idb_input · Xclaude Plugin MCP: Risk & Policy

WHAT IT DOES

What idb_input does on Xclaude Plugin

AI agents invoke idb_input to trigger actions in Xclaude Plugin. 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 idb_input needs a policy

This tool executes keyboard/text input operations in an iOS simulator, which constitutes triggering external operations whose effects depend on the arguments (what text is typed or keys pressed). It could be misused to interact with apps in unintended ways, e.g., submitting forms, triggering UI actions, or entering credentials.

From the tool's definition 'Type text or press keys in simulator' — triggers input actions in a running simulator environment

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

idb_input Rate-limited

idb_input 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": {
    "idb_input": {
      "limits": [
        {
          "counter": "idb_input_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 Xclaude Plugin, so you can run agents against it safely.

FAQ

Questions about idb_input

What does the idb_input tool do? +

Type text or press keys in simulator. It is categorised as a Execute tool in the Xclaude Plugin MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on idb_input? +

Register the Xclaude Plugin MCP server in PolicyLayer and add a rule for idb_input: 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 Xclaude Plugin. Nothing to install.

What risk level is idb_input? +

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

Can I rate-limit idb_input? +

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

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

idb_input is provided by the Xclaude Plugin MCP server (conorluddy/xclaude-plugin). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

idb_input is one line of Xclaude Plugin's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →