How to Use the CrewAI Platform MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK handle multi-agent handoffs using CrewAI Platform?

Yes. Your main OpenAI agent can use getcrew to inspect active account logic, then spin up specific crews using kickoffcrew based on the task requirements. This lets you delegate complex work to specialized CrewAI workers.

Run multi-agent CrewAI workflows directly inside your OpenAI Agents SDK using this managed MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CrewAI Platform MCP to OpenAI Agents SDK

Create your Vinkius account to connect CrewAI Platform to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup CrewAI Platform with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger and monitor jobs with OpenAI Agents SDK

The `kickoff_crew` tool lets your agent start new autonomous crew runs directly from your Python code. You pass the JSON payload, and the MCP server returns the hard customer bindings to track execution. To keep tabs on ongoing work, your agent can call `get_run_status` or `get_task` to trace gateway auth details and vault limits. This keeps your OpenAI dashboard updated with exact execution states.

Inspect active agent structures and configurations

The `get_agent` tool pulls the explicit rules and active billing info attached to any agent in your setup. This lets your OpenAI Agents SDK check constraints before handing off tasks to specialized sub-agents. You can also run `list_agents` to clean up expired validations and extract churn flags. It keeps your production system clean without manual database scripts.

Manage live crews and webhooks on the fly

The `list_crews` tool identifies active CRM records inside your headless CrewAI Platform setup. Your agent reads these records to decide which crew needs to handle incoming customer requests. Use `list_webhooks` to parse active arrays and hold states, giving your OpenAI Agents SDK real-time feedback on external events. If a run goes sideways, `cancel_run` stops the execution immediately.

Setup guide

Set up CrewAI Platform MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all CrewAI Platform tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives CrewAI Platform tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate CrewAI Platform tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="CrewAI Platform Agent",
            instructions="You have access to CrewAI Platform tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by CrewAI. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect CrewAI Platform now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about CrewAI Platform MCP in OpenAI Agents SDK

Install the SDK, then initialize the MCPServerStreamableHttp object with your Vinkius endpoint. Pass this server instance directly into your Agent constructor's mcp_servers list. The agent automatically registers all ten tools.

Yes. Your main OpenAI agent can use `get_crew` to inspect active account logic, then spin up specific crews using `kickoff_crew` based on the task requirements. This lets you delegate complex work to specialized CrewAI workers.

The SDK passes run data to your OpenAI dashboard automatically. When your agent calls `get_run_status` to check vault limits, the entire call stack and payload are logged for easy debugging.

Yes. You can configure this directly in your OpenAI agent setup by filtering the tool list before passing it to the constructor. This prevents the agent from calling destructive tools like `list_agents` if you want to protect your validation states.

Your JSON payloads and active CRM records stay inside the Vinkius V8 sandbox. The MCP Server acts as an ephemeral proxy. It never stores your API keys or database logs on persistent disks.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript