Labs · Optics and microscopy

Dino-Lite UVC LED control (dinoliteuvccontrol.DinoLiteUVCControl)

Dino-Lite UVC LED control (dinoliteuvccontrol.DinoLiteUVCControl), adapted from miked63017/dinolite_uvc_led_control. It reads main_led_on, flc_on, flc_brightness, auto_exposure and 3 more; runs set_illumination, set_flc_brightness, toggle_flc_led, toggle_auto_exposure and 2 more. set_illumination: turn the main LED or the FLC illumination on or off. A hardware driver: the market serves its fake backend, so no instrument is needed.

hardwareRisk R1licence not assertedcontract_checkedserved on the fake backend
openai4s lab add labs/miked63017__dinolite_uvc_led_control

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/miked63017__dinolite_uvc_led_control

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/miked63017__dinolite_uvc_led_control --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": {
    "dinolite-uvc-led-control": {
      "command": "python3",
      "args": [
        "-m",
        "mhs",
        "serve",
        "labs/miked63017__dinolite_uvc_led_control",
        "--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

  • main_led_on
  • flc_on
  • flc_brightness
  • auto_exposure
  • exposure_time
  • video_device
  • product_id

Adjusts

Nothing declared.

Actions

set_illumination
Turn the main LED or the FLC illumination on or off
set_flc_brightness
Set the FLC brightness level (0 to 6); FLC is switched on first when it is off
toggle_flc_led
Toggle one of the four FLC LEDs; FLC is switched on first when it is off
toggle_auto_exposure
Toggle automatic exposure on the microscope
step_exposure
Move one step in the device's exposure table; auto exposure is switched off first
illumination_off
Switch all illumination off (the safe state); it takes no input

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/miked63017__dinolite_uvc_led_control
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

Pinned commit
f70a4cedfa1f
Licence
NOASSERTION
Stars
26
Evidence
contract_checked on 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/miked63017__dinolite_uvc_led_control wraps the upstream code at the pinned commit. Its REFERENCE.md documents the full contract: every value, action, unit, limit and the safety declaration.