Call this tool when the user wants to start a Crews Council run. Creates the run row on the UnClick API and returns a ConversationalCard with next actions. LLM turns are expected to flow through MCP sampling; if the Orchestrator does not support sampling the card reports SAMPLING_NOT_SUPPORTED. R...
AI agents invoke start_crew_run to trigger actions in UnClick. 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 |
|---|---|---|---|
crew_id | string | Yes | The UUID of the Crew to run |
task_id | string | — | Client-generated idempotency key (UUIDv5 from thread_id + prompt_hash + time_bucket recommended). Required for safe retry. If omitted, the server creates a fres |
task_prompt | string | Yes | The task the Council should deliberate on |
token_budget | number | — | Optional token budget (default 150000) |
Parameters from the server's own tool schema.
The tool does more than read or write discrete data—it initiates and orchestrates a multi-turn workflow ('LLM turns are expected to flow through MCP sampling') with downstream effects that cannot be fully predicted or controlled at invocation time. This makes it Execute rather than Write.
From the tool's definition The tool 'starts a Crews Council run' and 'Creates the run row on the UnClick API and returns a ConversationalCard with next actions.' This initiates an external operation (a Crews Council run) whose effects depend on what the user requests and how subsequent…
Attacks that exploit this kind of access
Call this tool when the user wants to start a Crews Council run. Creates the run row on the UnClick API and returns a ConversationalCard with next actions. LLM turns are expected to flow through MCP sampling; if the Orchestrator does not support sampling the card reports SAMPLING_NOT_SUPPORTED. Response card surfaces was_duplicate when an existing run is returned for an already-seen task_id. It is categorised as a Execute tool in the UnClick MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
start_crew_run accepts 4 parameters: crew_id, task_id, task_prompt, token_budget. Required: crew_id, task_prompt. The full parameter table on this page comes from the server's own tool schema.
Register the UnClick MCP server in PolicyLayer and add a rule for start_crew_run: 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 UnClick. Nothing to install.
start_crew_run 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 start_crew_run 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 start_crew_run. 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.
start_crew_run is provided by the UnClick MCP server (@unclick/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →