vote_annotation · Peptoma MCP: Risk & Policy

WHAT IT DOES

What vote_annotation does on Peptoma

AI agents use vote_annotation to create or update resources in Peptoma — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Peptoma environment.

WHY IT NEEDS A POLICY

Why vote_annotation needs a policy

This tool modifies voting data (write operation) rather than purely reading or destroying. While it influences token rewards, the tool itself does not directly transfer funds—it modifies voting state that feeds into a reward algorithm. This is Write rather than Financial because the agent cannot directly commit financial transactions; it can only vote, which indirectly affects reward eligibility.

From the tool's definition Tool performs 'upvote or downvote' actions that modify state—specifically annotation voting records and influence reward distribution ($PEPTM tokens).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

vote_annotation Rate-limited

vote_annotation stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "vote_annotation": {
      "limits": [
        {
          "counter": "vote_annotation_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about vote_annotation

What does the vote_annotation tool do? +

Upvote or downvote a peer-review annotation on PEPTOMA. Voting helps surface high-quality scientific contributions and determines which annotations earn $PEPTM rewards. It is categorised as a Write tool in the Peptoma MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on vote_annotation? +

Register the Peptoma MCP server in PolicyLayer and add a rule for vote_annotation: 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 Peptoma. Nothing to install.

What risk level is vote_annotation? +

vote_annotation is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit vote_annotation? +

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

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

vote_annotation is provided by the Peptoma MCP server (peptoma/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.