How to Use the AutoGen MCP in CrewAI

Q: Can I use AutoGen tools inside a CrewAI agent definition?

Yes. You pass the Vinkius HTTP URL directly in the mcps list when defining your CrewAI agent. The agent automatically gets access to tools like createsession.

Q: How does CrewAI coordinate with AutoGen sessions?

CrewAI acts as the manager, calling createmessage to send tasks to AutoGen, and reading the output using listmessages to decide the next step.

Q: Can a CrewAI agent configure new AutoGen agents?

Yes. By giving a CrewAI agent access to createagent, it can dynamically build custom specialists based on the incoming backlog of tasks.

Q: How do I handle multiple MCP servers in CrewAI?

You use the MCPServerHTTP class from the crewai.mcp module. This lets you connect to this server alongside other tools, using a toolfilter if you only want to expose specific agent-creation tools.

Q: Where are my AutoGen agent configurations stored securely?

Your agent configurations queried via listagents are protected by Vinkius's zero-trust architecture. Credentials and agent definitions never persist in the execution container once the session ends.

Deploy collaborative CrewAI teams to monitor and manage AutoGen multi-agent sessions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AutoGen MCP to CrewAI

Create your Vinkius account to connect AutoGen to CrewAI 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 AutoGen with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Hierarchical team management with CrewAI

Let a CrewAI manager agent oversee your AutoGen processes via our MCP integration. The manager uses `list_sessions` to check on active runs, while subordinate crews handle specific tasks within those sessions. If a session gets stuck, your crew can run `create_message` to inject new instructions or nudge the local agents back on track. This keeps your pipeline moving without manual intervention.

Automated cleanup using an MCP Server

Autonomous crews need to clean up after themselves. Configure a specialized CrewAI agent to monitor resource usage and trigger `delete_session` when a task is marked complete. Before wiping the session, the agent can call `list_messages` to archive the full conversation history to your external database. This ensures you never lose valuable run data.

Dynamic skill assignment for crew tasks

Your CrewAI agents can dynamically check what tools are available in the AutoGen environment. By calling `list_skills`, the crew understands what Python code can run in the current context. They can then match these skills against `list_workflows` to decide whether to spin up a new dedicated AutoGen agent using `create_agent`. This lets your team scale its capabilities on the fly.

Setup guide

Set up AutoGen MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke AutoGen tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="AutoGen Analyst",
    goal="Access and analyze AutoGen data via MCP.",
    backstory="Expert analyst with direct AutoGen access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent AutoGen transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="AutoGen Analyst",
        goal="Access and analyze AutoGen data via MCP.",
        backstory="Expert analyst with direct AutoGen access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent AutoGen transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 Microsoft AutoGen. 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 AutoGen 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 AutoGen MCP in CrewAI

Yes. You pass the Vinkius HTTP URL directly in the `mcps` list when defining your CrewAI agent. The agent automatically gets access to tools like `create_session`.

CrewAI acts as the manager, calling `create_message` to send tasks to AutoGen, and reading the output using `list_messages` to decide the next step.

Yes. By giving a CrewAI agent access to `create_agent`, it can dynamically build custom specialists based on the incoming backlog of tasks.

You use the `MCPServerHTTP` class from the `crewai.mcp` module. This lets you connect to this server alongside other tools, using a `tool_filter` if you only want to expose specific agent-creation tools.

Your agent configurations queried via `list_agents` are protected by Vinkius's zero-trust architecture. Credentials and agent definitions never persist in the execution container once the session ends.

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