MCP_Control_STM32

# MCP Control STM32 ## MCP Section ### 1. Download Source Code ```bash git clone https://github.com/ana52070/MCP_Control_STM32.git cd MCP_Control_STM32 cd mcp-led_oled ``` ### 2. Create and Activate Virtual Environment To avoid dependency conflicts between different projects, it is recommended to use a virtual environment. Create and activate a virtual environment based on your operating system and Python version: #### For Python 3.3 and above ```bash python -m venv .venv ``` #### Activate Virtual Environment on Windows ```bash .venv\Scripts\activate ``` #### Activate Virtual Environment on Linux or macOS ```bash source .venv/bin/activate ``` ### 3. Install Dependencies Install dependencies directly using `pip`: ```bash pip install httpx>=0.28.1 mcp>=1.8.0 openai>=1.78.0 python-dotenv>=1.1.0 ``` ### 4. Modify Code Change the `.env` file to use your own large language model, with the default set to ollama: ``` BASE_URL=http://localhost:11434/v1/ MODEL=qwen2.5:1.5b OPENAI_API_KEY=ollama ``` If you are using the DeepSeek model, you need to write the following content in the `.env` file: ``` BASE_URL=https://api.deepseek.com MODEL=deepseek-chat OPENAI_API_KEY="DeepSeek API-Key" ``` Modify the serial port configuration in `server-led.py`: ``` # Serial Port Configuration SERIAL_PORT = "COM1" BAUDRATE = 115200 TIMEOUT = 1 # seconds ``` ### 5. Run MCP Code ``` python client.py server-led.py ``` ## STM32 Section ``` cd MCP_Control_STM32 ``` Compile and flash using Keil5, with the model being STM32F103C8T6. Alternatively, you can manually flash using the hex file: ``` MCP_Control_STM32\STM32_Project\Objects\Project.hex ```