cancel_trace · Openl MCP: Risk & Policy

WHAT IT DOES

What cancel_trace does on Openl

AI agents invoke cancel_trace to trigger actions in Openl. 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 cancel_trace needs a policy

This tool cancels an ongoing execution/trace operation, which is an action that triggers an external operation (stopping/interrupting a running process). It falls under Execute as it affects a running computation. The blast radius is medium since cancelling a trace could disrupt debugging or analysis workflows but is generally reversible by re-running the trace.

From the tool's definition Cancel ongoing trace execution for a project

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cancel_trace Rate-limited

cancel_trace 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": {
    "cancel_trace": {
      "limits": [
        {
          "counter": "cancel_trace_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 Openl, so you can run agents against it safely.

FAQ

Questions about cancel_trace

What does the cancel_trace tool do? +

Cancel ongoing trace execution for a project. It is categorised as a Execute tool in the Openl MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on cancel_trace? +

Register the Openl MCP server in PolicyLayer and add a rule for cancel_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 Openl. Nothing to install.

What risk level is cancel_trace? +

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

Can I rate-limit cancel_trace? +

Yes. Add a rate_limit block to the cancel_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 cancel_trace completely? +

Set action: deny in the PolicyLayer policy for cancel_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 cancel_trace? +

cancel_trace is provided by the Openl MCP server (openl-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.