---
title: "Data Catalog for AI Agents | Atlan"
url: "https://atlan.com/data-discovery-catalog/"
description: "Data catalogs made data findable for humans. Atlan is the context layer for AI - building the Enterprise Data Graph your agents read via MCP, A2A, or SQL."
---

> Atlan is hosting Context Conference, bringing together the leaders and builders at the frontier of giving AI the context it needs to understand their business. It runs online on October 28, 2026, from 11:00 AM to 2:00 PM ET. Atlan co-founder Prukalpa Sankar opens and closes the day. Leaders from AstraZeneca, BNY and Verizon share why they invest in context and what they get from it. Registrants get early access to The AI Context Gap, a new study from MIT Technology Review Insights. Register: https://atlan.com/context-conference/

**Data catalogs were the context layer for data. Atlan is the context layer for AI.** Atlan connects your entire data estate, maps every dependency through lineage, and enriches every asset with AI-generated context. The result: an Enterprise Data Graph that every AI agent in your stack reads via MCP, A2A, or SQL, and every human finds in the Data Marketplace.

[Book a Demo](https://atlan.com/forms/talk-to-sales-contact/) / [See How It Works](https://atlan.com/context-layer-demo/)

## The catalog solved the human problem. AI needed something bigger.

Data catalogs were built for a world where humans were the primary consumers of data. They made data findable, documented assets, tracked ownership. AI changed the requirements: agents don't browse, they need structured, machine-readable context served automatically, at scale, across every system and protocol. That is a context infrastructure problem.

Atlan is the [context layer for AI](https://atlan.com/context-layer/). [Native connectors](https://atlan.com/connectors/) pull metadata from every system. [Data Lineage](https://atlan.com/data-lineage/) maps column-level provenance automatically. [Context Agents](https://atlan.com/context-agents/) write the descriptions, definitions, and quality scores at a 90%+ acceptance rate. The Enterprise Data Graph is the result: context infrastructure every AI agent reads and every human searches.

## From the context layer for data to the context layer for AI

The context layer starts where your data catalog does, and goes much further.

- **The catalog collects.** Connectors pull metadata from warehouses, pipelines, BI tools, SaaS apps, and custom sources. [Connectors](https://atlan.com/connectors/)
- **Lineage connects it.** Data Lineage reconstructs column-level provenance across every system. Quality signals, governance classifications, and business definitions propagate downstream automatically. [Data Lineage](https://atlan.com/data-lineage/)
- **Context Agents enrich it.** Nine AI agents continuously write descriptions, build glossaries, score quality, classify domains, and resolve metric conflicts. AI-generated, human-certified. [Context Agents](https://atlan.com/context-agents/)
- **Every agent and every human reads from it.** The Context Lakehouse exposes the full context layer to AI agents via MCP, A2A, SQL, and REST. The Data Marketplace makes it searchable for humans in natural language. [Context Lakehouse](https://atlan.com/context-lakehouse/) / [Data Marketplace](https://atlan.com/data-marketplace/)

## Leading AI teams use Atlan to connect context

Trusted by $10T in enterprise value. Customer videos: Sridher Arumugham (DigiKey: Context Readiness), Kiran Panja (CME Group: Context at Speed), Andrew Reiskind (Mastercard: Context by Design), Mauro Flores (Virgin Media O2: Context for All).

## Collect: every system feeds the context layer, automatically

Start building your context layer in 3 steps. Choose OAuth or API credentials, select the scope, and set a schedule.

1. **Authenticate your connection.** Connect with OAuth or API credentials. Test authentication before running so you can pre-empt failures, not debug them.
2. **Scope what to bring in.** At the database, schema, or table level.
3. **Schedule and start ingesting.** Run daily, weekly, or on demand. Atlan handles incremental updates automatically, with no manual maintenance.

Native connectors for every layer of your stack: see the full list at [atlan.com/connectors](https://atlan.com/connectors/). Can't find a connector? Anybody can build one in days using Atlan's App SDK.

