twiddle-mcp
An MCP server that lets coding agents drive and verify mobile apps on iOS Simulator and Android Emulator, providing blocking wait primitives and semantic UI diffs to replace screenshot polling.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
roti-c137
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
wait_forwait_for_idleBLOCK until the UI stops changing (animations/loads settled). Volatile elements like clocks and spinners marked noisy are ignored. Use after navigation before reading the screen.
get_ui_treeGet the current accessibility tree as structured text with [ref=eN] markers usable in tap/type_text. Much cheaper and more precise than a screenshot.
ui_diffSemantic diff of the current UI vs a previous snapshot (default: the last one this server took). Answers 'what changed?' without comparing screenshots.
list_devicesList iOS simulators and Android emulators/devices. Booted devices first; use the returned id with every other tool.
launch_appLaunch an app by iOS bundle id or Android package name.
terminate_appTerminate a running app.
tapTap an element by [ref=eN] from get_ui_tree/wait_for, by selector, or by x/y. Refs re-resolve against the live tree; if the element is gone you get the current tree instead of a blind tap. With scroll:true, a selector that isn't on screen is searched for by scrolling through the content first. Retur…
type_textType text into the focused field (optionally tap a field first via ref/selector). submit presses Enter/Return.
swipeSwipe in a direction (from screen center) or between explicit points.
press_buttonPress a device button (home, back [Android], volumeUp, volumeDown, enter).
handle_alertAccept or dismiss a blocking alert/dialog (system permission prompts, 'Open in …?' sheets, in-app modals). Finds the right button from the current UI tree — no coordinates needed. Use buttonText for a specific button. Returns what was tapped and what changed; if no alert is present you get the curre…
screenshotPNG screenshot — the fallback for purely visual checks (colors, images, layout polish). For text/structure, prefer get_ui_tree or wait_for: cheaper and more precise.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
When Vitest UI server is listening, arbitrary file can be read and executed
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
undici vulnerable to cross-user information disclosure and parse-time crash via degenerate private cache directives
IOS_UDIDONLYTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
13/13 tools missing one or more hints — wait_for (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); wait_for_idle (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_ui_tree (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +10 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tool test coverage
Only 3/13 tools referenced in tests (23%)
Write tests that reference each tool by name so every tool has at least one test.
Shell command execution
2 calls in production code run through a shell (bench/mechanism-ios.mjs:92, bench/mechanism-ios.mjs:101)
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Production dependencies are patched
0 critical, 8 high severity in production deps — @modelcontextprotocol/sdk@1.12.0 (high), @modelcontextprotocol/sdk@1.12.0 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Dev dependencies
1 critical/high in dev-only deps (does not ship to users)
Upgrade dev dependencies when convenient.
Domain consistency
npm scope @twiddlethumb doesn't match GitHub owner roti-c137
Use the same org name across GitHub, npm, and your homepage so users can verify the publisher.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/roti-c137/twiddle-mcp)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check