pr_invoke · Pr Review MCP: Risk & Policy

WHAT IT DOES

What pr_invoke does on Pr Review

AI agents invoke pr_invoke to trigger actions in Pr Review. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why pr_invoke needs a policy

This tool executes an operation that invokes AI agents with side effects on a pull request. Invocation of agents constitutes triggering external operations, making it Execute rather than Write. The incomplete description ('When agent=') suggests parameterized agent selection, which could amplify risk.

From the tool's definition Tool description states 'Invoke AI code review agents on a PR', indicating it triggers external operations (agent invocation) whose effects depend on arguments (which agent, PR details).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

pr_invoke Rate-limited

pr_invoke stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "pr_invoke": {
      "limits": [
        {
          "counter": "pr_invoke_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Pr Review, so you can run agents against it safely.

FAQ

Questions about pr_invoke

What does the pr_invoke tool do? +

Invoke AI code review agents on a PR. When agent=. It is categorised as a Execute tool in the Pr Review MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on pr_invoke? +

Register the Pr Review MCP server in PolicyLayer and add a rule for pr_invoke: 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 Pr Review. Nothing to install.

What risk level is pr_invoke? +

pr_invoke is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit pr_invoke? +

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

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

pr_invoke is provided by the Pr Review MCP server (thebtf/pr-review-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.