{"id":"pyautogui-mcp-server","name":"pyautogui-mcp-server","af_score":40.8,"security_score":28.0,"reliability_score":20.0,"what_it_does":"Provides an MCP server (Streamable HTTP) that runs Python code in a fresh interpreter state with pyautogui instrumentation, returning captured stdout/stderr/results and inline screenshots (including mouse-operation previews). Includes a macOS-only helper to keep the display awake before automation.","best_when":"You control the client/agent and want an MCP tool to execute pyautogui-driven UI steps and receive logs + screenshots as structured tool outputs.","avoid_when":"You need strong security boundaries (e.g., running untrusted code) or you cannot grant the server/API full control over UI automation and screen capture.","last_evaluated":"2026-04-04T21:47:23.379251+00:00","has_mcp":true,"has_api":false,"auth_methods":[],"has_free_tier":false,"known_gotchas":["GUI automation is inherently stateful; retries can repeat mouse actions unless the agent adds its own guardrails","Running Python code remotely can be dangerous unless you fully trust the caller; no sandboxing guarantees are described","Screenshot coordinates may drift if display scaling/coordinate mapping differs; normalization is mentioned but not configured/documented in detail"],"error_quality":0.0}