PicoQuant Luminosa through LumiPy Measurement — 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/picoquant__lumipy

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/picoquant__lumipy --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": {
    "lumipy": {
      "command": "python3",
      "args": [
        "-m",
        "mhs",
        "serve",
        "labs/picoquant__lumipy",
        "--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

version
analysis_names
running
elapsed_meas_time
scan_range_min_x
scan_range_max_x
scan_range_min_y
scan_range_max_y
stop_on_num_frames
num_frames
stop_on_photons_in_brightest_px
photons_in_brightest_px
img_stop_on_meas_time
img_meas_time
point_stop_on_photons
point_num_photons
point_stop_on_meas_time
point_meas_time
write_ptu_file
path_to_ptu

Adjusts

scan_range_left
scan_range_top
scan_range_width
scan_range_height
scan_speed
image_size

Actions

configure_image_stop: Configure the image stop conditions (frame count, photon threshold, time).
configure_point_stop: Configure the point stop conditions (photon threshold and time).
set_ptu_output: Enable or disable PTU output during the next scan.
start_measurement: Start an image, line or point measurement (the native start_meas).
stop_measurement: Stop the measurement (native stop_meas) and confirm meas_status reads False; safe state.
set_measurement_name: Set the name of the next measurement (the native set_next_measurement_name).
get_analysis_curve: Read one live analysis curve and its optional fit arrays.
get_analysis_curve_types: List the curve types available for one live analysis.
get_analysis_image_types: List the image types available for one live analysis.
get_analysis_param: Read one live analysis parameter; its keys depend on the analysis and parameter type.
get_analysis_param_types: List the parameter types available for one live analysis.

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/picoquant__lumipy
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: picoquant/lumipy
Pinned commit: dc0fe266a552
Licence: MIT
Stars: 6
Evidence: contract_checked on the fake backend
Backends: fake, hardware

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