screenrecord_start · AVD MCP Server MCP: Risk & Policy

WHAT IT DOES

What screenrecord_start does on AVD MCP Server

AI agents invoke screenrecord_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 screenrecord_start needs a policy

screenrecord_start executes a screen recording command on an Android device, which is an operation that runs on the emulator and produces side effects (resource consumption, file generation). While not destructive or financial, it is fundamentally an Execute action that triggers an external system operation.

From the tool's definition Tool initiates screen recording on device ("Inicia gravação de tela no device") and returns a session identifier. This triggers an external operation on the Android Virtual Device whose effects depend on device state and recording parameters.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

screenrecord_start Rate-limited

screenrecord_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": {
    "screenrecord_start": {
      "limits": [
        {
          "counter": "screenrecord_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 screenrecord_start

What does the screenrecord_start tool do? +

Inicia gravação de tela no device e retorna sessionId. 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 screenrecord_start? +

Register the AVD MCP Server MCP server in PolicyLayer and add a rule for screenrecord_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 screenrecord_start? +

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

Can I rate-limit screenrecord_start? +

Yes. Add a rate_limit block to the screenrecord_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 screenrecord_start completely? +

Set action: deny in the PolicyLayer policy for screenrecord_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 screenrecord_start? +

screenrecord_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.