github_create_review · AI Code Review MCP Server MCP

WHAT IT DOES

What github_create_review does on AI Code Review MCP Server

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

WHY IT NEEDS A POLICY

Why github_create_review needs a policy

This tool creates new review comments on pull requests, which modifies GitHub state reversibly. While reviews can be edited or deleted later, the primary action is write-class (create). Severity is medium because misuse could spam or disrupt PR workflows with false/misleading reviews, but the blast radius is limited to a single PR and doesn't expose financial, destructive, or arbitrary code execution risks.

From the tool's definition Tool name 'github_create_review' and description 'Create a review on a pull request with optional line comments' explicitly perform creation/write operations on GitHub PR reviews.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

github_create_review Rate-limited

github_create_review 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": {
    "github_create_review": {
      "limits": [
        {
          "counter": "github_create_review_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 AI Code Review MCP Server, so you can run agents against it safely.

FAQ

Questions about github_create_review

What does the github_create_review tool do? +

Create a review on a pull request with optional line comments. It is categorised as a Write tool in the AI Code Review MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on github_create_review? +

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

What risk level is github_create_review? +

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

Can I rate-limit github_create_review? +

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

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

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