OpenMHSindependent draft 0.9
Playground
Open menu

Robots · Sensors and cameras

RealSense ROS 2 camera

RealSense ROS 2 camera, adapted from realsenseai/realsense-ros. It reads frame_id, width, height, device_name and 9 more; runs capture_image and capture_point_cloud. capture_image: capture a single image from a named camera with a declared resolution and exposure and return an image artifact reference. A hardware driver: the market serves its fake backend, so no instrument is needed.

hardwareRisk R0Apache-2.0contract_checkedserved on the fake backend
openai4s lab add robots/realsenseai__realsense-ros
All install options REFERENCE.md Upstream repository Registry record

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 robots/realsenseai__realsense-ros

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 robots/realsenseai__realsense-ros --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": {
    "realsense-ros": {
      "command": "python3",
      "args": [
        "-m",
        "mhs",
        "serve",
        "robots/realsenseai__realsense-ros",
        "--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

  • frame_id
  • width
  • height
  • device_name
  • serial_number
  • firmware_version
  • read_camera_info
  • read_device_info
  • read_frame_metadata
  • read_color_camera_info
  • read_depth_camera_info
  • read_color_metadata
  • read_depth_metadata

Adjusts

Nothing declared.

Actions

capture_image
Capture a single image from a named camera with a declared resolution and exposure and return an image artifact reference.
capture_point_cloud
Capture a depth point cloud over a declared range and return a point-cloud artifact reference with the point count and coordinate frame.

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 robots/realsenseai__realsense-ros
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
7a87097c499e
Licence
Apache-2.0
Stars
3,464
Evidence
contract_checked on the fake backend
Backends
fake

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