How to Use the Airbyte MCP in AutoGen

Q: Can I give different agents access to different tools?

Yes. You can equip a MonitoringAgent with only the list tools, while a ConfigurationAgent gets access to the get tools. This lets you enforce roles and responsibilities within your agent team, just like with a human team.

Assemble a team of AutoGen agents to debate, diagnose, and manage your Airbyte data pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Airbyte MCP to AutoGen

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create an AI Data Operations Team

Go beyond single-agent execution. With AutoGen, you can create a conversation between multiple agents to manage Airbyte. A `MonitorAgent` can use `list_jobs` to spot a failure and report it to the group. A `DiagnosticsAgent` then picks up the conversation, using `get_connection` and `get_source` to investigate the configuration. It presents its findings, and a `PlannerAgent` can propose a solution. This is collaborative problem-solving, done by your agents.

Debate Solutions to Pipeline Failures

The real strength of AutoGen is modeling different perspectives. Imagine a failed sync. One agent, focused on data integrity, might suggest a full resync. Another, focused on cost, might check the source data size and argue for a more targeted fix. They use the data from the Airbyte MCP tools as evidence in their debate. The `list_jobs` output shows the error, and `get_source` details might point to a schema change. The agents argue until they reach a consensus on the best path forward.

Your AutoGen MCP Server for Airbyte

These tools are the senses for your agent team. They provide the ground truth about your Airbyte environment. An agent can call `list_workspaces` to get an overview, or `list_destinations` to understand where data is flowing. Because AutoGen agents can call tools and then discuss the results, you can build very sophisticated systems. You can have one agent responsible for monitoring, another for security checks, and a user proxy that translates your requests into tasks for the team.

Setup guide

Set up Airbyte MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Airbyte tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Airbyte_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Airbyte data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Airbyte_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Airbyte data")
    print(result.messages[-1].content)

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 Airbyte. 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 Airbyte 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 Airbyte MCP in AutoGen

An agent conversation is a great way to diagnose Airbyte issues. One agent uses `list_jobs` to find a failed sync. Another agent takes the `connection_id` and uses `get_connection` to check its setup. They discuss the findings before presenting a summary and a suggested fix.

Yes, that's the core idea. You can have a group chat where one agent is responsible for calling `list_connections` and `list_jobs` periodically. If it finds an issue, it posts a message to the group, triggering other agents to start their diagnostic tasks.

It's the ability to have your AI agents deliberate. Instead of a single agent following a rigid plan, you have a team that can debate the output of tools like `get_source` and `list_jobs`. This leads to more robust and well-reasoned decisions about your data pipelines.

Yes. You can equip a `MonitoringAgent` with only the `list_*` tools, while a `ConfigurationAgent` gets access to the `get_*` tools. This lets you enforce roles and responsibilities within your agent team, just like with a human team.

Your Airbyte pipeline metadata, like source configurations and job logs, is passed from the MCP server to your running AutoGen agents. The data exists only for the duration of the agent conversation in your environment. Vinkius doesn't log or retain any of the specific configuration details your agents work with.

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