What is the MCP Arduino Server?

The MCP Arduino Server is a bridge that allows AI models to interact with Arduino hardware and software using the Model Context Protocol (MCP).

What are the requirements for using the MCP Arduino Server?

You need Python 3.10+, arduino-cli in your PATH, the MCP SDK, and optionally WireViz and an OpenAI API key.

How do I install the MCP Arduino Server?

You can install it from PyPI using pip install mcp-arduino-server or from source by cloning the GitHub repository and running pip install ..

What environment variables can I configure?

You can configure ARDUINO_CLI_PATH, WIREVIZ_PATH, MCP_SKETCH_DIR, LOG_LEVEL, OPENAI_API_KEY, and OPENROUTER_API_KEY.

How do I use the AI-powered WireViz diagrams?

You need to set the OPENAI_API_KEY environment variable and then use the generate_circuit_diagram_from_description method.

How do I integrate the MCP Arduino Server with MCP clients like Claude Desktop?

You need to configure your client with the server’s command, arguments, and environment settings, including the path to the server and your OpenAI API key.

What is the UBOS Platform?

UBOS is a full-stack AI Agent Development Platform that helps businesses orchestrate AI Agents, connect them with enterprise data, and build custom AI Agents with their own LLM models. It can be used in conjunction with the MCP Arduino Server.

How can I troubleshoot issues with the MCP Arduino Server?

You can set LOG_LEVEL=DEBUG for verbose logs, verify file and serial port permissions, install missing Arduino cores, and run arduino-cli commands manually to debug.