kill_emulator · Espresso MCP: Risk & Policy

WHAT IT DOES

What kill_emulator does on Espresso

AI agents use kill_emulator to create or update resources in Espresso — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Espresso environment.

WHY IT NEEDS A POLICY

Why kill_emulator needs a policy

An AI agent can call kill_emulator faster than any human can review — one bad instruction and it creates or modifies resources in Espresso by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

kill_emulator Rate-limited

kill_emulator stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "kill_emulator": {
      "limits": [
        {
          "counter": "kill_emulator_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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 kill_emulator

What does the kill_emulator tool do? +

Kill a specific Android Emulator. It is categorised as a Write tool in the Espresso MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on kill_emulator? +

Register the Espresso MCP server in PolicyLayer and add a rule for kill_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 kill_emulator? +

kill_emulator is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit kill_emulator? +

Yes. Add a rate_limit block to the kill_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 kill_emulator completely? +

Set action: deny in the PolicyLayer policy for kill_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 kill_emulator? +

kill_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.