How to Use the Atlan MCP in LangChain

Q: How can a LangChain agent find all tables marked with PII in Atlan?

Your agent would use a chain. First, it calls searchassets with a filter for the 'PII' classification. Then, it can iterate through the results to get the specific table names for the next step.

Build agents that query your Atlan data catalog. Connect LangChain to your single source of truth for governance and discovery.

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 LangChain

Create your Vinkius account to connect Atlan to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Find Data Assets Programmatically

This toolset lets your LangChain agent search Atlan's data catalog. Use `search_assets` to find tables, dashboards, or columns based on names, descriptions, or even SQL queries. The agent gets structured data back—perfect for the next step in a chain. You can build chains that first find an asset, then use its metadata to trigger another action, like generating a report or checking its classification. It's how you automate data discovery tasks that used to be manual.

Check Governance and Compliance

Your agent can pull governance artifacts directly from Atlan. It can call `list_glossaries` to get business term definitions or run `list_classifications` to check how data is tagged, like for PII or other sensitive information. This is great for building compliance bots. An agent can check if a new dataset meets policy before it's used, or verify that all assets in a project have the right tag by calling `list_purposes`. This MCP connection keeps your agent synced with your rules.

Manage Users and Access with this MCP Server

Give your agents the ability to see who's who in your Atlan workspace. The `list_users` tool returns a list of all provisioned users, while `list_personas` shows the different roles you've configured. A LangChain agent could use this to route questions. For example, it could find a data asset with `search_assets`, see who owns it, and then use another tool to notify them. It connects your catalog to your team.

Setup guide

Set up Atlan MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Atlan tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "atlan-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Atlan transactions"
    })
    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 LangChain

Your agent would use a chain. First, it calls `search_assets` with a filter for the 'PII' classification. Then, it can iterate through the results to get the specific table names for the next step.

Yes, they're a perfect fit for that pattern. The agent can reason about which tool to use, like using `search_assets` first, then deciding to call `list_glossaries` to understand a term from the asset's description.

Absolutely. Every tool call your LangChain agent makes to this MCP server is automatically traced in LangSmith. You'll see the exact inputs, outputs, and latency for each Atlan operation.

Use the tools from this MCP server as one step in your chain. You can have your agent query Atlan for a schema, then use a SQL toolkit in the next step to query the actual database directly.

This server only accesses Atlan metadata: asset names, descriptions, glossaries, user lists, and governance tags. It never touches the underlying data in your databases. All connections are over HTTPS and authenticated with your Vinkius token.

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