// SCAN REPORT

Phantom

24 tools. 18 can modify or destroy data without limits.

18 write tools that can modify data. Rate limits recommended.

Last updated: 30 Jun 2026

18 can modify or destroy data

6 read-only

24 tools total

Community server · catalogue entry verified 30/06/2026

How to control Phantom ↓

TOOL MAP

What Phantom exposes to your agents

Read (6) Write / Execute (18) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Phantom tools

Execute · Medium prepare_device This tool triggers multiple device state changes (dismissing keyboard, clearing clipboard, resetting status bar, forcing keyboard layout) on a real device or emulator. Execute · High launch_app This tool executes code/operations on real or simulated devices by launching applications. Execute · High multi_device This tool executes test automation commands across multiple devices in parallel. Execute · Medium wait_for_element This tool executes automation commands on mobile simulators/emulators/devices (external operations whose effects depend on arguments like element selectors and timeout values).

18 of Phantom's 24 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Phantom

PolicyLayer is an MCP gateway — it sits between your AI agents and Phantom, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "assert_not_visible": {
    "limits": [
      {
        "counter": "assert_not_visible_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "accessibility_audit": {
    "limits": [
      {
        "counter": "accessibility_audit_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Phantom — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON PHANTOM →

Instant setup, no code required.

FULL CATALOGUE

All 24 Phantom tools

EXECUTE 15 tools

Execute deep_link Ouvre une URL ou un deep link dans l Execute dismiss_keyboard Ferme le clavier sur le device actif (iOS et Android). No-op si pas de clavier visible. À utiliser après un ty Execute launch_app Lance une app sur le device actif. iOS : bundle ID (ex: com.monapp.ios). Android : package name (ex: com.monap Execute long_press Appui long sur un élément de l Execute multi_device Execute la meme action sur plusieurs devices et retourne les resultats combines. Utile pour tester sur iOS + A Execute prepare_device Prépare le device actif pour une session de test propre : dismiss keyboard, clear clipboard, reset status bar Execute rotate Change l Execute scroll_until_visible Scroll vers le bas (ou la direction choisie) jusqu Execute set_device Sélectionne le device à utiliser pour cette session de test. Si le device est éteint, il sera démarré automati Execute shake Simule un geste de shake sur le device. iOS : via raccourci Simulator (Ctrl+Cmd+Z). Android : swipes rapides. Execute swipe Fait un geste de swipe sur l Execute tap Tape sur un élément de l Execute type_text Écrit du texte dans un champ. Fonctionne sur iOS et Android. Peut cibler un champ par son label/texte. Avec ve Execute video_record Enregistre une vidéo de l Execute wait_for_element Attend qu

WRITE 3 tools

Write assert_not_visible Vérifie qu Write kill_app Ferme une app sur le device actif. Write test_report Gère le rapport de test automatique. Le rapport démarre AUTOMATIQUEMENT dès la première interaction (tap, type

READ 6 tools

Read accessibility_audit Verifie l Read assert_visible Vérifie qu Read get_ui_tree Retourne l Read list_devices Liste tous les devices disponibles — simulateurs iOS, émulateurs Android, et vrais devices connectés. Affiche Read screenshot Prend un screenshot du device actif (iOS ou Android) et le retourne comme image. Read visual_diff Compare deux screenshots pour detecter des regressions visuelles. action=

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Phantom

How do I prevent bulk modifications through Phantom? +

The Phantom server has 3 write tools including assert_not_visible, kill_app, test_report. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Phantom.

How many tools does the Phantom MCP server expose? +

24 tools across 4 categories: Destructive, Execute, Read, Write. 6 are read-only. 18 can modify, create, or delete data.

How do I enforce a policy on Phantom? +

Register the Phantom MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Phantom tool call.

Deterministic rules across all 24 Phantom tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON PHANTOM →

Instant setup, no code required.

24 Phantom tools catalogued and risk-classified — across an index of 43,000+ MCP servers.