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/barisyazici__libfranka-simInstalls 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/barisyazici__libfranka-sim --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": {
"libfranka-sim": {
"command": "python3",
"args": [
"-m",
"mhs",
"serve",
"robots/barisyazici__libfranka-sim",
"--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
width_mmmax_width_mmis_graspedis_stucktemperature_c
Adjusts
Nothing declared.
Actions
grasp- Close the gripper on a target object with a bounded force and report the achieved grasp width. A failed grasp is a completed operation with grasped=false, not a silent success.
release- Open the gripper to release the held object, optionally to a declared opening width, and report the achieved width.
hand_home- Drive the fingers fully open and clear the grasp and stuck state
hand_move- Drive the fingers to a width and wait until they settle
hand_stop- Stop the hand by driving the fingers fully open, the simulator's safe state
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/barisyazici__libfranka-sim
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
- Upstream
- barisyazici/libfranka-sim
- Pinned commit
d893e17dc77a- Licence
- Apache-2.0
- Stars
- 85
- Evidence
contract_checkedon the fake backend- Backends
- fake
The driver package MHS/drivers/robots/barisyazici__libfranka-sim wraps the upstream code at the pinned commit. Its REFERENCE.md documents the full contract: every value, action, unit, limit and the safety declaration.