trace_execution · InSite MCP: Risk & Policy

WHAT IT DOES

What trace_execution does on InSite

AI agents invoke trace_execution to trigger actions in InSite. 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 trace_execution needs a policy

This tool triggers an active runtime operation (enabling tracing) within the browser execution environment. While it doesn't directly modify page content or move money, it initiates an execution-level side effect by activating tracing subsystems that can capture sensitive browser activity, network traffic, and user interactions.

From the tool's definition 'Enable detailed execution tracing' and 'tracing for debugging browser operations' — activates a monitoring/instrumentation mode within the browser automation runtime

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

trace_execution Rate-limited

trace_execution 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": {
    "trace_execution": {
      "limits": [
        {
          "counter": "trace_execution_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 InSite, so you can run agents against it safely.

FAQ

Questions about trace_execution

What does the trace_execution tool do? +

Enable detailed execution tracing for debugging browser operations. It is categorised as a Execute tool in the InSite MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on trace_execution? +

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

What risk level is trace_execution? +

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

Can I rate-limit trace_execution? +

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

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

trace_execution is provided by the InSite MCP server (jowharshamshiri/insite). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.