conclave_ranked · Conclave MCP: Risk & Policy

WHAT IT DOES

What conclave_ranked does on Conclave MCP

AI agents invoke conclave_ranked to trigger actions in Conclave MCP. 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 conclave_ranked needs a policy

Based on sibling tools and server description, this tool likely executes ranked evaluations by consulting multiple frontier LLM APIs (GPT, Claude, Gemini, Grok, DeepSeek), which constitutes triggering external operations. The description is empty, lowering confidence.

From the tool's definition Tool name 'conclave_ranked' and server context referencing 'peer-ranked evaluations' suggest this triggers LLM queries and ranking operations across multiple external AI models.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

conclave_ranked Rate-limited

conclave_ranked 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": {
    "conclave_ranked": {
      "limits": [
        {
          "counter": "conclave_ranked_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 Conclave MCP, so you can run agents against it safely.

FAQ

Questions about conclave_ranked

What does the conclave_ranked tool do? +

conclave_ranked. It is categorised as a Execute tool in the Conclave MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on conclave_ranked? +

Register the Conclave MCP server in PolicyLayer and add a rule for conclave_ranked: 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 Conclave MCP. Nothing to install.

What risk level is conclave_ranked? +

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

Can I rate-limit conclave_ranked? +

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

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

conclave_ranked is provided by the Conclave MCP server (stephenpeters/conclave-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.