start-cpu-profiling · Debugger MCP Server MCP: Risk & Policy

WHAT IT DOES

What start-cpu-profiling does on Debugger MCP Server

AI agents invoke start-cpu-profiling to trigger actions in Debugger MCP Server. 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 start-cpu-profiling needs a policy

This tool triggers code execution and monitoring operations on a running application. While it doesn't modify data or delete anything (ruling out Write/Destructive), it actively executes profiling operations that depend on runtime state.

From the tool's definition The tool starts CPU profiling and generates flame graphs, which are active operations that trigger external processes and collect runtime data from a running application. It executes profiling logic that instruments and monitors the application's execution.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start-cpu-profiling Rate-limited

start-cpu-profiling 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": {
    "start-cpu-profiling": {
      "limits": [
        {
          "counter": "start-cpu-profiling_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 Debugger MCP Server, so you can run agents against it safely.

FAQ

Questions about start-cpu-profiling

What does the start-cpu-profiling tool do? +

Start CPU profiling to analyze performance bottlenecks and generate flame graphs. It is categorised as a Execute tool in the Debugger MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start-cpu-profiling? +

Register the Debugger MCP Server MCP server in PolicyLayer and add a rule for start-cpu-profiling: 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 Debugger MCP Server. Nothing to install.

What risk level is start-cpu-profiling? +

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

Can I rate-limit start-cpu-profiling? +

Yes. Add a rate_limit block to the start-cpu-profiling 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 start-cpu-profiling completely? +

Set action: deny in the PolicyLayer policy for start-cpu-profiling. 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 start-cpu-profiling? +

start-cpu-profiling is provided by the Debugger MCP Server MCP server (phoenixrr2113/debugger-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.