start_emulator · Espresso MCP: Risk & Policy

WHAT IT DOES

What start_emulator does on Espresso

AI agents invoke start_emulator to trigger actions in Espresso. 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 start_emulator needs a policy

Starting an Android emulator is an Execute action—it triggers an external operation whose effects depend on arguments (which emulator to start) and results in launching a complex system component. While not immediately destructive, it consumes system resources and initiates a state change in the underlying system.

From the tool's definition Tool name 'start_emulator' and description 'Start an Android Emulator by name' indicate execution of an external system operation that spawns a virtual machine process.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_emulator Rate-limited

start_emulator 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": {
    "start_emulator": {
      "limits": [
        {
          "counter": "start_emulator_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 Espresso, so you can run agents against it safely.

FAQ

Questions about start_emulator

What does the start_emulator tool do? +

Start an Android Emulator by name. It is categorised as a Execute tool in the Espresso MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start_emulator? +

Register the Espresso MCP server in PolicyLayer and add a rule for start_emulator: 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 Espresso. Nothing to install.

What risk level is start_emulator? +

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

Can I rate-limit start_emulator? +

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

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

start_emulator is provided by the Espresso MCP server (vs4vijay/espresso-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.