loaditout.ai
SkillsPacksTrendingLeaderboardAPI DocsBlogSubmitRequestsCompareAgentsXPrivacyDisclaimer
{}loaditout.ai
Skills & MCPPacksBlog

pyautogui_mcp_server

MCP Tool

on-panda/pyautogui_mcp_server

MCP server for simplest GUI agent đŸ•šī¸đŸ¤–

Install

$ npx loaditout add on-panda/pyautogui_mcp_server

Platform-specific configuration:

.claude/settings.json
{
  "mcpServers": {
    "pyautogui_mcp_server": {
      "command": "npx",
      "args": [
        "-y",
        "pyautogui_mcp_server"
      ]
    }
  }
}

Add the config above to .claude/settings.json under the mcpServers key.

About

MCP server for simplest GUI agent đŸ•šī¸đŸ¤–

pyautogui_mcp_server packages a Streamable HTTP MCP server for running Python code with pyautogui instrumentation.

It is designed for GUI automation workflows where plain pyautogui execution is not enough. The package adds MCP-friendly output handling, richer screenshots, and a small macOS display wake helper.

✨ What this package adds

Compared with running raw pyautogui calls directly, this library adds extra effort in the following areas:

  • Fresh Python execution state for every tool call.
  • Captured stdout, stderr, and final expression results in one MCP response stream.
  • Inline screenshot delivery as MCP image content instead of requiring manual file handling.
  • Annotated mouse-operation previews that show the target point or path before the action runs.
  • Screenshot normalization so captured images line up better with logical screen coordinates.
  • A separate macOS wake command for waking the display before automation starts.
đŸ› ī¸ Tool response example
<stdout>
Cut the right rope by dragging left to right through it.
</stdout>
<pyautogui-mcp.dragTo x=860 y=430 duration=0.2 button='left' 
    time_offset="T+1.1s" pyautogui.size=(1440, 900)>

</pyautogui-mcp.dragTo>
đŸ“Ļ Installation
pip install pyautogui_mcp_server

For local development:

pip install -e .[dev]
🚀 Run the MCP server

Use the module entrypoint:

python -m pyautogui_mcp_server --host 127.0.0.1 --port 9300

Or use the installed console script:

pyautogui-mcp-server --port 9300

Show CLI help:

python -m pyautogui_mcp_server --help

The server exposes a run_python_with_pyautogui MCP tool that executes Python in a fresh interpreter state with instrumented pyautogui behavior.

đŸ–Ĩī¸ Wake a macOS dis

Tags

gui-agentmcpmcp-serverpyautogui

Reviews

Loading reviews...

Quality Signals

0
Installs
Last updated29 days ago
Security: AREADME

Safety

Risk Levelmedium
Data Access
read
Network Accessnone

Details

Sourcegithub-crawl
Last commit3/20/2026
View on GitHub→

Embed Badge

[![Loaditout](https://loaditout.ai/api/badge/on-panda/pyautogui_mcp_server)](https://loaditout.ai/skills/on-panda/pyautogui_mcp_server)