How to Use the Atlan MCP in LlamaIndex

Q: How do I tell my LlamaIndex agent which Atlan tools to use?

You'll wrap them in a McpToolSpec. This lets you pass only the specific tools you want to your agent, like allowing it to use just searchassets and listglossaries.

Ground your LlamaIndex RAG apps in your live Atlan data catalog. Build a query engine that knows your data's 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 LlamaIndex

Create your Vinkius account to connect Atlan to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Your Entire Data Catalog

This isn't just about one-off lookups. LlamaIndex can use the tools from this MCP server to systematically crawl and index your Atlan metadata. It can run `search_assets` for everything, pull all definitions with `list_glossaries`, and fetch all policies with `list_classifications`. The result is a vector index—a searchable knowledge base of your data landscape. When you ask a question, LlamaIndex finds the most relevant, up-to-date metadata from Atlan to inform the answer.

Build a Governance-Aware Chatbot with LlamaIndex

Create a RAG pipeline that answers questions about your data governance. Your agent can query its index of Atlan `Personas`, `Purposes`, and `Classifications` to explain access rules or data handling policies. Instead of just getting a list of policies, a user can ask "What's our policy for customer email data?". LlamaIndex will find the relevant classification and purpose information from its indexed Atlan data to give a plain-English answer.

Answer Questions About Data Ownership

Use the `list_users` tool to build an index of all stakeholders in your Atlan workspace. Your RAG application can now answer questions like "Who are the data stewards for the marketing department?". Combine this with asset information from `search_assets`. A user can ask "Who owns the 'quarterly_revenue' dashboard?", and the agent can cross-reference the asset's owner ID with the indexed user list to give a direct name. This MCP connection keeps your index fresh.

Setup guide

Set up Atlan MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Atlan MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Atlan tools.",
)
response = await agent.run("List recent Atlan data")

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 LlamaIndex

You can do both. Use the MCP tools directly for live queries, or build a `VectorStoreIndex` from the tool outputs for faster, semantic Q&A on your Atlan metadata.

You'll wrap them in a `McpToolSpec`. This lets you pass only the specific tools you want to your agent, like allowing it to use just `search_assets` and `list_glossaries`.

Yes, that's what it's built for. You can combine the Atlan MCP tools with a `SimpleDirectoryReader` to create a unified index over your data catalog and your Confluence pages.

It grounds the agent's responses in facts from your data catalog. By fetching real-time metadata from Atlan, the agent's answers about your data assets are based on your single source of truth, not guesswork.

LlamaIndex will index metadata from your Atlan instance—things like asset definitions, glossary terms, and user roles. The underlying data in your warehouses is never accessed. The connection itself is encrypted and requires your unique Vinkius API key.

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