How to Use the Atlan MCP in AutoGen

Q: How do I give different AutoGen agents different Atlan tools?

You can create separate tool lists from the mcpservertools function. Then, just pass a specific list of tools to each AssistantAgent when you create it, defining its unique capabilities.

Q: Can one AutoGen agent find data in Atlan and pass it to another?

Yes, that's the core of AutoGen. An agent can call searchassets, and the resulting asset list becomes part of the conversation history. Other agents can then read that message and act on the data.

Q: How would an AutoGen agent use Atlan to check for data quality issues?

A 'QualityAgent' could use searchassets to find assets with no owner or missing classifications. It would then present this list to a 'StewardAgent,' kicking off a conversation about how to fix the gaps in your Atlan catalog.

Q: Is it complicated to set up the Atlan tools for my AutoGen agents?

No, it's pretty direct. The autogen-extmcp package handles it. You just point it to the MCP server URL, and it gives you a list of Python functions ready to be passed to your agents.

Let your AutoGen agents debate and decide on data strategy using live info from your Atlan catalog. Build smarter, collaborative AI teams.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Atlan MCP to AutoGen

Create your Vinkius account to connect Atlan 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 Atlan with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Equip Agents for Data Governance Debates

Create an agent conversation where different AI personas use Atlan data to argue their points. A 'SecurityAgent' can use `list_classifications` to flag assets with PII, while a 'DataScientistAgent' uses `search_assets` to find datasets for a new model. They don't just act; they converse. The security agent might challenge the use of a dataset, pointing to its classification. The data scientist agent can then counter by finding an alternative, anonymized asset.

Automate Catalog Management with this MCP Server

Design an AutoGen workflow to maintain your Atlan catalog. One agent could be tasked with finding assets missing descriptions using `search_assets`. It then passes that list to another agent that suggests descriptions. A human 'ProductManager' agent in the loop can approve the suggestions. The system uses tools like `list_glossaries` to ensure the new descriptions use standard business terms, creating a consensus-driven maintenance loop.

Simulate Access Control Scenarios

Use AutoGen to model how different roles interact with your data. You can have an agent representing a 'MarketingAnalyst' persona from Atlan try to access data. Another 'ComplianceAgent' can use `list_purposes` and `list_personas` from this MCP connection to check if that access is allowed by policy. This lets you test and validate your Atlan governance rules through simulated conversations before they cause real-world problems.

Setup guide

Set up Atlan 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 Atlan 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="Atlan_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Atlan 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="Atlan_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Atlan 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 Atlan. 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 Atlan 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 Atlan MCP in AutoGen

You can create separate tool lists from the `mcp_server_tools` function. Then, just pass a specific list of tools to each `AssistantAgent` when you create it, defining its unique capabilities.

Yes, that's the core of AutoGen. An agent can call `search_assets`, and the resulting asset list becomes part of the conversation history. Other agents can then read that message and act on the data.

A 'QualityAgent' could use `search_assets` to find assets with no owner or missing classifications. It would then present this list to a 'StewardAgent,' kicking off a conversation about how to fix the gaps in your Atlan catalog.

No, it's pretty direct. The `autogen-ext[mcp]` package handles it. You just point it to the MCP server URL, and it gives you a list of Python functions ready to be passed to your agents.

The agents will discuss metadata from your Atlan catalog, like asset names, governance classifications, and user lists. They don't access the actual data. The entire multi-agent conversation happens within your AutoGen environment, and communication with the MCP server is encrypted.

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