eval_g_eval · Multivon MCP: Risk & Policy

WHAT IT DOES

What eval_g_eval does on Multivon

AI agents use eval_g_eval 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_g_eval needs a policy

An AI agent can call eval_g_eval 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_g_eval Rate-limited

eval_g_eval 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_g_eval": {
      "limits": [
        {
          "counter": "eval_g_eval_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_g_eval

What does the eval_g_eval tool do? +

eval_g_eval. 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_g_eval? +

Register the Multivon MCP server in PolicyLayer and add a rule for eval_g_eval: 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_g_eval? +

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

Can I rate-limit eval_g_eval? +

Yes. Add a rate_limit block to the eval_g_eval 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_g_eval completely? +

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

eval_g_eval 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.