run_council
Submit a question or decision to Meta Council. A panel of specialized AI agents will independently analyze it, then a synthesis step combines their opinions into a unified recommendation with full transparency. Starts asynchronously by default; use get_session with the returned session id.
This record as markdown: /tools/com-meta-council-decision-intelligence/run-council.md
What run_council does on Meta Council
AI agents invoke run_council to trigger actions in Meta Council. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | — | Model to use (e.g., 'claude-sonnet-4-6', 'gpt-4o', 'deepseek-chat'). Omit to use user's default. |
panel | string | — | Panel slug to use (e.g., 'default', 'technology', 'healthcare'). Use 'auto' for automatic panel selection. Omit to use default panel. |
query | string | Yes | The question or decision to analyze |
wait_seconds | integer | — | Optional synchronous wait (0-90 seconds). Default 0 returns the session id immediately, avoiding reverse-proxy timeouts. |
Parameters from the server's own tool schema.
Why run_council is rated High
run_council executes a decision-making workflow involving multiple AI agents that analyze and synthesize information based on user input. While it does not modify data directly (unlike sibling tools like add_invoice_line_item or approve_consulting_deliverable), it triggers an external operation that runs code/logic and produces outputs that could influence downstream decisions or actions.
From the tool's definition Tool "submits a question or decision to Meta Council" which "starts asynchronously" and triggers a "panel of specialized AI agents" to "independently analyze" and produce a "synthesis" and "recommendation." This initiates an external computational operation…
Attacks that exploit this kind of access
The rule that runs run_council safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Meta Council, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For run_council, this is the rule to start with:
run_council 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 Meta Council, apply this rule, and every run_council call is checked against it from then on.
Questions about run_council
Submit a question or decision to Meta Council. A panel of specialized AI agents will independently analyze it, then a synthesis step combines their opinions into a unified recommendation with full transparency. Starts asynchronously by default; use get_session with the returned session id. It is categorised as a Execute tool in the Meta Council MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
run_council accepts 4 parameters: model, panel, query, wait_seconds. Required: query. The full parameter table on this page comes from the server's own tool schema.
Register the Meta Council MCP server in PolicyLayer and add a rule for run_council: 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 Meta Council. Nothing to install.
run_council 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 run_council 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 run_council. 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.
run_council is provided by the Meta Council MCP server (https://meta-council.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Meta Council, and thousands of servers like it.
Across the catalogue