Universal Robots arm (ur_interface.ur:UR) — 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 labs/ad-sdl__ur_module

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 labs/ad-sdl__ur_module --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": {
    "ur-module": {
      "command": "python3",
      "args": [
        "-m",
        "mhs",
        "serve",
        "labs/ad-sdl__ur_module",
        "--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

movement_state
joint_positions
robot_mode
safety_status
operational_mode
program_state
loaded_program
program_run_status
remote_control

Adjusts

Nothing declared.

Actions

home: Command one or more actuated joints to target positions in joint space, optionally over a declared duration, and report whether the target was reached within tolerance.
pause_program: Pause the loaded URP program with the dashboard 'pause'; completed only when the dashboard answers 'Pausing program'
stop_program: Stop the loaded URP program with the dashboard 'stop' (the upstream node's safety_stop); completed only when the dashboard answers 'Stopped'; not the e-stop
power_off_arm: Power the arm off with the dashboard 'power off' (the upstream node's e_stop) and confirm POWER_OFF by fresh 'robotmode' reads; it takes no input
power_on: Re-enable after a reset (refused while latched, never run by the reset, a permit for each call): with safety status NORMAL, send the dashboard 'brake release' to an arm in POWER_OFF, BOOTING, POWER_ON or IDLE and confirm RUNNING; it never unlocks a protective stop, restarts safety or changes the operational mode

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 labs/ad-sdl__ur_module
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: ad-sdl/ur_module
Pinned commit: 75f1c5fe53c7
Licence: MIT
Stars: 4
Evidence: contract_checked on the fake backend
Backends: fake, hardware

The driver package MHS/drivers/labs/ad-sdl__ur_module wraps the upstream code at the pinned commit. Its REFERENCE.md documents the full contract: every value, action, unit, limit and the safety declaration.