replay_manifest · Academic Figures MCP: Risk & Policy

WHAT IT DOES

What replay_manifest does on Academic Figures

AI agents invoke replay_manifest to trigger actions in Academic Figures. 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 replay_manifest needs a policy

This tool re-executes a previously saved manifest, triggering the same multi-step figure generation pipeline (plan, generate, evaluate, etc.) again. It runs an external operation whose effects depend on the saved manifest's arguments, making it Execute category. Misuse could result in unintended regeneration of figures or resource consumption, warranting medium severity.

From the tool's definition Replay a previously saved manifest using the same prompt

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

replay_manifest Rate-limited

replay_manifest 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": {
    "replay_manifest": {
      "limits": [
        {
          "counter": "replay_manifest_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 Academic Figures, so you can run agents against it safely.

FAQ

Questions about replay_manifest

What does the replay_manifest tool do? +

Replay a previously saved manifest using the same prompt. It is categorised as a Execute tool in the Academic Figures MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on replay_manifest? +

Register the Academic Figures MCP server in PolicyLayer and add a rule for replay_manifest: 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 Academic Figures. Nothing to install.

What risk level is replay_manifest? +

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

Can I rate-limit replay_manifest? +

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

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

replay_manifest is provided by the Academic Figures MCP server (u9401066/academic-figures-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.