batch_judge · Model Radar MCP: Risk & Policy

WHAT IT DOES

What batch_judge does on Model Radar

AI agents invoke batch_judge to trigger actions in Model Radar. 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 batch_judge needs a policy

The description is empty, so classification is uncertain. Based on the tool name 'batch_judge' and context from sibling tools ('judge', 'batch_run', 'benchmark'), this tool likely runs batch evaluation/judging of LLM model outputs, which constitutes executing external operations. No financial or destructive implications are apparent. Confidence is low due to empty description.

From the tool's definition Tool name 'batch_judge' and empty description; sibling tool 'judge' implies evaluating/scoring model outputs, 'batch' implies running this at scale

Risk signalsBulk/mass operation — affects multiple targets

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

batch_judge Rate-limited

batch_judge 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": {
    "batch_judge": {
      "limits": [
        {
          "counter": "batch_judge_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 Model Radar, so you can run agents against it safely.

FAQ

Questions about batch_judge

What does the batch_judge tool do? +

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

How do I enforce a policy on batch_judge? +

Register the Model Radar MCP server in PolicyLayer and add a rule for batch_judge: 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 Model Radar. Nothing to install.

What risk level is batch_judge? +

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

Can I rate-limit batch_judge? +

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

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

batch_judge is provided by the Model Radar MCP server (srclight/model-radar). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.