Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

agemu

NPM · AGENTIC-EMULATOR

Fast Android emulator and iOS Simulator control for coding agents: screenshots, UI tree, taps, logs

Available components

+18 this week 82 Trust /100

Last scanned (19 hours ago)

Scores higher than 71% of npm servers

Category Testing and QA

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency100
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to piotr-graczyk-dev/agentic-emulator). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 5 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability69
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 3642 tokens (~117/item across 31 items; 31 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management23
  • Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "shutdown" implies "shutdown" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 32 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (16)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Nov 26 +16
    • Malware scan: unverified → pass ▲ security
  • 15 Nov 26 0
    • Malware scan: unverified → pass ▲ security
    • Stability: unverified → 0.03 ▲ functional
    • Package version: 0.2.1 → 0.2.2 functional
  • 14 Nov 26 64

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Analysed npm/agentic-emulator@0.2.2

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem npm
Reason Verified
Discovered via Registry attestation endpoint
Source repo piotr-graczyk-dev/agentic-emulator
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/piotr-graczyk-dev/agentic-emulator/.github/workflows/release.yml@refs/tags/v0.2.2
Rekor log index 3898855366
Predicate type SLSA build provenance https://slsa.dev/provenance/v1
Subject digest sha512:04a9bfffaa40defd196bfc6723db5efdb342019e37b7fef7719524ab406db608be5854ca8e0d1c4f0e66ba4501e62b241a39797b9c73b69f507745145

Background: How many MCP packages publish verified provenance →

Dependencies 0 packages
Packages resolved 0
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 31 exposed · ~3,505 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
appearance ~53

Read the system appearance, or switch light/dark mode.

NameTypeReqDescription
devicestring–Device id or name (optional when exactly one device is booted)
modestring–Omit to read the current appearance

No output schema declared.

No examples provided.

apps ~38

List installed user apps (not the system image's).

NameTypeReqDescription
devicestring–Device id or name (optional when exactly one device is booted)

No output schema declared.

No examples provided.

boot ~163

Boot a device to an agent-ready state; from its baseline snapshot this takes seconds and returns state booted. The first boot of a new Android device (or a baseline retake after a GPU mode, AVD configuration or agemu upgrade) prepares the baseline once, which usually takes 7-8 minutes and never more than 20 (then the boot fails): boot then returns at once with state "preparing" and the phase; poll devices every 30-60 s (or call boot again) until the state is booted. Other calls on a preparing device fail at once with an error saying so.

NameTypeReqDescription
coldboolean–Force a cold boot
devicestring–Device id or name (optional when exactly one device is booted)

No output schema declared.

No examples provided.

clear_app_data ~77

Clear one app's data so it starts like a fresh install (stopped, data and permissions gone; iOS keeps keychain items, as a reinstall does on a device).

NameTypeReqDescription
appstringyesPackage name or bundle id
devicestring–Device id or name (optional when exactly one device is booted)

No output schema declared.

No examples provided.

clipboard ~78

Read the device clipboard (plain text), or set it.

NameTypeReqDescription
actionstring–get (default) or set (default when text is given)
devicestring–Device id or name (optional when exactly one device is booted)
textstring–Text to put on the clipboard (action set; empty clears it)

No output schema declared.

No examples provided.

crashes ~172

Crash, ANR (Android), system-kill (iOS watchdog, jetsam) and unexpected-exit reports of the device's apps, oldest first: time, kind, exception, reason and the crashing thread's top frames.

NameTypeReqDescription
appstring–Package name or bundle id (default: every app)
devicestring–Device id or name (optional when exactly one device is booted)
jsonboolean–Return JSON instead of text
limitnumber–At most this many reports, the newest (default 10, max 100)
sincestring–A time (2026-11-07T10:00:00Z), a duration back from now (5m) or "launch" (the app's last launch through agemu)

No output schema declared.

No examples provided.

create ~40

Create a new device.

NameTypeReqDescription
namestringyesDevice name
platformstringyesandroid or ios
profilestring–Profile name

No output schema declared.

