Gausium OpenAPI

MCP Server for Gausium Robot OpenAPI - Control and monitor Gausium cleaning robots through AI assistants

python

0

GitHub Stars

python

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "cfrs2005-mcp-gs-robot": {
      "command": "mcp-gs-robot",
      "args": [],
      "env": {
        "GS_CLIENT_ID": "your_client_id",
        "GS_CLIENT_SECRET": "your_client_secret",
        "GS_OPEN_ACCESS_KEY": "your_access_key"
      }
    }
  }
}

You can connect AI models and assistants to Gausium cleaning robots through a dedicated MCP server. It provides a standardized interface to list robots, view status, manage maps and tasks, and run automated workflows, enabling seamless AI-first control and monitoring of your robot fleet.

How to use

You interact with the server through an MCP client. Start by running the local MCP bridge, which exposes a set of endpoints you can call from your AI tools. Typical usage patterns include listing all accessible robots, checking a robot’s current status, selecting a map for navigation, and submitting clean tasks. You can also rely on smart routing tools to automatically pick the right API version for a robot and route task reports intelligently. Use the provided tools to orchestrate end-to-end automated workflows from status to execution.

To integrate with Claude Code or Cursor, install the MCP server locally or run it from your environment, then configure your MCP client to connect to the local stdio bridge. The server is designed to work with stdio transport for tight integration with AI assistants. After setup, you can issue commands such as listing robots, retrieving detailed robot status, and submitting temporary tasks, all from natural language prompts or code-driven workflows.

How to install

Prerequisites you need on your system before installing this MCP server: Python 3.x and an environment manager such as uv (uvx). You may also install via pip if you prefer a prebuilt package.

# Option 1: Install from PyPI (recommended)
pip install mcp-gs-robot

# Option 2: Install from source
# Clone repository
git clone https://github.com/cfrs2005/mcp-gs-robot.git
cd mcp-gs-robot

# Setup with uv (recommended)
uv venv
source .venv/bin/activate  # Windows: .venv\Scripts\activate
uv pip install -e .

Additional notes

Configure your Gausium API credentials before starting the server. You need the following environment variables set with your actual values: GS_CLIENT_ID, GS_CLIENT_SECRET, GS_OPEN_ACCESS_KEY.

Run the MCP server in stdio mode for Claude Code integration. You will typically start the server with the following command, depending on how you installed it.

# Start MCP server (stdio mode) using Python module entry
python -m gs_openapi.main

# Or, if installed via pip
mcp-gs-robot

Available tools

list_robots

List all accessible robots connected to the MCP server.

get_robot_status

Return detailed status information for a specific robot, including position and health.

list_robot_task_reports

Retrieve historical task reports with optional filtering.

list_robot_maps

List available maps for robot navigation.

create_robot_command

Send a command to a robot to start, pause, or stop a task.

get_site_info

Provide building and floor information for context-aware tasks.

get_map_subareas

Get detailed area information for a map to guide tasks.

submit_temp_task

Submit temporary or ad-hoc cleaning tasks.

get_robot_status_smart

Auto-select V1/V2 API based on robot series for status queries.

get_task_reports_smart

Intelligent routing for task report retrieval.

get_robot_capabilities

Expose supported APIs for a specific robot model.