format_code · Neurodev MCP: Risk & Policy

WHAT IT DOES

What format_code does on Neurodev

AI agents use format_code to create or update resources in Neurodev — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Neurodev environment.

WHY IT NEEDS A POLICY

Why format_code needs a policy

Formatting code is a Write operation because it modifies files reversibly (the original logic is preserved, only style changes). It does not execute code (Execute), delete data (Destructive), or trigger external operations. Severity is low because formatting changes are non-breaking, easily reviewable, and fully reversible via version control or re-running the formatter with different settings.

From the tool's definition Tool description states 'Auto-format Python code' and 'Returns formatted, PEP8-compliant code' — these are reversible modifications that reformat existing code without deleting or executing it.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

format_code Rate-limited

format_code stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "format_code": {
      "limits": [
        {
          "counter": "format_code_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Neurodev, so you can run agents against it safely.

FAQ

Questions about format_code

What does the format_code tool do? +

Auto-format Python code using black and autopep8. Returns formatted, PEP8-compliant code with consistent style. It is categorised as a Write tool in the Neurodev MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on format_code? +

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

What risk level is format_code? +

format_code is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit format_code? +

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

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

format_code is provided by the Neurodev MCP server (ravikant1918/neurodev-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.