This MCP server project provides a minimal MCP development setup used for learning and experimenting with MCP concepts. It relies on Python and the UV tooling ecosystem to manage environment synchronization and package installation. After setting up, you can start the server (via the mcp_lite_dev module) and use the included configuration and environment variables to interact with weather data (OpenWeatherMap) and the SiliconFlow-based model API. The documentation suggests you configure API keys and base URLs in a .env file to enable external data sources used by the MCP workflows. The repository focuses on incremental MCP topics and project structure rather than a heavy production deployment, making it suitable for local exploration and hands-on MCP experiments.

Prerequisites:

• Python 3.10+ installed on your system
• Access to install Python packages (pip)

Installation steps:

1. Install uv (Python package manager for this project workflow): python -m pip install uv set UV_INDEX=https://mirrors.aliyun.com/pypi/simple

2. Synchronize dependencies for Python 3.10 and extras (as shown in the project guide): uv sync --python 3.10 --all-extras

3. Set up a local virtual environment (recommended):

   Windows (PowerShell)

   cd .venv/Scripts .\activate

   macOS/Linux

   source .venv/bin/activate

4. Create and configure environment variables (.env) in the project root: OPENWEATHER_API_KEY=YOUR_API_KEY BASE_URL=https://api.siliconflow.cn/v1 MODEL=deepseek-ai/DeepSeek-V3 API_KEY=YOUR_API_KEY

5. Install the project/package if needed and run the MCP server using the module entry point: python -m mcp_lite_dev

Tips and notes:

• Ensure Python 3.10+ is active in your environment before installing dependencies.
• The .env file must be present in the project root with the required keys (OPENWEATHER_API_KEY, BASE_URL, MODEL, API_KEY).
• If you encounter environment variable issues, verify that the correct .env file is loaded by your runtime and that the UV tool has permission to access network resources.
• The project appears to be a learning/memo project around MCP rather than a large-scale production server; use it to experiment with MCP concepts, not for high-traffic deployments.
• If your environment uses a custom PyPI mirror, set UV_INDEX accordingly to ensure package installation works smoothly.