update_reviews · Downscoping MCP: Risk & Policy

WHAT IT DOES

What update_reviews does on Downscoping

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

WHY IT NEEDS A POLICY

Why update_reviews needs a policy

This tool creates or modifies review records on pull requests, which is a reversible write operation. While reviews can influence code merging decisions, the action itself is not destructive (reviews can be updated or dismissed) and does not directly move money or execute arbitrary code.

From the tool's definition Tool name 'update_reviews' and description 'Submit a review for a pull request' indicate creation/modification of review data on a pull request.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_reviews Rate-limited

update_reviews 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": {
    "update_reviews": {
      "limits": [
        {
          "counter": "update_reviews_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 Downscoping, so you can run agents against it safely.

FAQ

Questions about update_reviews

What does the update_reviews tool do? +

Submit a review for a pull request. It is categorised as a Write tool in the Downscoping MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on update_reviews? +

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

What risk level is update_reviews? +

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

Can I rate-limit update_reviews? +

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

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

update_reviews is provided by the Downscoping MCP server (kbroughton/downscoping-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.