debugpy_evaluate · Debugpy MCP: Risk & Policy

WHAT IT DOES

What debugpy_evaluate does on Debugpy

AI agents invoke debugpy_evaluate to trigger actions in Debugpy. 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 debugpy_evaluate needs a policy

Evaluating arbitrary expressions or REPL snippets in a running Python process is code execution. An AI agent could run any Python code in the context of the debugged process, with effects depending entirely on what is evaluated — including file I/O, network calls, or system commands. This is a classic Execute-category tool with high blast radius.

From the tool's definition Evaluate a watch expression or REPL snippet

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

debugpy_evaluate Rate-limited

debugpy_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": {
    "debugpy_evaluate": {
      "limits": [
        {
          "counter": "debugpy_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 Debugpy, so you can run agents against it safely.

FAQ

Questions about debugpy_evaluate

What does the debugpy_evaluate tool do? +

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

How do I enforce a policy on debugpy_evaluate? +

Register the Debugpy MCP server in PolicyLayer and add a rule for debugpy_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 Debugpy. Nothing to install.

What risk level is debugpy_evaluate? +

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

Can I rate-limit debugpy_evaluate? +

Yes. Add a rate_limit block to the debugpy_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 debugpy_evaluate completely? +

Set action: deny in the PolicyLayer policy for debugpy_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 debugpy_evaluate? +

debugpy_evaluate is provided by the Debugpy MCP server (will-garrett/debugpy-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.