Install
Three ways to run this device. Each one serves its fake backend: no instrument, no simulator install and no upstream checkout.
OpenAI4S (one command)
openai4s lab add robots/aurelienroy__ardupilot_sitl_gazebo_pluginInstalls the device into the OpenAI4S Lab on its fake backend and starts it. First time? See setup below.
Or, in the workbench, open the Lab tab → Market → Install.
Standalone MHS endpoint
git clone --depth 1 https://github.com/PKU-YuanGroup/OpenMHS.git && cd OpenMHS
PYTHONPATH=MHS/sdk/src python3 -m mhs serve robots/aurelienroy__ardupilot_sitl_gazebo_plugin --port 7400
# in a second terminal, from the same directory:
PYTHONPATH=MHS/sdk/src python3 -m mhs describe --endpoint http://127.0.0.1:7400Serves the device as an MHS endpoint on port 7400 from an OpenMHS clone (Python 3.10 or later, standard library only); describe prints what it offers.
Any MCP host (Claude Desktop, Cursor, …)
{
"mcpServers": {
"ardupilot-sitl-gazebo-plugin": {
"command": "python3",
"args": [
"-m",
"mhs",
"serve",
"robots/aurelienroy__ardupilot_sitl_gazebo_plugin",
"--mcp"
],
"env": {
"PYTHONPATH": "/path/to/OpenMHS/MHS/sdk/src"
}
}
}
}Add this server to the host's MCP configuration and replace /path/to/OpenMHS with the path of your OpenMHS clone. The host starts the server and talks to it on stdin and stdout.
What it does
Measures
observe_motor_speed
Adjusts
Nothing declared.
Actions
take_lapse_lock- Take the plugin's bounded wall-time lapse lock with the upstream method default horizon of 1 s; this pauses the plugin loop that steps the paused Gazebo world and exchanges packets with ArduPilot SITL, not ArduPilot itself, and the plugin clears the lock automatically when the timer expires
release_lapse_lock- Release this driver's lapse lock; succeeds only when the returned holder count is zero, because a positive count means another holder still pauses the loop
Names as the driver declares them. Units, limits and the safety declaration are in the package's REFERENCE.md.
First-time setup
The OpenAI4S workbench with the OpenMHS lab, from a source checkout:
# OpenAI4S workbench with the OpenMHS lab (source checkout)
git clone --recursive https://github.com/PKU-YuanGroup/OpenAI4S.git
cd OpenAI4S && ./setup.sh && source .venv/bin/activate
openai4s lab add robots/aurelienroy__ardupilot_sitl_gazebo_plugin
openai4s serve # open the Lab tabThe standalone endpoint and the MCP server need only an OpenMHS clone and Python 3.10 or later. More in the market's getting-started guide and on the OpenAI4S host page.
Source and evidence
- Pinned commit
75430fbc7796- Licence
- Apache-2.0
- Stars
- 34
- Evidence
contract_checkedon the fake backend- Backends
- fake
The driver package MHS/drivers/robots/aurelienroy__ardupilot_sitl_gazebo_plugin wraps the upstream code at the pinned commit. Its REFERENCE.md documents the full contract: every value, action, unit, limit and the safety declaration.