comment_contract · Trace MCP: Risk & Policy

WHAT IT DOES

What comment_contract does on Trace MCP

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

WHY IT NEEDS A POLICY

Why comment_contract needs a policy

This tool creates or modifies data (comments in source files) in a reversible manner. The changes are additive documentation that can be removed or edited. It does not execute code, delete data, or cause irreversible effects. While it modifies files, the impact is constrained to adding metadata/comments rather than altering functional code or data structures.

From the tool's definition Tool performs 'Add cross-reference comments to validated producer/consumer pairs' and 'Documents the contract relationship in both files' — operations that modify file contents by injecting documentation comments.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

comment_contract Rate-limited

comment_contract 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": {
    "comment_contract": {
      "limits": [
        {
          "counter": "comment_contract_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 Trace MCP, so you can run agents against it safely.

FAQ

Questions about comment_contract

What does the comment_contract tool do? +

Add cross-reference comments to validated producer/consumer pairs. Documents the contract relationship in both files. It is categorised as a Write tool in the Trace MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on comment_contract? +

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

What risk level is comment_contract? +

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

Can I rate-limit comment_contract? +

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

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

comment_contract is provided by the Trace MCP server (mnehmos/mnehmos.trace.mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.