This record as markdown: /tools/io-github-0nork-0nmcp/council-debate.md
What council_debate does on 0nmcp
AI agents invoke council_debate to trigger actions in 0nmcp. 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 council_debate is rated High
This tool orchestrates calls to multiple external AI services, causing them to generate and exchange critiques. It executes external API operations whose effects depend on the arguments (which providers, what topic). No data is persistently written or deleted, but external compute and API calls are triggered, placing it in the Execute category. Misuse could incur API costs or generate harmful content at scale.
From the tool's definition 'Have AI providers critique each other' — triggers external operations against multiple AI provider APIs
Attacks that exploit this kind of access
The rule that runs council_debate safely
PolicyLayer is an MCP gateway: it sits between your AI agents and 0nmcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For council_debate, this is the rule to start with:
council_debate 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.
The button opens the PolicyLayer dashboard: create your workspace, connect 0nmcp, apply this rule, and every council_debate call is checked against it from then on.
Questions about council_debate
Have AI providers critique each other. It is categorised as a Execute tool in the 0nmcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the 0n MCP server in PolicyLayer and add a rule for council_debate: 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 0nmcp. Nothing to install.
council_debate is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the council_debate 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.
Set action: deny in the PolicyLayer policy for council_debate. 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.
council_debate is provided by the 0n MCP server (0nmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on 0n, and thousands of servers like it.
This server
Across the catalogue