long_press · Phantom MCP: Risk & Policy

WHAT IT DOES

What long_press does on Phantom

AI agents invoke long_press 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 long_press needs a policy

A long press is a UI interaction that triggers external operations on a simulator/emulator or real device. It falls under Execute as it performs a browser/device action whose effects depend on which element is targeted. The description is truncated ('Appui long sur un élément de l') reducing confidence slightly, but the tool name and context make the action clear.

From the tool's definition 'long_press' - performs a long press action on a UI element, which is a touch/interaction automation action on a device

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

long_press Rate-limited

long_press 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": {
    "long_press": {
      "limits": [
        {
          "counter": "long_press_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 long_press

What does the long_press tool do? +

Appui long sur un élément de l. 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 long_press? +

Register the Phantom MCP server in PolicyLayer and add a rule for long_press: 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 long_press? +

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

Can I rate-limit long_press? +

Yes. Add a rate_limit block to the long_press 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 long_press completely? +

Set action: deny in the PolicyLayer policy for long_press. 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 long_press? +

long_press 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.