// SCAN REPORT

Pr Review

21 tools. 11 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 2 Jul 2026

11 can modify or destroy data

10 read-only

21 tools total

Community server · catalogue entry verified 02/07/2026

How to control Pr Review ↓

TOOL MAP

What Pr Review exposes to your agents

Read (10) Write / Execute (10) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Pr Review tools

Destructive · High pr_reset_coordination Resetting/clearing a coordination run removes or overwrites existing coordination state that cannot be recovered. Execute · High pr_invoke This tool executes an operation that invokes AI agents with side effects on a pull request. Write · Medium pr_cancel This tool cancels an active review process, which is a reversible state change (the review could presumably be re-invoked). Write · Medium pr_labels This tool performs both read and write operations on PR labels.

11 of Pr Review's 21 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Pr Review

PolicyLayer is an MCP gateway — it sits between your AI agents and Pr Review, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "pr_reset_coordination": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "pr_cancel": {
    "limits": [
      {
        "counter": "pr_cancel_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "pr_await_reviews": {
    "limits": [
      {
        "counter": "pr_await_reviews_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Pr Review — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON PR REVIEW →

Instant setup, no code required.

FULL CATALOGUE

All 21 Pr Review tools

DESTRUCTIVE 1 tools

Destructive pr_reset_coordination Reset/clear the current coordination run. Uses interactive elicitation for confirmation when supported, falls

EXECUTE 1 tools

Execute pr_invoke Invoke AI code review agents on a PR. When agent=

WRITE 9 tools

Write pr_cancel Cancel an active review invocation, preventing further polling. Provide either invocationId (from pr_invoke or Write pr_claim_work Claim file partition for parallel PR review processing Write pr_create Create a new pull request from an existing branch Write pr_labels Get, add, remove, or set labels on a PR Write pr_merge Merge a pull request. Uses interactive elicitation for confirmation when supported, falls back to confirm=true Write pr_progress_update Report orchestrator phase transition (called by background subagent) Write pr_report_progress Report completion status for a claimed file partition Write pr_resolve Mark a review thread as resolved Write pr_reviewers Request or remove reviewers on a PR

READ 10 tools

Read pr_await_reviews Non-blocking: checks agent review completion status once and returns immediately. Use after pr_invoke — pass t Read pr_changes Get comments since cursor for incremental updates Read pr_get Get detailed comment information including full body and AI prompt Read pr_get_work_status Get current coordination run status and progress Read pr_list List PR review comments with optional filtering by resolved/file/severity Read pr_list_prs List all pull requests in a repository with stats (review threads, comments, changes) Read pr_poll_updates Poll for new review updates since a timestamp (comments, commits, status, agents). Use include=[ Read pr_progress_check Check orchestrator progress and run status in a single call Read pr_sessions List active and recent review invocations across sessions. Shows which agents were invoked, their completion s Read pr_summary Get PR review statistics: total, resolved, unresolved counts by severity and file

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Pr Review

Can an AI agent delete data through the Pr Review MCP server? +

Yes. The Pr Review server exposes 1 destructive tools including pr_reset_coordination. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Pr Review? +

The Pr Review server has 9 write tools including pr_cancel, pr_claim_work, pr_create. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Pr Review.

How many tools does the Pr Review MCP server expose? +

21 tools across 4 categories: Destructive, Execute, Read, Write. 10 are read-only. 11 can modify, create, or delete data.

How do I enforce a policy on Pr Review? +

Register the Pr Review MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Pr Review tool call.

Deterministic rules across all 21 Pr Review tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON PR REVIEW →

Instant setup, no code required.

21 Pr Review tools catalogued and risk-classified — across an index of 43,000+ MCP servers.