MCP Hub
Back to servers

qontinui-mcp

A lightweight MCP server that provides an interface for the Qontinui Runner desktop application, enabling AI agents to load, run, and monitor visual automation workflows.

Tools
7
Updated
Jan 9, 2026
Validated
Jan 11, 2026

qontinui-mcp

Lightweight MCP server for Qontinui Runner - enables AI-driven visual automation.

Installation

pip install qontinui-mcp

Quick Start

  1. Start the Qontinui Runner (desktop application)

  2. Configure your AI client (Claude Desktop, Claude Code, Cursor, etc.)

Add to your MCP configuration:

{
  "mcpServers": {
    "qontinui": {
      "command": "qontinui-mcp",
      "args": []
    }
  }
}
  1. Run workflows via AI

The AI can now:

  • Load workflow configuration files
  • Run visual automation workflows
  • Monitor execution status
  • Control which monitor to use

Configuration

Environment variables:

VariableDescriptionDefault
QONTINUI_RUNNER_HOSTRunner host addressAuto-detected (WSL-aware)
QONTINUI_RUNNER_PORTRunner HTTP port9876

Available Tools

ToolDescription
get_executor_statusGet runner status
list_monitorsList available monitors
load_configLoad a workflow configuration file
ensure_config_loadedLoad config if not already loaded
get_loaded_configGet loaded configuration info
run_workflowRun a workflow by name
stop_executionStop current execution

Example Usage

# In an AI conversation:
"Load the config at /path/to/workflow.json and run the 'login_test' workflow on the left monitor"

Development

# Clone
git clone https://github.com/qontinui/qontinui-mcp
cd qontinui-mcp

# Install dependencies
poetry install

# Run server locally
poetry run qontinui-mcp

License

MIT

Reviews

No reviews yet

Sign in to write a review