// SCAN REPORT

OpenReview MCP Server

13 tools. 6 can modify or destroy data without limits.

6 write tools that can modify data. Rate limits recommended.

Last updated: 3 Jul 2026

6 can modify or destroy data

7 read-only

13 tools total

Community server · catalogue entry verified 03/07/2026

How to control OpenReview MCP Server ↓

TOOL MAP

What OpenReview MCP Server exposes to your agents

Read (7) Write / Execute (6) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous OpenReview MCP Server tools

Write · High edit_review Edit_review modifies existing review data reversibly within the OpenReview system. Write · Medium post_comment Posting a comment creates new data in the OpenReview system. Write · High submit_meta_review Meta-reviews are write actions that create new scholarly content and recommendations in a conference system. Write · High submit_review This tool creates or modifies review data in the OpenReview system, which is a reversible write operation.

6 of OpenReview MCP Server's 13 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control OpenReview MCP Server

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

Rate limit write operations

{
  "confirm_submission": {
    "limits": [
      {
        "counter": "confirm_submission_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_discussion": {
    "limits": [
      {
        "counter": "get_discussion_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 OpenReview MCP Server — 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 OPENREVIEW →

Instant setup, no code required.

FULL CATALOGUE

All 13 OpenReview MCP Server tools

WRITE 6 tools

Write confirm_submission Confirm and submit a pending review, meta-review, or comment to OpenReview. Write edit_review edit_review Write message_reviewer message_reviewer Write post_comment post_comment Write submit_meta_review submit_meta_review Write submit_review submit_review

READ 7 tools

Read get_discussion get_discussion Read get_pdf get_pdf Read get_review_status Check review completion status for all your assigned papers. Read get_reviews Get all official reviews for a submission. Read get_submission get_submission Read list_assignments List papers assigned to you for a given venue. Read list_venues List all OpenReview venues where you have an active role (Reviewer, Area Chair, or Senior Area Chair).

FAQ

Questions about OpenReview MCP Server

How do I prevent bulk modifications through OpenReview MCP Server? +

The OpenReview MCP Server server has 6 write tools including confirm_submission, edit_review, message_reviewer. 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 OpenReview MCP Server.

How many tools does the OpenReview MCP Server MCP server expose? +

13 tools across 2 categories: Read, Write. 7 are read-only. 6 can modify, create, or delete data.

How do I enforce a policy on OpenReview MCP Server? +

Register the OpenReview MCP Server 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 OpenReview MCP Server tool call.

Deterministic rules across all 13 OpenReview MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON OPENREVIEW →

Instant setup, no code required.

13 OpenReview MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.