batch_add_comments · Code Review MCP: Risk & Policy

WHAT IT DOES

What batch_add_comments does on Code Review

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

WHY IT NEEDS A POLICY

Why batch_add_comments needs a policy

This tool creates new comments on PRs/MRs, which are reversible modifications (comments can be edited or deleted). It does not execute code, delete data, or move money. The 'batch' nature and ability to add multiple comments simultaneously increases the potential blast radius compared to single-comment operations, warranting medium severity—an agent could spam or maliciously comment on many PRs if given uncontrolled…

From the tool's definition Tool name 'batch_add_comments' and description 'Batch add multiple inline comments and optionally a general comment' indicate creation of comment data on pull requests/merge requests.

Risk signalsBulk/mass operation — affects multiple targets

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

batch_add_comments Rate-limited

batch_add_comments 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": {
    "batch_add_comments": {
      "limits": [
        {
          "counter": "batch_add_comments_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 Code Review, so you can run agents against it safely.

FAQ

Questions about batch_add_comments

What does the batch_add_comments tool do? +

Batch add multiple inline comments and optionally a general comment. It is categorised as a Write tool in the Code Review MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on batch_add_comments? +

Register the Code Review MCP server in PolicyLayer and add a rule for batch_add_comments: 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 Code Review. Nothing to install.

What risk level is batch_add_comments? +

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

Can I rate-limit batch_add_comments? +

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

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

batch_add_comments is provided by the Code Review MCP server (oldjii/code-review-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.