No examples provided.

devices ~21

List Android and iOS devices with state, profile and screen size.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

find ~120

Find elements by text/label/id/role.

NameTypeReqDescription
containsstring–Case-insensitive substring of text or label
devicestring–Device id or name (optional when exactly one device is booted)
idstring–resource-id (Android) or accessibilityIdentifier (iOS)
indexnumber–Pick the n-th match (0-based)
rolestring–Normalized role: button, text, textfield, switch, image, cell...
textstring–Exact text or accessibility label

No output schema declared.

No examples provided.

install ~51

Install an app (.apk for Android, .app for iOS Simulator).

NameTypeReqDescription
devicestring–Device id or name (optional when exactly one device is booted)
pathstringyesAbsolute path

No output schema declared.

No examples provided.

launch ~209

Launch an app by package name / bundle id. iOS also takes process arguments (e.g. an Expo dev client's --initialUrl), environment and relaunch.

NameTypeReqDescription
appstringyesPackage name or bundle id
argsarray–Process arguments (iOS)
devicestring–Device id or name (optional when exactly one device is booted)
envobject–Process environment (iOS)
relaunchboolean–Terminate a running instance first (iOS)
returnUiboolean–Also return the UI outline of the screen the action ends on (act, wait and observe in one call)
waitForobject–After the action, wait for an element matching this selector (fields: text, contains, id, role) in the same call
waitGoneboolean–Wait for waitFor to disappear instead
waitTimeoutMsnumber–Timeout for waitFor, default 10000

No output schema declared.

No examples provided.

location ~87

Set the simulated GPS location, or clear it (back to the device's baseline).

NameTypeReqDescription
actionstring–set (default when coordinates are given) or clear
devicestring–Device id or name (optional when exactly one device is booted)
latitudenumber–Degrees, -90..90
longitudenumber–Degrees, -180..180

No output schema declared.

No examples provided.

logs ~305

Recent log lines of one app (or the whole device), oldest first, as `time level process[pid] tag: message`. Filter by time, minimum level and text; the newest lines that fit limit and maxBytes are returned. The last line gives a cursor: pass it as since to read only newer lines.

NameTypeReqDescription
appstring–Package name or bundle id: only its processes' lines (default: every process)
containsstring–Case-insensitive substring of the tag or the message
devicestring–Device id or name (optional when exactly one device is booted)
jsonboolean–Return JSON instead of text lines
levelstring–Minimum level (iOS: debug lines are not captured; info includes iOS default)
limitnumber–At most this many lines, the newest (default 100, max 10000)
maxBytesnumber–At most about this many bytes of lines (default 16384, max 1048576)
regexstring–RE2 regular expression matched against the tag or the message
sincestring–Only lines from this point: a time (2026-11-07T10:00:00Z), a duration back from now (30s, 5m), "launch" (the app's last launch through agemu) or a cursor from a previous logs result (c123...)

No output schema declared.

No examples provided.

open_url ~198

Open a URL or deep link as a link tapped in another app would (Android: VIEW intent with CATEGORY_BROWSABLE). App/universal links open the app only if their domain is verified. With waitFor it also waits for the next screen.

NameTypeReqDescription
devicestring–Device id or name (optional when exactly one device is booted)
returnUiboolean–Also return the UI outline of the screen the action ends on (act, wait and observe in one call)
urlstringyesURL with a scheme: https://..., myapp://path, exp+app://...
waitForobject–After the action, wait for an element matching this selector (fields: text, contains, id, role) in the same call
waitGoneboolean–Wait for waitFor to disappear instead
waitTimeoutMsnumber–Timeout for waitFor, default 10000

No output schema declared.

No examples provided.

park ~72

Park a booted device: stop it in place, so it uses no CPU and the host can reclaim its memory, keeping its apps and screen as they are. The next call on it resumes it (or use resume).

NameTypeReqDescription
devicestring–Device id or name (optional when exactly one device is booted)

No output schema declared.

