debugpy_attach · Debugpy MCP: Risk & Policy

WHAT IT DOES

What debugpy_attach does on Debugpy

AI agents invoke debugpy_attach 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_attach needs a policy

Attaching a debugger to a running process is an Execute-category action — it injects into a live process and enables code inspection, breakpoint setting, and arbitrary evaluation. The description is empty, so confidence is reduced, but the server context strongly implies this tool initiates a debugpy attach operation against a target process, which can have significant side effects on that process's execution.

From the tool's definition Tool name 'debugpy_attach' on a server that 'enables agents to attach debugpy to running Python processes inside Docker containers' via 'process injection'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

debugpy_attach Rate-limited

debugpy_attach 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_attach": {
      "limits": [
        {
          "counter": "debugpy_attach_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_attach

What does the debugpy_attach tool do? +

debugpy_attach. 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_attach? +

Register the Debugpy MCP server in PolicyLayer and add a rule for debugpy_attach: 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_attach? +

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

Can I rate-limit debugpy_attach? +

Yes. Add a rate_limit block to the debugpy_attach 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_attach completely? +

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

debugpy_attach 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.