# automate-mcp

Source: https://glimind.com/server/pypi%2Fautomate-mcp
Registry id: `pypi/automate-mcp`
Status: unknown

## Install

```json
{
  "mcpServers": {
    "automate-mcp": {
      "command": "uvx",
      "args": [
        "automate-mcp"
      ]
    }
  }
}
```

Claude Code:

```sh
claude mcp add automate-mcp -- uvx automate-mcp
```

## Tools (19)

- `click`: Click at screen coordinates
- `cloud_vision_config`: Show current cloud vision configuration status
- `delete_script`: Delete a script
- `double_click`: Double-click at screen coordinates
- `drag`: Drag from one position to another
- `install_script`: Install a script from a URL or the community library
- `list_scripts`: Show all saved automation scripts
- `mouse_move`: Move cursor without clicking
- `parse_screen`: Detect all UI elements via cloud OmniParser
- `press_key`: Press a key or combo (e.g. ctrl+c, win)
- `reason_action`: Ask a VLM what GUI action to take next
- `run_script`: Run a saved script by name
- `save_script`: Save the current workflow as a reusable script
- `screenshot`: Capture the screen and return as base64 PNG
- `scroll`: Scroll up or down
- `show_script`: View a script's contents
- `smart_act`: Full autonomous loop: parse → reason → execute → repeat
- `type_text`: Type text (full Unicode / CJK support)
- `warm_endpoints`: Wake up scaled-to-zero HF endpoints before use

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.