run_eval · Gq Insight MCP: Risk & Policy

WHAT IT DOES

What run_eval does on Gq Insight

AI agents invoke run_eval to trigger actions in Gq Insight. 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 run_eval needs a policy

This tool executes an evaluation routine that processes data and produces output, fitting the Execute category (triggers an operation whose effects depend on arguments/context). It is not Read because it performs active scoring/comparison rather than passive retrieval. It is not Destructive or Financial, as there is no irreversible data loss or financial commitment.

From the tool's definition The tool performs a programmatic evaluation ('Score the retrieval + answer tools against the labeled eval set'), which requires executing an automated process against test data and generating results—a computational operation with external effects.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_eval Rate-limited

run_eval 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": {
    "run_eval": {
      "limits": [
        {
          "counter": "run_eval_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 Gq Insight, so you can run agents against it safely.

FAQ

Questions about run_eval

What does the run_eval tool do? +

Score the retrieval + answer tools against the labeled eval set. It is categorised as a Execute tool in the Gq Insight MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_eval? +

Register the Gq Insight MCP server in PolicyLayer and add a rule for run_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 Gq Insight. Nothing to install.

What risk level is run_eval? +

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

Can I rate-limit run_eval? +

Yes. Add a rate_limit block to the run_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 run_eval completely? +

Set action: deny in the PolicyLayer policy for run_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 run_eval? +

run_eval is provided by the Gq Insight MCP server (yusufdxb/gq-insight-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.