comment_on_pr · Mcp Pagure MCP: Risk & Policy

WHAT IT DOES

What comment_on_pr does on Mcp Pagure

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

WHY IT NEEDS A POLICY

Why comment_on_pr needs a policy

This tool creates or modifies data (adds a comment) in a reversible manner. Comments can typically be edited or deleted, so it is not destructive. The blast radius is medium because malicious comments could be used for social engineering, spam, or harassment of developers, but the effect is limited to metadata/discussion content rather than code or system access. It falls under Write category per the rules.

From the tool's definition Tool description states 'Add a comment to a pull request' — this creates new comment data on a pull request object.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

comment_on_pr Rate-limited

comment_on_pr 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": {
    "comment_on_pr": {
      "limits": [
        {
          "counter": "comment_on_pr_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 Mcp Pagure, so you can run agents against it safely.

FAQ

Questions about comment_on_pr

What does the comment_on_pr tool do? +

Add a comment to a pull request. It is categorised as a Write tool in the Mcp Pagure MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on comment_on_pr? +

Register the Mcp Pagure MCP server in PolicyLayer and add a rule for comment_on_pr: 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 Mcp Pagure. Nothing to install.

What risk level is comment_on_pr? +

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

Can I rate-limit comment_on_pr? +

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

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

comment_on_pr is provided by the Mcp Pagure MCP server (lemenkov/mcp-pagure). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.