benchmark · Model Radar MCP: Risk & Policy

WHAT IT DOES

What benchmark does on Model Radar

AI agents invoke benchmark 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 benchmark needs a policy

Given the server's purpose of pinging 130+ LLM models and ranking them by latency, a 'benchmark' tool most likely triggers real-time performance tests across multiple external providers, which constitutes executing external operations. However, the empty description lowers confidence significantly. It could also be a Read operation if it merely retrieves pre-computed benchmark results.

From the tool's definition Tool name is 'benchmark'; description is empty or uninformative.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

benchmark Rate-limited

benchmark 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": {
    "benchmark": {
      "limits": [
        {
          "counter": "benchmark_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 benchmark

What does the benchmark tool do? +

benchmark. 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 benchmark? +

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

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

Can I rate-limit benchmark? +

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

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

benchmark 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.