type_text · Phantom MCP: Risk & Policy

WHAT IT DOES

What type_text does on Phantom

AI agents invoke type_text to trigger actions in Phantom. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why type_text needs a policy

This tool executes UI automation actions by typing text into fields on iOS/Android simulators or real devices. It triggers external operations (UI interaction) whose effects depend on arguments, placing it in Execute. Severity is medium because misuse could input unintended data into app fields (e.g., forms, search boxes), but effects are generally reversible and limited to the device under test.

From the tool's definition 'Écrit du texte dans un champ' (writes text into a field), 'Peut cibler un champ par son label/texte', 'Avec verify=true, re-lit le champ après le type' — triggers input actions on simulator/emulator UI fields

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

type_text Rate-limited

type_text stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "type_text": {
      "limits": [
        {
          "counter": "type_text_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Phantom, so you can run agents against it safely.

FAQ

Questions about type_text

What does the type_text tool do? +

Écrit du texte dans un champ. Fonctionne sur iOS et Android. Peut cibler un champ par son label/texte. Avec verify=true (opt-in), re-lit le champ après le type pour détecter les pickers d. It is categorised as a Execute tool in the Phantom MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on type_text? +

Register the Phantom MCP server in PolicyLayer and add a rule for type_text: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Phantom. Nothing to install.

What risk level is type_text? +

type_text is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit type_text? +

Yes. Add a rate_limit block to the type_text rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block type_text completely? +

Set action: deny in the PolicyLayer policy for type_text. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides type_text? +

type_text is provided by the Phantom MCP server (nthimpulse/phantom-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.