Qontinui

Provides an MCP server that loads, runs, and monitors AI-driven visual workflows via the Qontinui Runner.

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": {
    "qontinui-qontinui-mcp": {
      "command": "qontinui-mcp",
      "args": [],
      "env": {
        "QONTINUI_RUNNER_HOST": "localhost",
        "QONTINUI_RUNNER_PORT": "9876"
      }
    }
  }
}

You can run the Qontinui MCP Server to let your AI agent drive visual automation workflows through the Qontinui Runner. This lightweight server exposes controls for loading configurations, starting workflows, monitoring progress, and selecting the monitor you want to operate on, enabling seamless AI-driven automation flows.

How to use

Use the MCP client to interact with the Qontinui MCP Server. You can load workflow configurations, start and monitor visual automation workflows, and control which monitor to use during execution. The server is designed to work with AI clients that can issue commands to load configurations, run specific workflows by name, and query execution status.

Typical usage pattern:

Load a workflow configuration file
Run a named workflow on a chosen monitor
Monitor execution status and results
Stop execution if needed or adjust which monitor to use for subsequent steps.

How to install

Prerequisites: Python and pip must be installed on your system.

Install the MCP server package using Python’s package manager.

pip install qontinui-mcp

Additional setup and quick start

Configure your MCP to use the Qontinui MCP Server by referencing the following stdio configuration in your MCP setup.

{
  "mcpServers": {
    "qontinui": {
      "command": "qontinui-mcp",
      "args": []
    }
  }
}

Notes on running and environment

Environment variables you can use with the Qontinui MCP Server include details about how to connect to the Qontinui Runner. Specifically, you can set the runner host and port to customize how the MCP server communicates with the runner environment.

Usage example with AI

In an AI workflow, you might instruct the system to "Load the config at /path/to/workflow.json and run the 'login_test' workflow on the left monitor" to kick off a sequence of visual automation steps.

Development and contribution

The server is built to be lightweight and easy to integrate with AI clients. If you need to contribute, install development dependencies and run the local server to test changes.

Available tools

get_executor_status

Get runner status including current activity and health indicators.

list_monitors

List available monitors connected to the Qontinui Runner.

load_config

Load a workflow configuration file into the MCP server for execution.

ensure_config_loaded

Load the configuration if it has not already been loaded.

get_loaded_config

Retrieve information about the currently loaded workflow configuration.

run_workflow

Run a specific workflow by name, optionally targeting a particular monitor.

stop_execution

Stop the currently running workflow or automation.