No examples provided.

permission ~188

Grant, revoke or reset an app's privacy permissions without the system dialog. revoke = denied without asking again; reset = ask again on next use. Android kills the app when one is revoked or reset. A grant the app could not get on a device (not in its manifest / no Info.plist usage description) is refused.

NameTypeReqDescription
actionstringyesWhat to do
appstringyesPackage name or bundle id
devicestring–Device id or name (optional when exactly one device is booted)
permissionsarray–Names: camera, microphone, photos, photos-add, location, location-always, contacts, contacts-limited, calendar, reminders, notifications, motion, media-library, siri; or a raw Android permission (and…

No output schema declared.

No examples provided.

press_key ~158

Press a key: home, back, enter, delete, tab, escape, lock, volumeup, volumedown.

NameTypeReqDescription
devicestring–Device id or name (optional when exactly one device is booted)
keystringyesKey name
returnUiboolean–Also return the UI outline of the screen the action ends on (act, wait and observe in one call)
waitForobject–After the action, wait for an element matching this selector (fields: text, contains, id, role) in the same call
waitGoneboolean–Wait for waitFor to disappear instead
waitTimeoutMsnumber–Timeout for waitFor, default 10000

No output schema declared.

No examples provided.

profiles ~30

List screen profiles (real device sizes) usable with set_profile.

NameTypeReqDescription
platformstring–android or ios

No output schema declared.

No examples provided.

push ~211

Send a push notification to an app (iOS; Android has no faithful path). It shows only if the app may post notifications. With waitFor it also waits for the banner or screen.

NameTypeReqDescription
appstringyesBundle id
devicestring–Device id or name (optional when exactly one device is booted)
payloadobjectyesAPNs payload with an "aps" object, at most 4096 bytes, e.g. {"aps":{"alert":{"title":"Hi","body":"Hello"}}}
returnUiboolean–Also return the UI outline of the screen the action ends on (act, wait and observe in one call)
waitForobject–After the action, wait for an element matching this selector (fields: text, contains, id, role) in the same call
waitGoneboolean–Wait for waitFor to disappear instead
waitTimeoutMsnumber–Timeout for waitFor, default 10000

No output schema declared.

No examples provided.

reset ~40

Restore a booted device to its clean baseline state (fast).

NameTypeReqDescription
devicestring–Device id or name (optional when exactly one device is booted)

No output schema declared.

No examples provided.

resume ~49

Resume a parked device; returns once it is agent-ready. Does nothing on a device that is not parked.

NameTypeReqDescription
devicestring–Device id or name (optional when exactly one device is booted)

No output schema declared.

No examples provided.

screenshot ~84

Capture the screen. Returns the image plus its file path. Coordinates on a scale=1 image are tap coordinates.

NameTypeReqDescription
devicestring–Device id or name (optional when exactly one device is booted)
formatstring–png or jpeg
scalenumber–Downscale factor 0-1 for the returned image (default 0.5)

No output schema declared.

No examples provided.

set_profile ~91

Switch the screen to a real-device profile (see profiles) or a custom Android size.

NameTypeReqDescription
densitynumber–Custom density dpi (Android)
devicestring–Device id or name (optional when exactly one device is booted)
heightnumber–Custom height px (Android)
profilestring–Profile name
widthnumber–Custom width px (Android)

No output schema declared.

No examples provided.

shutdown ~32

Shut a device down.

NameTypeReqDescription
devicestring–Device id or name (optional when exactly one device is booted)

No output schema declared.

No examples provided.

swipe ~191

Swipe from (x,y) to (x2,y2) in screenshot pixels.

NameTypeReqDescription
devicestring–Device id or name (optional when exactly one device is booted)
durationMsnumber–duration, default 300
returnUiboolean–Also return the UI outline of the screen the action ends on (act, wait and observe in one call)
waitForobject–After the action, wait for an element matching this selector (fields: text, contains, id, role) in the same call
waitGoneboolean–Wait for waitFor to disappear instead
waitTimeoutMsnumber–Timeout for waitFor, default 10000
xnumberyesstart x
x2numberyesend x
ynumberyesstart y
y2numberyesend y

No output schema declared.

