qontinui-lib-mcp
Enables AI-powered visual automation workflows by providing tools for searching nodes, creating and validating workflows, and executing automation scripts via natural language.
README
Qontinui MCP Server (Python)
MCP server for Qontinui visual automation - enables AI-powered workflow generation and execution.
Features
Knowledge Tools
- search_nodes - Search for action nodes using natural language
- search_workflows - Search for workflow templates
- get_nodes_by_category - Filter nodes by category
- get_nodes_by_action_type - Filter by action type (CLICK, FIND, TYPE, etc.)
- list_categories - List all available categories
- get_action_details - Get detailed node information
Workflow Tools
- validate_workflow - Validate workflow structure with cycle detection
- create_workflow - Create workflow from action steps
- generate_workflow - Generate workflow from natural language description
Execution Tools (requires qontinui library)
- run_automation - Execute automation scripts
- capture_screenshot - Capture current screen
- assert_state_visible - Assert visual state is on screen
- wait_for_state - Wait until state appears
- compare_screenshots - Visual diff between images
- is_execution_available - Check if execution is available
Installation
cd qontinui-mcp-py
poetry install
Usage
Run the MCP server
poetry run qontinui-mcp
Configure with Claude Desktop
Add to ~/.config/claude/claude_desktop_config.json (Linux) or equivalent:
{
"mcpServers": {
"qontinui": {
"command": "poetry",
"args": ["run", "qontinui-mcp"],
"cwd": "/path/to/qontinui-mcp-py"
}
}
}
Or using the installed script:
{
"mcpServers": {
"qontinui": {
"command": "/path/to/qontinui-mcp-py/.venv/bin/qontinui-mcp"
}
}
}
Development
# Install dependencies
poetry install
# Run in development
poetry run python -m qontinui_mcp.server
# Format + lint
poetry run ruff format .
poetry run ruff check .
poetry run mypy src/
Architecture
qontinui-mcp-py/
├── src/qontinui_mcp/
│ ├── __init__.py
│ ├── server.py # MCP server implementation
│ ├── database/
│ │ ├── __init__.py
│ │ ├── schema.sql # SQLite + FTS5 schema
│ │ ├── loader.py # DB initialization
│ │ └── search.py # FTS5 search functions
│ ├── tools/
│ │ ├── __init__.py
│ │ ├── generator.py # Workflow generation
│ │ └── execution.py # Automation execution
│ ├── types/
│ │ ├── __init__.py
│ │ └── models.py # Pydantic models
│ └── utils/
│ ├── __init__.py
│ └── validation.py # Workflow validation
├── pyproject.toml
└── README.md
Action Types Supported
Basic Actions
- FIND, CLICK, DOUBLE_CLICK, RIGHT_CLICK, MIDDLE_CLICK
- DEFINE, TYPE, MOVE, HOVER
- VANISH, WAIT_VANISH, HIGHLIGHT
- SCROLL_MOUSE_WHEEL, SCROLL_UP, SCROLL_DOWN
- MOUSE_DOWN, MOUSE_UP, KEY_DOWN, KEY_UP
- CLASSIFY
Composite Actions
- CLICK_UNTIL, DRAG, RUN_PROCESS
Database
The server uses SQLite with FTS5 for full-text search:
- Location:
~/.qontinui/mcp/qontinui.db - Auto-created on first run
- Supports fuzzy search with ranking
License
Licensed under the GNU Affero General Public License v3.0 or later (AGPL-3.0-or-later). See LICENSE for full terms.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.