eval_answer_accuracy · Multivon MCP: Risk & Policy

WHAT IT DOES

What eval_answer_accuracy does on Multivon

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

WHY IT NEEDS A POLICY

Why eval_answer_accuracy needs a policy

An AI agent can call eval_answer_accuracy faster than any human can review — one bad instruction and it creates or modifies resources in Multivon by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

eval_answer_accuracy Rate-limited

eval_answer_accuracy 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": {
    "eval_answer_accuracy": {
      "limits": [
        {
          "counter": "eval_answer_accuracy_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 Multivon, so you can run agents against it safely.

FAQ

Questions about eval_answer_accuracy

What does the eval_answer_accuracy tool do? +

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

How do I enforce a policy on eval_answer_accuracy? +

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

What risk level is eval_answer_accuracy? +

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

Can I rate-limit eval_answer_accuracy? +

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

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

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

// THE FULL RECORD

eval_answer_accuracy is one line of Multivon's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →