PyAutoGUI
MCP-PyAutoGUI-Server provides automated GUI testing and control capabilities through a Python-based interface. Developed by He Tao, this server wraps the PyAutoGUI library to enable AI assistants to control mouse movements, simulate keyboard input, take screenshots, and find images on screen across Windows, macOS, and Linux. The implementation offers tools for precise cursor positioning, clicking, typing text, pressing hotkeys, and screen analysis through a standardized protocol. It's particularly useful for automating repetitive GUI tasks, creating test scripts, or allowing AI systems to interact directly with desktop applications through visual interfaces.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- media
- Source
- PulseMCP
- Repository
- github.com/hetaobackend/mcp-pyautogui-server
- Author type
- human
- Updated
- 2026-05-22
Use via MCP
Resolve PyAutoGUI from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp --scope user for --scope project to commit it to .mcp.json.