avd_start · AVD MCP Server MCP: Risk & Policy

WHAT IT DOES

What avd_start does on AVD MCP Server

AI agents invoke avd_start to trigger actions in AVD MCP Server. 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 avd_start needs a policy

This tool triggers external operations (Android emulator startup) whose effects depend on arguments (boot options like wipeData can alter state). It is not a simple read operation (avd_list, avd_status) but an action that initiates a system process. While it does not delete data irreversibly by itself, the wipeData option combined with emulator control makes it an Execute-category tool.

From the tool's definition Tool description states 'Sobe um AVD com opções de boot' (Starts an AVD with boot options), enabling launch of Android Virtual Device emulators with various configurations (coldBoot, wipeData, noWindow, readOnly, gpuMode).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

avd_start Rate-limited

avd_start 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": {
    "avd_start": {
      "limits": [
        {
          "counter": "avd_start_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 AVD MCP Server, so you can run agents against it safely.

FAQ

Questions about avd_start

What does the avd_start tool do? +

Sobe um AVD com opções de boot (coldBoot, wipeData, noWindow, readOnly, gpuMode). It is categorised as a Execute tool in the AVD MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on avd_start? +

Register the AVD MCP Server MCP server in PolicyLayer and add a rule for avd_start: 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 AVD MCP Server. Nothing to install.

What risk level is avd_start? +

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

Can I rate-limit avd_start? +

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

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

avd_start is provided by the AVD MCP Server MCP server (jramalho/avd-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.