Tecan Fluent liquid handler — 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/fredrik-qi__fork_fluent_sila2_connector

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/fredrik-qi__fork_fluent_sila2_connector --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": {
    "fork-fluent-sila2-connector": {
      "command": "python3",
      "args": [
        "-m",
        "mhs",
        "serve",
        "labs/fredrik-qi__fork_fluent_sila2_connector",
        "--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

state
progress
last_error
runnable_methods
variable_names

Adjusts

Nothing declared.

Actions

start_fluent: Start FluentControl or attach to a running instance without credentials; the connector may wait without a timeout and then prepares the method 'Method to prepare'
prepare_method: Prepare a FluentControl method; the connector deletes the Journaling/000 and Journaling/ToDelete directories before preparing
run_method: Run the currently prepared FluentControl method
pause_run: Pause the current FluentControl method; this is not the safe-state stop
resume_run: Resume a method paused by pause_run
stop_method: Stop the running method (SilaFluentController.StopMethod) and confirm that State reads RunModeRunFinished or EditMode; it takes no input
aspirate: Aspirate with the connector's fixed 8-tip A1 selection; it requires a live execution channel and passes the volume, labware, liquid class and well offset through unchanged
dispense: Dispense with the connector's fixed A1-H1 8-tip selection; it requires a live execution channel and passes the volume, labware, liquid class and well offset through unchanged
drop_tips: Drop the mounted disposable tips into the named labware
set_location: Set the location of a labware on the worktable
transfer_labware: Transfer labware on the worktable with the RGA
transfer_labware_back_to_base: Transfer labware back to the spot where it was added to the worktable
set_variable_value: Set a variable of the prepared method and read it back

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/fredrik-qi__fork_fluent_sila2_connector
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: fredrik-qi/fork_fluent_sila2_connector
Pinned commit: 4a2f857c619c
Licence: BSD-3-Clause
Stars: 0
Evidence: contract_checked on the fake backend
Backends: fake, hardware

The driver package MHS/drivers/labs/fredrik-qi__fork_fluent_sila2_connector wraps the upstream code at the pinned commit. Its REFERENCE.md documents the full contract: every value, action, unit, limit and the safety declaration.