simframe MCP server

Read from the package source without running it. The installed server may list more.

• sim_assert

  Check one thing about the screen and fail loudly if it is not so. Cheaper inside a sim_do flow, where a failed assert stops the remaining steps.

• sim_capture

  Inspect or control the background capture loops: action "status" (what is running and how fresh), "start", "stop". Capture starts automatically on first use, so you rarely need this.

• sim_devices

  List the devices simframe can drive — iOS simulators and Android emulators.

• sim_do

  THE MAIN TOOL, and the cheapest path. Plan the WHOLE flow and run it in one call — tap, type, scroll, wait, assert — asserting after each step that matters. Every step settles and is checked against what that action did here before, so a wrong turn halts the flow instead of tapping on. Single-action tools are for recovery.

• sim_find

  Resolve one intent to one control: "tap Save", "the Assets tab", "back". Understands verbs, typos, and where on screen you meant. When two things answer equally well it says so and lists them rather than guessing. Use it when you doubt a selector will resolve; otherwise just tap. Prefer a label or a #ref over coordinates.

• sim_flow_runwrite action

  Replay a saved flow by name, verifying each step. Omit `name` to list the saved flows. Save one with sim_do's `saveAs`.

• sim_goal

  Hand simframe a goal in words and let it drive there locally, returning only at a milestone: done (with evidence), blocked by the verify barrier, ambiguous, not found, or out of budget. Use it instead of a sequence of single taps when you know where you want to be: "open Time Sheets", "find Larger Text", "Settings > Accessibility > Display & Text Size". It walks remembered routes first, taps what

• sim_goto

  Walk to a screen simframe already knows, over edges it has already verified, with no model call per step. Names come from sim_recall or a previous map. Refuses rather than guesses when the route is unknown or the name is ambiguous — a refusal is cheap and a wrong walk is not.

• sim_launch

  Launch or relaunch an app, optionally with launch arguments and environment variables — the way to put an app into a test mode without touching its UI.

• sim_look

  A screenshot: ~1600 tokens, the most expensive call here. Only for what text cannot answer — layout, colour, spacing, a control the map omits. NOT for what a field contains, whether a button is enabled, or whether an action worked: sim_ui reports the first two and the flow's own verdict already answered the third.

• sim_map

  Crawl an app unattended and record every screen and transition into the graph, so later goals and sim_goto are served from memory with no model calls. Opt-in and slow on purpose: minutes, not seconds. Read-only by default — it opens doors and never types, toggles, or opens a write flow; the verify barrier (Delete, Pay, Send, Sign out, Submit, Save…) and leaving the app are never crossed. Resumes a

• sim_open_url

  Open a URL or deep link on the device — the fastest way to reach a screen when the app has a link for it.

• sim_permission

  Grant, revoke or reset a privacy permission for an app. Do this instead of tapping the system alert: the alert is not part of the app under test, and its buttons move between OS versions. Not every service exists on every platform — the device's own backend refuses one it does not have. Services: ….

• sim_recall

  What happened recently, as text: the screens visited, the actions taken, and what each one did. Use it to re-orient after a failure instead of taking a screenshot, and to learn the screen names sim_goto accepts.

• sim_scroll_to

  Scroll until something is in view. A control that scrolled off the bottom of a list is not missing, and this is the difference.

• sim_state

  Cheapest possible check: a stable screen hash, whether anything changed SINCE YOUR LAST LOOK in this session, how long the screen has been still, and an ASCII map of which regions moved. A fraction of the cost of even the text screen map. Use it to poll ("has it finished loading?"). To find out WHAT is on screen, use sim_ui.

• sim_storage

  What the app saved, as text: its UserDefaults and (for React Native) its AsyncStorage, read straight out of

• sim_strip

  Return the last few buffered frames tiled into ONE image, oldest first — an image, so not cheap. Lets you understand a transition, animation or flicker in a single call instead of a burst of screenshots. Looks backwards in time; it does not wait.

• sim_tap

  Tap one thing. For more than one step, use sim_do — it batches the verification and costs one round trip. Returns the screen map afterwards.

• sim_type_into

  Focus a field and type into it. Prefer a sim_do step when this is part of a sequence.

• sim_ui

  READ THE SCREEN as text: every element numbered, with region, type, label, state, contents and tap point, plus which screen this is and what simframe knows about it. A tenth the cost of a screenshot and more useful, because it says what is tappable and where. Act on what it shows by NAME — whatever it calls "General", you can tap as "General"; the #3 numbers are exact but only until the screen mov

• sim_wait

  Wait for the screen to change, settle, or both. sim_do already settles after every step, so you rarely need this inside a flow — reach for it when something moves without you acting, like a push or a background load. Pass `since` from a hash captured before the thing you are waiting on.

• sim_wait_for

  Block until something appears on screen, then return the screen map. Use this instead of pausing and re-reading.

• Code scan48 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitylocal package, no credentials required12/15
• Maintenancelast push 10 days ago15/15
• Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Safety score

92/100

higher than 95% of 48,255 servers

Tools

23

the typical server has 7

Tools that change things

4%

typical: 0%. Fewer write tools means less an agent can break

Downloads a week

1,219

more than 95% of 12,191 servers with a package

Grade history

• 2026-09-19restoreB → Ascore 92
• 2026-09-19restoreC → Bscore 74: Shell command built from a string (injection risk)

simframe: common questions

Is simframe MCP server safe?

Yes, by our scan: it is graded A (92/100). Read the simframe safety report

How do I install simframe?

It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.

Does simframe need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is simframe maintained?

The last commit was 30 days ago (2026-10-05). The latest release is v0.23.1.

What can I use instead of simframe?

Servers from other publishers that do the same job: Mobilerun MCP server, Mobile MCP server and MCP Appium - Mobile Development and Automation Server MCP server. Compare all simframe alternatives.

How does simframe compare with other MCP servers?

safety score 92/100 (higher than 95% of 48,255 servers); tools 23 (the typical server has 7); tools that change things 4% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.