How to Use the Atlan MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK agent automatically filter Atlan assets?

Yes, your agent uses the searchassets tool to pull specific objects based on your criteria. It returns structured data that the agent parses to make decisions.

Query your data governance catalog directly from the OpenAI Agents SDK for production-ready context.

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 OpenAI Agents SDK

Create your Vinkius account to connect Atlan 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 Atlan with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search Atlan assets with OpenAI Agents SDK

Stop digging through web interfaces to find table metadata. Your agent triggers `search_assets` to pull schema details directly into your execution loop. This MCP Server provides the raw context your agent needs to understand data lineage before it writes a single line of SQL.

Audit governance with OpenAI Agents SDK

Run `list_classifications` to see exactly how your team tags sensitive information across the stack. Your agent now knows which tables contain PII without manual mapping. It handles the heavy lifting by exposing the exact governance labels defined in your workspace. Your agent checks these tags before touching restricted data.

Map organizational context in OpenAI Agents SDK

Access the full hierarchy of your company data using `list_glossaries` and `list_personas`. Your agent maps technical assets to business definitions in real time. Connect these tools to your agent to ensure every query aligns with internal terminology. It eliminates the guessing game when your agent interprets business logic.

Setup guide

Set up Atlan 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 Atlan tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Atlan 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="Atlan Agent",
            instructions="You have access to Atlan 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 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 OpenAI Agents SDK

You initialize the connection using the MCPServerStreamableHttp class. Pass your Vinkius endpoint into the constructor and add it to your Agent's tool list.

Yes, your agent uses the `search_assets` tool to pull specific objects based on your criteria. It returns structured data that the agent parses to make decisions.

The server exposes metadata that you feed into your custom guardrails. Your agent can validate classification tags before it executes any sensitive operations.

The Vinkius-hosted server handles the abstraction. You keep your agent logic stable while we manage the underlying connection to the workspace.

The server only reads metadata like schema names, classifications, and user lists. It does not touch your actual row-level data or sensitive PII records.

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