agent_log · Cursor Otel MCP: Risk & Policy

WHAT IT DOES

What agent_log does on Cursor Otel

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

WHY IT NEEDS A POLICY

Why agent_log needs a policy

This tool writes/emits a log record to an observability backend (OpenTelemetry). It creates data but does not delete, execute code, or involve financial operations. Misuse could pollute telemetry logs but has minimal blast radius.

From the tool's definition 'Emit an OpenTelemetry log record' — creates a log entry in the telemetry system

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

agent_log Rate-limited

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

FAQ

Questions about agent_log

What does the agent_log tool do? +

Emit an OpenTelemetry log record, optionally correlated to the current turn trace. It is categorised as a Write tool in the Cursor Otel MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on agent_log? +

Register the Cursor Otel MCP server in PolicyLayer and add a rule for agent_log: 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 agent_log? +

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

Can I rate-limit agent_log? +

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

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

agent_log 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.