avd_run_and_screenshot · AVD MCP Server MCP: Risk & Policy

WHAT IT DOES

What avd_run_and_screenshot does on AVD MCP Server

AI agents invoke avd_run_and_screenshot 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_run_and_screenshot needs a policy

This tool runs code/commands (pnpm, gradle, etc.) on an AVD, which qualifies as Execute category. Severity is high because arbitrary command execution on an emulator could install malware, exfiltrate data, or compromise the development environment. It's not Destructive because the effects are dependent on which commands are passed as arguments and can potentially be undone.

From the tool's definition Tool description indicates it 'roda comando' (runs command) with support for pnpm/gradle/etc, and 'tira screenshot' (takes screenshot). The sibling tools include adb_shell and app_launch which are clearly execution-oriented.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

avd_run_and_screenshot Rate-limited

avd_run_and_screenshot 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_run_and_screenshot": {
      "limits": [
        {
          "counter": "avd_run_and_screenshot_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_run_and_screenshot

What does the avd_run_and_screenshot tool do? +

Sobe AVD se necessário, roda comando (pnpm/gradle/etc) e tira screenshot. 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_run_and_screenshot? +

Register the AVD MCP Server MCP server in PolicyLayer and add a rule for avd_run_and_screenshot: 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_run_and_screenshot? +

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

Can I rate-limit avd_run_and_screenshot? +

Yes. Add a rate_limit block to the avd_run_and_screenshot 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_run_and_screenshot completely? +

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

avd_run_and_screenshot 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.