generate_tests · Code Review MCP: Risk & Policy

WHAT IT DOES

What generate_tests does on Code Review

AI agents use generate_tests 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 generate_tests needs a policy

This tool generates test suggestions—artifacts that would be written to code, making it a Write operation. However, the changes are reversible (test files can be modified or deleted), and the tool itself does not execute tests or modify production code. Severity is low because generating test code has minimal blast radius; incorrect suggestions would at most require manual review and deletion.

From the tool's definition Tool 'generate_tests' suggests test scenarios, which involves creating or generating test code. Description indicates it proposes test cases (happy path, invalid input scenarios) that would be written into test files.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

generate_tests Rate-limited

generate_tests 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": {
    "generate_tests": {
      "limits": [
        {
          "counter": "generate_tests_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 generate_tests

What does the generate_tests tool do? +

Suggests test scenarios for the given code: happy path, invalid input,. 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 generate_tests? +

Register the Code Review MCP server in PolicyLayer and add a rule for generate_tests: 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 generate_tests? +

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

Can I rate-limit generate_tests? +

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

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

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