to set up an MCP server with an API key stored in a .env file. It uses DeepSeek as the LLM backend and includes sample Python and Node.js servers for task lists, weather, and stock data. Aimed at developers learning MCP.

How to use Add API key to .env file?

Create a .env file with OPENAI_API_KEY, OPENAI_BASE_URL, and OPENAI_MODEL (e.g., DeepSeek). Install dependencies with uv add mcp openai python-dotenv. Edit server.json to point to the server scripts (tasklist.py, weather.py, stock.js). Run the client with cd client && uv run client.py server.json.

Key features of Add API key to .env file

• Minimal MCP project for learning.
• Uses .env file for API key configuration.
• Supports multiple LLM services via environment variables.
• Includes Python and Node.js server examples.
• Client auto‑discovers servers from server.json.
• Easy setup with uv virtual environment.

Use cases of Add API key to .env file

• Learn how MCP servers and clients interact.
• Prototype a multi‑server MCP application.
• Test DeepSeek or other OpenAI‑compatible LLMs with MCP.
• Quickstart template for custom MCP server development.

FAQ from Add API key to .env file

What API key is required?

A DeepSeek API key (or any OpenAI‑compatible API) must be added to the .env file as OPENAI_API_KEY.

How do I switch to a different LLM service?

Change the OPENAI_BASE_URL and OPENAI_MODEL in .env to match the desired service.

What servers are provided?

The project includes tasklist.py, weather.py, and stock.js as example MCP servers.

How do I run the project?

Activate the virtual environment, then run uv run client.py server.json from the client directory.

Where does the data live?

Task data is stored in tasks.csv in the project root. Other server data comes from external APIs (not specified).