send_trace · Otel MCP: Risk & Policy

WHAT IT DOES

What send_trace does on Otel

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

WHY IT NEEDS A POLICY

Why send_trace needs a policy

Based on the server context (emitting OpenTelemetry traces, metrics, and logs to OTLP endpoints) and the tool name 'send_trace', this tool likely sends/writes trace data to a configured endpoint. This is a Write operation as it creates/posts telemetry data to an external system. Confidence is lowered due to the empty description.

From the tool's definition Tool name is 'send_trace'; description is empty or uninformative.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_trace Rate-limited

send_trace 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": {
    "send_trace": {
      "limits": [
        {
          "counter": "send_trace_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 Otel, so you can run agents against it safely.

FAQ

Questions about send_trace

What does the send_trace tool do? +

send_trace. It is categorised as a Write tool in the 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 send_trace? +

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

What risk level is send_trace? +

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

Can I rate-limit send_trace? +

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

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

send_trace is provided by the Otel MCP server (probsjustin/otel_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.