ArduPilot MCP Server Sandbox

@hfujikawa77

About ArduPilot MCP Server Sandbox

ArduPilotドローンをAIエージェントから操作するMCPサーバーです。

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "ardupilot-controller": {
      "command": "python",
      "args": [
        "C:/Users/your-user-name/path/to/ardupilot_mcp_server.py"
      ],
      "alwaysAllow": [
        "arm",
        "disarm",
        "takeoff",
        "change_mode"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is ArduPilot MCP Server Sandbox?

The ArduPilot MCP Server Sandbox is an MCP server that enables natural language control of ArduPilot drones via an LLM host such as Claude Desktop or Cline. It communicates with the drone over MAVLink TCP at 127.0.0.1:5762 and is intended for developers and drone enthusiasts who want to integrate LLM-based command interfaces with ArduPilot.

How to use ArduPilot MCP Server Sandbox?

Install Python 3.10+, run pip install -r requirements.txt, then start the server with python ardupilot_mcp_server.py. Configure your MCP host (Claude Desktop or Cline) by editing its settings file to point to the server script. The README provides exact JSON configuration examples for both hosts.

Key features of ArduPilot MCP Server Sandbox

Natural language drone control via LLM hosts
Supports ArduPilot SITL simulation and real vehicles
MAVLink communication over TCP at localhost:5762
Provides tools: arm, disarm, takeoff, change_mode, get_position, etc.
Includes star mission creation and upload capability
Works with Claude Desktop and Cline

Use cases of ArduPilot MCP Server Sandbox

Command drone arming, takeoff, and mode changes through chat
Create and upload star-shaped missions centered on current position
Retrieve current GPS position and stored missions from the drone
Automate drone operations by prompting an LLM with natural language

FAQ from ArduPilot MCP Server Sandbox

What are the prerequisites to run the server?

Python 3.10+, an ArduPilot instance (SITL or real drone), and MAVLink reachable at tcp:127.0.0.1:5762.

How do I set up the simulator?

Use Mission Planner’s built‑in simulator: launch Mission Planner, click “Simulation”, select “Multirotor”, then click “Stable”. The simulator listens on tcp:127.0.0.1:5762.

What MCP tools does the server expose?

It exposes ten tools: arm, disarm, takeoff, change_mode, get_position, clear_mission, download_mission, upload_star_mission, and start_mission.

Can this server be used with a real drone?

Yes, as long as the real ArduPilot drone provides MAVLink access via TCP on 127.0.0.1:5762.

Which MCP hosts are supported?

The README provides configuration examples for Claude Desktop and for Cline (VS Code extension).

Frequently asked questions

What are the prerequisites to run the server?

Python 3.10+, an ArduPilot instance (SITL or real drone), and MAVLink reachable at `tcp:127.0.0.1:5762`.

How do I set up the simulator?

Use Mission Planner’s built‑in simulator: launch Mission Planner, click “Simulation”, select “Multirotor”, then click “Stable”. The simulator listens on `tcp:127.0.0.1:5762`.

What MCP tools does the server expose?

It exposes ten tools: arm, disarm, takeoff, change_mode, get_position, clear_mission, download_mission, upload_star_mission, and start_mission.

Can this server be used with a real drone?

Yes, as long as the real ArduPilot drone provides MAVLink access via TCP on `127.0.0.1:5762`.

Which MCP hosts are supported?

The README provides configuration examples for Claude Desktop and for Cline (VS Code extension).

Comments

Basic information

More Reasoning MCP servers

🐢🚀 Node.js Sandbox MCP Server

alfonsograziano

A Node.js–based Model Context Protocol server that spins up disposable Docker containers to execute arbitrary JavaScript.

154

Unified MCP Suite

Godzilla675

A suite of Model Context Protocol (MCP) servers designed to enhance AI agent capabilities. Provides tools for media search/understanding (images, video), web information retrieval, PDF generation, and PowerPoint presentation creation, enabling agents to interact with diverse data

NeoCoder: Neo4j-Guided AI Coding Workflow

angrysky56

An MCP server allowing AI assistants to use a Neo4j knowledge graph as their primary, dynamic instruction manual and long term project memory with adaptive templating and autonomous tool development tools.

MCP Sandbox

danstarns

Turn any JavaScript module into a sandboxed MCP (Model Context Protocol) server with automatic reflection and type inference.

n8n Workflow Builder MCP Server

makafeli

AI assistant integration for n8n workflow automation through Model Context Protocol (MCP). Connect Claude Desktop, ChatGPT, and other AI assistants to n8n for natural language workflow management.

530