request_pr_review

THE RISK

Medium Risk

Why request_pr_review needs a policy

This tool modifies a pull request by adding review requests, which is a reversible write operation (reviewers can be removed). It doesn't execute code, delete data, or involve financial transactions. Misuse could spam users with review requests but has limited blast radius.

From the tool's definition Request review from users on a pull request

Documented attack patterns abuse exactly the kind of access request_pr_review gives an agent:

POLICY

How to control request_pr_review

PolicyLayer is an MCP gateway — it sits between your AI agents and Forgejo, and nothing reaches the server without passing your rules. This is the rule we recommend for request_pr_review:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "request_pr_review": {
      "limits": [
        {
          "counter": "request_pr_review_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

request_pr_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.

Create a free account and register Forgejo — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Forgejo tools

Destructive admin_delete_user Delete a user (requires admin privileges) Destructive delete_branch Delete a branch from a repository Destructive delete_file Delete a file from a repository Destructive delete_issue_comment Delete a comment on an issue Destructive delete_label Delete a label from a repository Destructive delete_milestone Delete a milestone from a repository Destructive delete_org Delete an organization Destructive delete_repo Delete a repository by owner and name

All 103 Forgejo tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about request_pr_review

What does the request_pr_review tool do? +

Request review from users on a pull request. It is categorised as a Write tool in the Forgejo MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on request_pr_review? +

Register the Forgejo MCP server in PolicyLayer and add a rule for request_pr_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 Forgejo. Nothing to install.

What risk level is request_pr_review? +

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

Can I rate-limit request_pr_review? +

Yes. Add a rate_limit block to the request_pr_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 request_pr_review completely? +

Set action: deny in the PolicyLayer policy for request_pr_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 request_pr_review? +

request_pr_review is provided by the Forgejo MCP server (sqcows/forgejo-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Forgejo tool call.

Start from Forgejo, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →