judge.rank_responses · ContextForge MCP Gateway MCP

WHAT IT DOES

What judge.rank_responses does on ContextForge MCP Gateway

AI agents invoke judge.rank_responses to trigger actions in ContextForge MCP Gateway. 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 judge.rank_responses needs a policy

This tool invokes an LLM-as-a-judge mechanism to evaluate and rank responses, which constitutes triggering an external operation (LLM inference call). It doesn't merely read static data; it executes a computational/AI process whose output depends on the inputs provided.

From the tool's definition 'Rank multiple responses from best to worst using LLM-as-a-judge' — triggers an LLM evaluation process as an external operation

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

judge.rank_responses Rate-limited

judge.rank_responses 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": {
    "judge.rank_responses": {
      "limits": [
        {
          "counter": "judge.rank_responses_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 ContextForge MCP Gateway, so you can run agents against it safely.

FAQ

Questions about judge.rank_responses

What does the judge.rank_responses tool do? +

Rank multiple responses from best to worst using LLM-as-a-judge. It is categorised as a Execute tool in the ContextForge MCP Gateway MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on judge.rank_responses? +

Register the ContextForge MCP Gateway MCP server in PolicyLayer and add a rule for judge.rank_responses: 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 ContextForge MCP Gateway. Nothing to install.

What risk level is judge.rank_responses? +

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

Can I rate-limit judge.rank_responses? +

Yes. Add a rate_limit block to the judge.rank_responses 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 judge.rank_responses completely? +

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

judge.rank_responses is provided by the ContextForge MCP Gateway MCP server (jrmatherly/mcp-context-forge). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.