anon.li
Let your agent manage private email aliases and encrypted file drops over OAuth MCP
iOS Simulator MCP
Lets your coding agent tap, type, swipe and screenshot its way through the iOS Simulator
About
Write code, screenshot the result, iterate
Add it with claude mcp add ios-simulator npx ios-simulator-mcp and ask something like "launch my app, tap through onboarding and screenshot every screen". Tools include get_booted_sim_id, ui_describe_all, ui_tap, ui_type, ui_swipe, screenshot and video recording, plus app install and launch. Anthropic's Claude Code best practices post points to it for the screenshot and iterate loop. Things to know: it needs a Mac with Xcode simulators, Node and Facebook IDB, and versions before 1.3.3 had a command injection bug, so stay on a current release (2.1.0 as of August 2026). Built by Joshua Yoes, MIT, about 2.2k GitHub stars.
Features
- Reads the full accessibility tree of the current screen
- Tap, type, swipe and long press by coordinates
- Screenshots and screen recordings of a run
- Install and launch apps on a booted simulator
- One line setup with npx
- Works with Claude Code, Cursor and other MCP clients
Install
Related skills
All skillsRelated articles
All articlesHow to Let Claude Code Test Your Mobile App
Give Claude Code hands in the iOS Simulator or an Android emulator so it checks its own UI changes. Five MCP tools, real setup commands, honest tradeoffs.
Browser Automation for AI Agents (2026)
I compare five ways to give an AI agent a browser, from local Chrome over MCP to hosted cloud browsers, with real install commands and pricing.
Langfuse vs Braintrust (2026): Pricing, Self-Hosting, MCP
I compare Langfuse and Braintrust for LLM tracing and evals: free tiers, paid plans, self-hosting, open source status and their MCP servers.
