deep_link · Phantom MCP: Risk & Policy

WHAT IT DOES

What deep_link does on Phantom

AI agents invoke deep_link 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 deep_link needs a policy

This tool opens URLs or deep links in an app/simulator, which triggers external navigation or application actions. This is an Execute-level operation as it causes the device/emulator to perform an action (navigate to URL or open a deep link), with medium severity since it can navigate to arbitrary URLs or trigger app-specific actions but is limited to the simulator/device context.

From the tool's definition Tool name 'deep_link' and partial description 'Ouvre une URL ou un deep link dans l' (Opens a URL or a deep link in)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

deep_link Rate-limited

deep_link 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": {
    "deep_link": {
      "limits": [
        {
          "counter": "deep_link_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 deep_link

What does the deep_link tool do? +

Ouvre une URL ou un deep link dans 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 deep_link? +

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

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

Can I rate-limit deep_link? +

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

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

deep_link 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.