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 labs/accelerationconsortium__opentrons-flexInstalls 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 labs/accelerationconsortium__opentrons-flex --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": {
"opentrons-flex": {
"command": "python3",
"args": [
"-m",
"mhs",
"serve",
"labs/accelerationconsortium__opentrons-flex",
"--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
simulatingmachine_status
Adjusts
lights_buttonlights_rails
Actions
home- Home every Flex axis with FlexMotionController.home(); the declared re-enable: after a halt or an e-stop the connector refuses every other actuation until this full home completes. The latch refuses it and a safety reset never runs it.
cartesian_pose- Move the tool centre point to a Cartesian position and orientation in a named frame. The endpoint solves inverse kinematics; an unreachable target is rejected before motion.
stop- Halt all motion with FlexMotionController.stop() (the OT3API halt path); it takes no input, is the declared safe state, and leaves the robot needing a full home
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 labs/accelerationconsortium__opentrons-flex
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
2639016ee9f2- Licence
- NOASSERTION
- Stars
- 3
- Evidence
contract_checkedon the fake backend- Backends
- fake, hardware
The upstream repository asserts no licence (NOASSERTION); check it before you redistribute the upstream code.
The driver package MHS/drivers/labs/accelerationconsortium__opentrons-flex wraps the upstream code at the pinned commit. Its REFERENCE.md documents the full contract: every value, action, unit, limit and the safety declaration.