conclave_config · Conclave MCP: Risk & Policy

WHAT IT DOES

What conclave_config does on Conclave MCP

AI agents use conclave_config to create or update resources in Conclave MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Conclave MCP environment.

WHY IT NEEDS A POLICY

Why conclave_config needs a policy

The naming pattern strongly implies this tool modifies conclave configuration parameters (model selection, ranking methods, consensus rules, etc.). Configuration changes are reversible (Write, not Destructive), but could redirect LLM queries to malicious models or alter consensus logic if misconfigured by an agent without proper guardrails.

From the tool's definition Tool name 'conclave_config' suggests configuration modification. The empty description prevents direct verification, but 'config' typically indicates Write operations that modify settings or state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

conclave_config Rate-limited

conclave_config stays usable, but capped — an agent stuck in a loop can't make hundreds of changes 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_config": {
      "limits": [
        {
          "counter": "conclave_config_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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_config

What does the conclave_config tool do? +

conclave_config. It is categorised as a Write tool in the Conclave MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on conclave_config? +

Register the Conclave MCP server in PolicyLayer and add a rule for conclave_config: 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_config? +

conclave_config is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit conclave_config? +

Yes. Add a rate_limit block to the conclave_config 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_config completely? +

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

conclave_config 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.