Use CrewAI with your AI.
Connect your account once and let the AI you already use work with it, without building another integration. Orchestrate multi-agent workflows via CrewAI. list crews and agents, kickoff autonomous runs, and monitor task execution directly from any AI agent.
Developed, maintained, and hosted by Vinkius.
MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED
Waiting for input…
Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.
Complete set · 3 capabilities
The complete CrewAI capability set.
These are the exact actions your AI can choose when you ask it to work with CrewAI.
01-03
3 capabilities in this set.
Part of 3 available through CrewAI.
- 01
Get status
Retrieve explicit execution state tracing limits
- 02
Kickoff crew
Provision a highly-available JSON Payload generating hard execution bindings
- 03
Get inputs
Identify bounded inputs required to kickoff a crew
Observed, not estimated
766ms average. Fast in production.
CrewAI is checked daily against the live service.
- Fastest day
- 630ms
- Slowest day
- 984ms
- 14-day trend
- Slowing+26%
Connect your client
One URL. Every client.
Activate the Connector, copy your link, and paste it into the client you already use. 3 capabilities arrive ready to run.
Preview access · not provider authentication
The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of CrewAI, so you can see the experience inside your AI.
It does not authenticate your account with CrewAI. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.
CrewAI Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_vQl1sjKmbDR8pDbzxB1A2J0p9pCxG6EwZ7FmwnqF/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — CrewAI capabilities are ready to use.
{
"mcpServers": {
"crewai-platform-mcp": {
"url": "https://edge.vinkius.com/vk_preview_vQl1sjKmbDR8pDbzxB1A2J0p9pCxG6EwZ7FmwnqF/mcp"
}
}
}
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Step-by-step instructions for each client are in the guide. How to connect
FAQ
Questions CrewAI owners ask.
- 01
Can my agent kickoff a new CrewAI workflow?
Yes. Use the 'kickoff_crew' capability. Provide the Crew ID and a JSON object with the required inputs. The agent will activate the multi-agent processing immediately, returning a run ID for tracking.
- 02
How do I monitor the progress of an active agent run?
Use the 'get_run_status' capability with your Crew ID and Run ID. Your agent will grab the live execution state, showing you which agents are currently working and which tasks have been completed.
- 03
Can I cancel a running crew via the agent?
Absolutely. The 'cancel_run' capability dispatches an instant interrupt signal to the CrewAI platform, hard-stopping active LLM contexts and terminating the execution flow immediately.
Explore
More in Superpower
Assertible AI Connector
Automate API testing and monitoring via Assertible — trigger deployments, run service tests, and sync specific
ViewFlagsmith AI Connector
Manage feature flags and remote config via Flagsmith — toggle features, manage identities, and update environm
ViewBeeceptor AI Connector
Mock APIs, intercept requests, and manage proxy rules directly from your AI agent.
ViewTool Argument Completeness Checker AI Connector
Audits LLM tool calls to detect missing parameters and value hallucinations.
View
Suggestions
Agent DAG Scheduler AI Connector
A deterministic engine for calculating execution order and scheduling metrics for multi-agent workflows.
ViewVercel AI SDK Stream Parser AI Connector
Deterministic parser for Vercel AI SDK 3.0 Data Stream protocol chunks.
ViewLLM Output JSON Extractor AI Connector
Isolates valid JSON objects from mixed markdown/text LLM outputs using deterministic bracket-matching.
ViewReqBin AI Connector
Test and verify API requests using ReqBin Echo — send JSON payloads and inspect the echoed response to debug r
View
