adb_answer_call · Openclaw Adb MCP: Risk & Policy

WHAT IT DOES

What adb_answer_call does on Openclaw Adb

AI agents invoke adb_answer_call to trigger actions in Openclaw Adb. 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 adb_answer_call needs a policy

This tool triggers a phone action (answering a call) on an Android device via ADB. It executes an external operation with real-world side effects — connecting an active phone call — which cannot be trivially undone and could expose the user to privacy risks or unwanted conversations if misused by an AI agent.

From the tool's definition Answer an incoming call

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

adb_answer_call Rate-limited

adb_answer_call 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": {
    "adb_answer_call": {
      "limits": [
        {
          "counter": "adb_answer_call_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 Openclaw Adb, so you can run agents against it safely.

FAQ

Questions about adb_answer_call

What does the adb_answer_call tool do? +

Answer an incoming call. It is categorised as a Execute tool in the Openclaw Adb MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on adb_answer_call? +

Register the Openclaw Adb MCP server in PolicyLayer and add a rule for adb_answer_call: 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 Openclaw Adb. Nothing to install.

What risk level is adb_answer_call? +

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

Can I rate-limit adb_answer_call? +

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

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

adb_answer_call is provided by the Openclaw Adb MCP server (wilsonbeam/openclaw-adb-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.