ME5413 Gazebo course world — device market

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)

shell

openai4s lab add robots/nus-advanced-robotics-centre__me5413_final_project

Installs 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

shell

git clone --depth 1 https://github.com/PKU-YuanGroup/OpenMHS.git && cd OpenMHS
PYTHONPATH=MHS/sdk/src python3 -m mhs serve robots/nus-advanced-robotics-centre__me5413_final_project --port 7400
# in a second terminal, from the same directory:
PYTHONPATH=MHS/sdk/src python3 -m mhs describe --endpoint http://127.0.0.1:7400

Serves 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, …)

mcp configuration

{
  "mcpServers": {
    "me5413-final-project": {
      "command": "python3",
      "args": [
        "-m",
        "mhs",
        "serve",
        "robots/nus-advanced-robotics-centre__me5413_final_project",
        "--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

Nothing declared.

Adjusts

Nothing declared.

Actions

remove_moving_obstacle: Delete the moving planar_box obstacle once with the acknowledged DeleteModel service; this is not a stop
clear_objects: Publish Int16 0 on the RViz panel's respawn topic to delete the random objects
regenerate_objects: Publish Int16 1 on the RViz panel's respawn topic to regenerate the random objects
open_exit: Publish Bool true on /cmd_unblock to request the one-time exit removal
delete_model: Delete one named Gazebo model through the acknowledged DeleteModel service
read_box_odom: Read one fresh /box_odom sample published by the object spawner plugin
read_box_markers: Read one fresh /gazebo/ground_truth/box_markers sample

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:

shell

# 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/nus-advanced-robotics-centre__me5413_final_project
openai4s serve        # open the Lab tab

The 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

Upstream: nus-advanced-robotics-centre/me5413_final_project
Pinned commit: 9fd6ce2643f7
Licence: MIT
Stars: 92
Evidence: contract_checked on the fake backend
Backends: fake

The driver package MHS/drivers/robots/nus-advanced-robotics-centre__me5413_final_project wraps the upstream code at the pinned commit. Its REFERENCE.md documents the full contract: every value, action, unit, limit and the safety declaration.