No examples provided.

tap ~259

Tap at x,y (screenshot pixels) or at the center of the element matching a selector. With waitFor it also waits for the next screen.

NameTypeReqDescription
containsstring–Case-insensitive substring of text or label
devicestring–Device id or name (optional when exactly one device is booted)
idstring–resource-id (Android) or accessibilityIdentifier (iOS)
indexnumber–Pick the n-th match (0-based)
returnUiboolean–Also return the UI outline of the screen the action ends on (act, wait and observe in one call)
rolestring–Normalized role: button, text, textfield, switch, image, cell...
textstring–Exact text or accessibility label
waitForobject–After the action, wait for an element matching this selector (fields: text, contains, id, role) in the same call
waitGoneboolean–Wait for waitFor to disappear instead
waitTimeoutMsnumber–Timeout for waitFor, default 10000
xnumber–X in screenshot pixels
ynumber–Y in screenshot pixels

No output schema declared.

No examples provided.

terminate ~44

Force-stop an app.

NameTypeReqDescription
appstringyesPackage name or bundle id
devicestring–Device id or name (optional when exactly one device is booted)

No output schema declared.

No examples provided.

type_text ~175

Type text into the focused field.

NameTypeReqDescription
devicestring–Device id or name (optional when exactly one device is booted)
keysboolean–Send one key event per character (slower) instead of setting the field's text (Android) or pasting it (iOS)
returnUiboolean–Also return the UI outline of the screen the action ends on (act, wait and observe in one call)
textstringyesText to type
waitForobject–After the action, wait for an element matching this selector (fields: text, contains, id, role) in the same call
waitGoneboolean–Wait for waitFor to disappear instead
waitTimeoutMsnumber–Timeout for waitFor, default 10000

No output schema declared.

No examples provided.

ui_tree ~71

Accessibility/UI hierarchy as a compact outline: [ref] role "text" id=... @(x,y wxh). Frames are screenshot pixels.

NameTypeReqDescription
devicestring–Device id or name (optional when exactly one device is booted)
jsonboolean–Return full JSON instead of the outline

No output schema declared.

No examples provided.

uninstall ~48

Uninstall a user app with its data.

NameTypeReqDescription
appstringyesPackage name or bundle id
devicestring–Device id or name (optional when exactly one device is booted)

No output schema declared.

No examples provided.

wait_for ~150

Wait until an element matching the selector appears (or disappears with gone=true).

NameTypeReqDescription
containsstring–Case-insensitive substring of text or label
devicestring–Device id or name (optional when exactly one device is booted)
goneboolean–Wait for disappearance
idstring–resource-id (Android) or accessibilityIdentifier (iOS)
indexnumber–Pick the n-th match (0-based)
rolestring–Normalized role: button, text, textfield, switch, image, cell...
textstring–Exact text or accessibility label
timeoutMsnumber–Timeout, default 10000

No output schema declared.

No examples provided.

Install

How do I install the agemu MCP server?

agemu runs locally as an npm package, launched with npx -y agentic-emulator mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · agentic-emulator

# add to Claude Code
claude mcp add piotr-graczyk-dev-agemu -- npx -y agentic-emulator mcp
Common questions

What is the agemu MCP server?

agemu is an MCP server listed in the public MCP registry as io.github.piotr-graczyk-dev/agemu. Fast Android emulator and iOS Simulator control for coding agents: screenshots, UI tree, taps, logs. This page covers its npm package (agentic-emulator).

Is the agemu MCP server safe to use?

agemu scores 82 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the agemu MCP server expose?

agemu exposes 31 tools: devices, profiles, create, boot, shutdown, and 26 more. Their descriptions and schemas cost roughly 3,505 tokens of context every time the server is loaded.

Is the agemu MCP server still maintained?

agemu is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the agemu MCP server under?

agemu declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the agemu MCP server?

VerifyMCP ran 16 checks on agemu, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.