crewai_kickoff
AI agents invoke crewai_kickoff to trigger actions in CrewAI MCP Orchestrator. 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.
In CrewAI, 'kickoff' is the primary method to start a crew's execution, triggering multi-agent workflows. This constitutes executing external operations whose effects depend on arguments. The description is empty, so confidence is reduced, but sibling tools like 'crewai_flow_run' confirm this server executes agent systems.
From the tool's definition Tool name 'crewai_kickoff' on a server described as providing tools to 'dynamically generate, edit, test, and execute multi-agent systems'. The 'kickoff' term is standard CrewAI terminology for launching/running a crew execution.
Attacks that exploit this kind of access
crewai_kickoff. It is categorised as a Execute tool in the CrewAI MCP Orchestrator MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the CrewAI MCP Orchestrator MCP server in PolicyLayer and add a rule for crewai_kickoff: 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 CrewAI MCP Orchestrator. Nothing to install.
crewai_kickoff 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 crewai_kickoff 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 crewai_kickoff. 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.
crewai_kickoff is provided by the CrewAI MCP Orchestrator MCP server (ssolis-ti/crewai-mcp-hq). 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 →