M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
COMPARE UP TO 4 SERVERS

Compare MCP servers

Compare scores, permissions, risks, and fit in one decision-focused table.

DimensioniOS Simulator MCP ServerInteract with and inspect iOS simulators through MCP.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS56 / 100 · C79 / 100 · B
Reliability8 / 2012 / 20
Security and permissions10 / 2018 / 20
Maintenance10 / 2016 / 20
Documentation15 / 2018 / 20
Setup experience13 / 2015 / 20
Best for
  • Teams developing or performing QA with macOS, Xcode, and iOS simulators
  • Users who want an AI assistant to perform mobile UI validation through MCP
  • Developers checking the iOS accessibility tree and UI responses
  • Engineering teams scaling AI coding agents while controlling spend
  • Platform teams that need auditable, rollback-aware agent execution records
  • Organizations using multiple agents (Claude, Codex, Gemini) under one governed flow
Not for
  • Environments without macOS, Xcode, or iOS simulators
  • Testing scenarios that require a physical iOS device
  • Tasks that do not need simulator control, inspection, or app installation
  • Developers who just want a simple code-completion helper without run governance
  • Teams unwilling to accept local JSONL run records with HMAC signing
  • Environments without a supported adapter (Claude/Codex/Gemini CLIs, direct provider, or verifier-only)
Required permissions
  • Requires access to the iOS Simulator and Xcode tools on macOS.
  • Requires Facebook IDB; by default, idb is resolved from PATH, or IOS_SIMULATOR_MCP_IDB_PATH can specify a custom path.
  • Screenshot and video features need write access to the output directory; the default is ~/Downloads, configurable with IOS_SIMULATOR_MCP_DEFAULT_OUTPUT_DIR.
  • App installation and launch require an application path or bundle identifier.
  • Read/write access to the configured repo root (writable scope restrictable via --allow-path/--deny-path)
  • Ability to invoke the chosen agent CLI (Claude/Codex/Gemini, etc.) and its underlying model account
  • Local disk writes for run records, receipts, and share outputs (share/run-receipt., etc.)
  • Execution of user-configured verifier commands (e.g. npm test)
Risks and side effects
  • ui_tap, ui_type, ui_swipe, install_app, and launch_app can change simulator or application state.
  • Screenshots and videos may save simulator screen content to local files.
  • Versions below 1.3.3 have command injection vulnerabilities; the README states this is fixed and recommends version 1.3.3 or later.
  • Text input supports ASCII printable characters only.
  • Verifier commands are executed; poorly chosen verifier commands carry security risk despite preflight policy checks
  • Cost and token figures may be estimates (labeled with provenance) and should not be treated as settled accounting
  • Receipt integrity must be verified before use as trustworthy evidence; missing rollback evidence is flagged as EVIDENCE_BOUNDARY
  • Policy defaults come from martin.config.yaml and can be overridden by CLI flags; misconfiguration can loosen safety boundaries
Supported clientsCursor, Claude CodeClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools140