ai_review_paper · Science Ai MCP: Risk & Policy

WHAT IT DOES

What ai_review_paper does on Science Ai

AI agents invoke ai_review_paper to trigger actions in Science Ai. 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 ai_review_paper needs a policy

This tool executes automated review agents whose behavior depends on the input paper and reviewer specialization selected. While non-destructive and non-financial in direct terms, it is Execute rather than Read because it 'runs' agent logic that performs complex operations (analysis, review generation) rather than merely retrieving or querying static data.

From the tool's definition Tool description states 'Run one of the specialist reviewer agents' — the verb 'run' indicates execution of agent logic that processes academic papers.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ai_review_paper Rate-limited

ai_review_paper 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": {
    "ai_review_paper": {
      "limits": [
        {
          "counter": "ai_review_paper_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 Science Ai, so you can run agents against it safely.

FAQ

Questions about ai_review_paper

What does the ai_review_paper tool do? +

Run one of the specialist reviewer agents (methodology, language, figures,. It is categorised as a Execute tool in the Science Ai MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on ai_review_paper? +

Register the Science Ai MCP server in PolicyLayer and add a rule for ai_review_paper: 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 Science Ai. Nothing to install.

What risk level is ai_review_paper? +

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

Can I rate-limit ai_review_paper? +

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

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

ai_review_paper is provided by the Science Ai MCP server (selfpy/science-ai-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.