"author:iamxicor" matching MCP servers:

Enables AI agents to control iOS Simulator apps by reading the screen as compact text instead of screenshots and returning the updated screen after every action. Supports tapping, typing, scrolling, key presses, and app or URL launches with one tool call per step instead of two.

Exposes the React Native performance harness to any agent, letting it connect to a running dev build, capture render and flamegraph traces, and turn them into deterministic findings with ranked per-route tables. Enables agents to run A/A noise-floor calibration, interleaved A/B measurements, gates, and PR-body generation from validated verdicts.