benchmark_quality · MCP MAGMA Handbook Server MCP

WHAT IT DOES

What benchmark_quality does on MCP MAGMA Handbook Server

AI agents invoke benchmark_quality to trigger actions in MCP MAGMA Handbook Server. 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_quality needs a policy

This tool executes benchmark operations ("Run quality benchmarks") rather than simply reading or writing data. While it doesn't delete data (not Destructive), doesn't handle money (not Financial), and appears reversible (not purely side-effect-free like Read), the execution of benchmarks constitutes active code execution that triggers computational processes.

From the tool's definition Tool description states it will "Run quality benchmarks" which involves executing performance evaluation operations. The word "Run" indicates active execution of code/processes rather than passive data retrieval.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

benchmark_quality Rate-limited

benchmark_quality 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_quality": {
      "limits": [
        {
          "counter": "benchmark_quality_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 MCP MAGMA Handbook Server, so you can run agents against it safely.

FAQ

Questions about benchmark_quality

What does the benchmark_quality tool do? +

Run quality benchmarks to evaluate search performance across different query types. It is categorised as a Execute tool in the MCP MAGMA Handbook Server 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_quality? +

Register the MCP MAGMA Handbook Server MCP server in PolicyLayer and add a rule for benchmark_quality: 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 MCP MAGMA Handbook Server. Nothing to install.

What risk level is benchmark_quality? +

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

Can I rate-limit benchmark_quality? +

Yes. Add a rate_limit block to the benchmark_quality 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_quality completely? +

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

benchmark_quality is provided by the MCP MAGMA Handbook Server MCP server (legenai/mcp-magma-handbook). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.