qontinui-mcp
MCP 服务配置
复制以下 JSON 到 OPClaw 或其他 MCP 客户端的配置文件中即可使用
{
"mcpServers": {
"qontinui": {
"args": [],
"command": "qontinui-mcp"
}
}
}
服务介绍
qontinui-mcp
Lightweight MCP server for Qontinui Runner - enables AI-driven visual automation.
Installation
pip install qontinui-mcp
Quick Start
-
Start the Qontinui Runner (desktop application)
-
Configure your AI client (Claude Desktop, Claude Code, Cursor, etc.)
Add to your MCP configuration:
{
"mcpServers": {
"qontinui": {
"command": "qontinui-mcp",
"args": []
}
}
}
- 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:
| Variable | Description | Default |
|---|---|---|
QONTINUI_RUNNER_HOST |
Runner host address | Auto-detected (WSL-aware) |
QONTINUI_RUNNER_PORT |
Runner HTTP port | 9876 |
Available Tools
| Tool | Description |
|---|---|
get_executor_status |
Get runner status |
list_monitors |
List available monitors |
load_config |
Load a workflow configuration file |
ensure_config_loaded |
Load config if not already loaded |
get_loaded_config |
Get loaded configuration info |
run_workflow |
Run a workflow by name |
stop_execution |
Stop 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