end_turn · Cursor Otel MCP: Risk & Policy

WHAT IT DOES

What end_turn does on Cursor Otel

AI agents invoke end_turn to trigger actions in Cursor Otel. 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 end_turn needs a policy

end_turn triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

end_turn Rate-limited

end_turn 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": {
    "end_turn": {
      "limits": [
        {
          "counter": "end_turn_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 Cursor Otel, so you can run agents against it safely.

FAQ

Questions about end_turn

What does the end_turn tool do? +

End the OpenTelemetry trace for an agent turn. Call after completing your response. It is categorised as a Execute tool in the Cursor Otel MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on end_turn? +

Register the Cursor Otel MCP server in PolicyLayer and add a rule for end_turn: 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 Cursor Otel. Nothing to install.

What risk level is end_turn? +

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

Can I rate-limit end_turn? +

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

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

end_turn is provided by the Cursor Otel MCP server (smith/cursor-otel). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.