council_ask
Ask multiple AI providers the same question simultaneously. Sends the prompt to all available AIs (GPT-4o, Gemini, Grok, Claude) in parallel. Returns each response with timing. YOUR credentials are never shared. Example: council_ask({ prompt:
This record as markdown: /tools/io-github-0nork-0nmcp/council-ask.md
What council_ask does on 0nmcp
AI agents call council_ask to retrieve information from 0nmcp without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why council_ask is rated Low
The tool's function is to query multiple AI providers in parallel and return their responses. While it makes external API calls, those calls are informational queries, not destructive operations, arbitrary code execution, or financial transactions. The explicit statement that 'YOUR credentials are never shared' reinforces that this is a safe read operation.
From the tool's definition Tool description states it 'Ask[s] multiple AI providers the same question simultaneously' and 'Returns each response with timing.' This is a query/retrieval operation that sends a prompt to external services and retrieves responses.
Attacks that exploit this kind of access
The rule that runs council_ask 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_ask, this is the rule to start with:
council_ask is read-only, so it stays allowed. 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_ask call is checked against it from then on.
Questions about council_ask
Ask multiple AI providers the same question simultaneously. Sends the prompt to all available AIs (GPT-4o, Gemini, Grok, Claude) in parallel. Returns each response with timing. YOUR credentials are never shared. Example: council_ask({ prompt:. It is categorised as a Read tool in the 0nmcp MCP Server, which means it retrieves data without modifying state.
Register the 0n MCP server in PolicyLayer and add a rule for council_ask: 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_ask is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the council_ask 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_ask. 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_ask 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