MCP Arduino Server
An MCP server for the Arduino CLI, offering tools to manage sketches, boards, libraries, and files.
MCP Arduino Server (mcp-arduino-server)
A FastMCP-powered bridge exposing arduino-cli functionality via the Model Context Protocol (MCP). Manage sketches, boards, libraries, files, plus generate WireViz schematics from YAML or natural language.
Requirements
- Python ≥3.10
- arduino-cli in
PATH - MCP SDK (
mcp[cli]) - WireViz (optional; for diagram generation)
- OPENAI_API_KEY (for AI‑powered WireViz)
- thefuzz[speedup] (optional; enables fuzzy local library search)
Installation
From PyPI:
pip install mcp-arduino-server
From source:
git clone https://github.com/Volt23/mcp-arduino-server.git
cd mcp-arduino-server
pip install .
Configuration
Environment variables override defaults:
| Variable | Default / Description |
|---|---|
| ARDUINO_CLI_PATH | auto-detected |
| WIREVIZ_PATH | auto-detected |
| MCP_SKETCH_DIR | ~/Documents/Arduino_MCP_Sketches/ |
| LOG_LEVEL | INFO |
| OPENAI_API_KEY | your OpenAI API key (required for AI‑powered WireViz) |
| OPENROUTER_API_KEY | optional alternative to OPENAI_API_KEY |
| ARDUINO_SERIAL_LOG_MAX_BYTES | max size per serial log file (bytes; 0 disables) |
| ARDUINO_SERIAL_LOG_ROTATE_COUNT | number of rotated serial logs to keep |
Quick Start
mcp-arduino-server
Server listens on STDIO for JSON-RPC MCP calls. Key methods:
Sketches
create_new_sketch(name)list_sketches()read_file(path)write_file(path, content[, board_fqbn])(auto-compiles & opens.ino)
Build & Deploy
verify_code(sketch, board_fqbn)upload_sketch(sketch, port, board_fqbn)
Libraries
lib_search(name[, limit])lib_install(name)list_library_examples(name)
Boards
list_boards()board_search(query)
Serial Monitor
serial_monitor_start(port, baud, buffer_lines, log_to_file, ...)serial_monitor_read(monitor_id, lines)serial_monitor_list()serial_monitor_stop(monitor_id)
File Ops
rename_file(src, dest)remove_file(path)(destructive; operations sandboxed to home & sketch directories)
WireViz Diagrams
generate_circuit_diagram_from_description(desc, sketch="", output_base="circuit")(AI‑powered; requiresOPENAI_API_KEY, opens PNG automatically)
MCP Client Configuration
To integrate with MCP clients (e.g., Claude Desktop), set your OpenAI API key in the environment (or alternatively OPENROUTER_API_KEY for OpenRouter):
{
"mcpServers": {
"arduino": {
"command": "/path/to/mcp-arduino-server",
"args": [],
"env": {
"WIREVIZ_PATH": "/path/to/wireviz",
"OPENAI_API_KEY": "<your-openai-api-key>"
}
}
}
}
Troubleshooting
- Set
LOG_LEVEL=DEBUGfor verbose logs. - Verify file and serial-port permissions.
- Install missing cores:
arduino-cli core install <spec>. - Run
arduino-clicommands manually to debug.
License
MIT
Related Servers
Scout Monitoring MCP
sponsorPut performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
sponsorAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
GDB MCP Server
An MCP server that enables LLM clients to interact with GDB for debugging and binary analysis.
Mermaid
Generate mermaid diagram and chart with AI MCP dynamically.
AgentChatBus
AgentChatBus is a persistent AI communication bus that lets multiple independent AI Agents chat, collaborate, and delegate tasks — across terminals, across IDEs, and across frameworks.
MCP Server + Asgardeo
A sample MCP server that uses Asgardeo for client authentication and connection.
Remote MCP Server (Authless)
An example of a remote MCP server deployable on Cloudflare Workers without authentication.
Cursor History MCP
Best MCP server for browsing, searching, backup, and exporting Cursor AI chat history.
Petstore MCP Server & Client
An MCP server and client implementation for the Swagger Petstore API.
MCP Quickstart
A basic MCP server from the Quickstart Guide, adapted for OpenAI's Chat Completions API.
go-mcp実験場
A Go-based MCP server example demonstrating correct usage of go.mod and build/run commands.
Octomind
Create and manage end-to-end tests using the Octomind platform.