eval_tool_call_accuracy · Multivon MCP: Risk & Policy

WHAT IT DOES

What eval_tool_call_accuracy does on Multivon

AI agents invoke eval_tool_call_accuracy to trigger actions in Multivon. 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 eval_tool_call_accuracy needs a policy

The tool name suggests it evaluates tool call accuracy, likely running some form of execution or assessment against tool calls. Given the server context ('direct access to evaluation tools') and sibling tools that perform evaluations, this likely executes an evaluation process. However, with an empty description, confidence is lowered.

From the tool's definition Tool name: eval_tool_call_accuracy; description is empty/uninformative.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

eval_tool_call_accuracy Rate-limited

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

FAQ

Questions about eval_tool_call_accuracy

What does the eval_tool_call_accuracy tool do? +

eval_tool_call_accuracy. It is categorised as a Execute tool in the Multivon MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on eval_tool_call_accuracy? +

Register the Multivon MCP server in PolicyLayer and add a rule for eval_tool_call_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_tool_call_accuracy? +

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

Can I rate-limit eval_tool_call_accuracy? +

Yes. Add a rate_limit block to the eval_tool_call_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_tool_call_accuracy completely? +

Set action: deny in the PolicyLayer policy for eval_tool_call_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_tool_call_accuracy? +

eval_tool_call_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.