approve_intelligence_qa_pair · Plurity MCP: Risk & Policy

WHAT IT DOES

What approve_intelligence_qa_pair does on Plurity

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

WHY IT NEEDS A POLICY

Why approve_intelligence_qa_pair needs a policy

The tool appears to update or change the status of an intelligence QA pair from unapproved to approved—a write operation that modifies data reversibly. Without a description, confidence is reduced, but contextual siblings (create_toll_qa_pair, delete_toll_qa_pair, list_intelligence_qa_pairs) suggest this is part of a QA management system where approval is a metadata update rather than a destructive action.

From the tool's definition Tool name 'approve_intelligence_qa_pair' suggests modifying or approving a QA pair record, which is a reversible write operation. The empty description limits certainty, but 'approve' typically modifies state without deletion.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

approve_intelligence_qa_pair Rate-limited

approve_intelligence_qa_pair 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": {
    "approve_intelligence_qa_pair": {
      "limits": [
        {
          "counter": "approve_intelligence_qa_pair_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 Plurity, so you can run agents against it safely.

FAQ

Questions about approve_intelligence_qa_pair

What does the approve_intelligence_qa_pair tool do? +

approve_intelligence_qa_pair. It is categorised as a Write tool in the Plurity MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on approve_intelligence_qa_pair? +

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

What risk level is approve_intelligence_qa_pair? +

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

Can I rate-limit approve_intelligence_qa_pair? +

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

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

approve_intelligence_qa_pair is provided by the Plurity MCP server (plurity-ai/plurity-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.