Can my AI search for a specific dashboard or data table by keyword?

Yes. Ask the agent to perform an asset search using a natural phrase like 'Q3 revenue report' or 'customer addresses table'. The agent triggers Atlan's semantic asset search, returning linked objects across all connected BI and database sources.

Are custom Atlan Classifications and Tags exposed to the AI?

Yes. The agent can list all organizational classifications configured in Atlan (e.g., Sensitive, Restricted, CCPA). This lets the AI contextualize whether the assets it discovers are safe to be shared globally or subject to governance restrictions.

Can the agent modify or write back metadata to Atlan?

No. This MCP integration focuses strictly on safe discovery and organizational governance retrieval (queries). It guarantees your metadata catalogues remain pristine, acting purely as an active lookup augmentation tool for your agent.

Atlan MCP Server for Pydantic AI 6 tools — connect in under 2 minutes

Name: Atlan
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 6 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Atlan through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Atlan "
            "(6 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Atlan?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Atlan MCP Server

Connect your Atlan workspace to any AI agent and empower it to become a master data steward. By linking the leading Active Metadata Management platform with agents, you gain conversational governance and instant data cataloging capabilities on demand.

Pydantic AI validates every Atlan tool response against typed schemas, catching data inconsistencies at build time. Connect 6 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Asset Search — Query your entire connected data ecosystem (tables, dashboards, columns) via natural text to discover lineage and trusted data instantly
Business Glossaries — Retrieve organizational glossaries containing verified business terms, acronyms, and trusted definitions used by your enterprise
Classifications & Policies — List active data classifications (like PII or Confidential tags) and configured sharing purposes (data policies) across the estate
Users & Personas — Inspect registered users and configured access control profiles (Personas) aligned to specific business roles

The Atlan MCP Server exposes 6 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Atlan to Pydantic AI via MCP

Follow these steps to integrate the Atlan MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 6 tools from Atlan with type-safe schemas

Why Use Pydantic AI with the Atlan MCP Server

Pydantic AI provides unique advantages when paired with Atlan through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Atlan integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Atlan connection logic from agent behavior for testable, maintainable code

Atlan + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Atlan MCP Server delivers measurable value.

Type-safe data pipelines: query Atlan with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Atlan tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Atlan and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Atlan responses and write comprehensive agent tests

Atlan MCP Tools for Pydantic AI (6)

These 6 tools become available when you connect Atlan to Pydantic AI via MCP:

list_classifications

) configured in Atlan for data governance purposes. List all classifications defined in Atlan

list_glossaries

List all business glossaries in Atlan

list_personas

List all Atlan Personas

list_purposes

List all Atlan Purposes

list_users

List all users in the Atlan workspace

search_assets

Search for data assets in the Atlan Data Catalog

Example Prompts for Atlan in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Atlan immediately.

"Search for any data assets related to 'churn prediction'."

"What business glossaries do we have configured in our metadata?"

"List all security classifications defined across our catalogs."

Troubleshooting Atlan MCP Server with Pydantic AI

Common issues when connecting Atlan to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Atlan + Pydantic AI FAQ

Common questions about integrating Atlan MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Atlan MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.