batch_run · Model Radar MCP: Risk & Policy

WHAT IT DOES

What batch_run does on Model Radar

AI agents invoke batch_run 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_run needs a policy

The tool appears to execute batched operations against external LLM model endpoints based on the server's purpose. However, confidence is not higher due to the empty description—the tool name alone suggests execution but without explicit description confirming whether it merely queries benchmarks or actually invokes model operations.

From the tool's definition Tool name 'batch_run' combined with server context that pings and benchmarks LLM models across multiple providers suggests execution of batched operations. The '_run' suffix indicates the tool triggers actions.

Risk signalsBulk/mass operation — affects multiple targets

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

batch_run Rate-limited

batch_run 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_run": {
      "limits": [
        {
          "counter": "batch_run_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_run

What does the batch_run tool do? +

batch_run. 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_run? +

Register the Model Radar MCP server in PolicyLayer and add a rule for batch_run: 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_run? +

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

Can I rate-limit batch_run? +

Yes. Add a rate_limit block to the batch_run 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_run completely? +

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

batch_run 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.