debug_evaluate · Polybugger MCP: Risk & Policy

WHAT IT DOES

What debug_evaluate does on Polybugger

AI agents invoke debug_evaluate to trigger actions in Polybugger. 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 debug_evaluate needs a policy

Evaluating an expression in a live Python debugger context is effectively arbitrary code execution. While the description says 'evaluate,' in a debug context this typically calls eval() or similar, which can execute any Python code with the permissions of the debugged process. The blast radius is high because an agent could run destructive or exfiltrating code through this interface.

From the tool's definition "Evaluate a Python expression" — evaluating arbitrary Python expressions can run any code, access the filesystem, make network calls, or cause other side effects depending on the expression provided.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

debug_evaluate Rate-limited

debug_evaluate 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": {
    "debug_evaluate": {
      "limits": [
        {
          "counter": "debug_evaluate_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 Polybugger, so you can run agents against it safely.

FAQ

Questions about debug_evaluate

What does the debug_evaluate tool do? +

Evaluate a Python expression. It is categorised as a Execute tool in the Polybugger MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on debug_evaluate? +

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

What risk level is debug_evaluate? +

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

Can I rate-limit debug_evaluate? +

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

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

debug_evaluate is provided by the Polybugger MCP server (wilfoa/polybugger-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.