## Connect: column-level lineage, context that compounds

Atlan reconstructs lineage from your SQL, pipelines, and APIs, so quality signals, governance classifications, and business definitions propagate to every downstream asset automatically. Four methods, one unified graph:

- **SQL parsing.** Atlan's parser reads millions of SQL queries from Snowflake, BigQuery, Redshift, and Databricks to extract the actual transformation logic.
- **Native integrations.** For tools SQL parsing can't reach, Atlan crawls each tool's native API to extract field-level dependencies and stitches them into the same graph.
- **OpenLineage.** Atlan natively consumes OpenLineage events from Airflow, Spark, dbt Cloud, and Astronomer, capturing runtime inputs, outputs, and column-level transformations as pipelines execute.
- **Custom lineage.** Atlan's App Framework provides REST APIs and SDKs for programmatic lineage, CSV imports for bulk ingestion, and a visual Lineage Builder for manual modeling.

## Enrich: nine AI agents, every layer of context, 90%+ acceptance rate

Context Agents enrich the context layer continuously. AI-generated at scale, human-certified before it ships.

| Agent | Role | What it does |
|---|---|---|
| Scout | Usage Intelligence | Ranks assets by what your team actually queries. |
| Scribe | Description Writer | Writes descriptions from SQL patterns and lineage. |
| Lexis | Glossary Builder | Builds your business glossary from column patterns. |
| Doc | Readme Author | Synthesizes signals into comprehensive dataset readmes. |
| Nexus | Terms Linker | Links every column to the business term analysts use. |
| Sage | Metric Arbiter | Finds conflicting metric definitions and locks one answer. |
| Atlas | Domain Classifier | Tags every asset with its business domain at scale. |
| Vera | Quality Scorer | Scores every critical asset on completeness and freshness. |
| Orion | Ontologist | Maps the ontology connecting every domain and metric. |

Rollout in 30 days, not 12 months:

- **Start with what matters.** Context Agents identify your Gold Layer, Popular BI, Popular SQL, and upstream dependencies first, enriching the assets people use before the long tail. Value shows up in days.
- **AI scores every output.** Each output carries a composite confidence score across accuracy, clarity, style, and completeness. High-confidence outputs auto-apply; lower-confidence outputs route to humans.
- **Humans decide and govern.** Stewards shift from documentation to certification: sampling, validating, and resolving the cases that need judgment. One click, not 847 manual reviews.

## Deliver to AI agents: one context layer, every protocol

AI agents don't browse; they read context. The Context Lakehouse exposes the full context layer to every AI agent via MCP, A2A, SQL, and REST.

- **MCP (Model Context Protocol):** what an asset means, whether it's trusted, and what policies apply, checked in a single call before anything executes.
- **A2A (Agent-to-Agent):** agents write observations, quality signals, and usage patterns back into the store, so context compounds with every interaction.
- **SQL:** standard SQL over Iceberg; query metadata exactly as you query your data, with every engine your team already runs.
- **REST and Graph APIs:** full programmatic access to the graph to build integrations, automate workflows, or pipe context into model training pipelines.

"AI initiatives require more context than ever. Atlan's metadata lakehouse is configurable, intuitive, and able to scale to hundreds of millions of assets." - Andrew Reiskind, Chief Data Officer, Mastercard

## Deliver to humans: search your data in plain language

The same context layer is searchable for humans in natural language, SQL, or by business term, with access governed automatically. Traditional catalogs were built for data teams, with clunky search, jargon-heavy interfaces, and no trust signals. Atlan offers plain-English search, role-personalized results, and embedding in Slack and Teams.

- **Conversational search.** Ask in natural language and get the right data product with certification, freshness, lineage, and one-click access, not a list of 200 tables.
- **Personalized experiences.** Atlan personalizes by role and domain, so every user sees the data products that matter to them.
- **Slack and MS Teams integration.** Ask questions, receive data product recommendations, and request access without leaving Slack or Microsoft Teams.
- **Zero-touch provisioning.** When a request is approved, access enforces automatically in Snowflake or Databricks: masking, column-level restrictions, attribute-based access control. No tickets. No waiting.

"The UI was so intuitive that even first-time users could search, navigate and find what they needed. Within the first year after that we cataloged over 18 million assets, defined more than 1,300 glossary terms, and we are tackling new use cases every quarter." - Kiran Panja, MD, Cloud & Data Engineering, CME Group

## Industry recognition

- **Customer Favorite, The Forrester Wave: Data Governance Solutions, Q3 2025:** "Users consistently praise Atlan's ease of use, flexibility, and responsiveness. They highlight its intuitive UI, strong lineage and smart search capabilities, and seamless integration across the data stack." [Report](https://atlan.com/know/forrester-wave-data-governance-2025/)
- **Leader, 2026 Gartner Magic Quadrant for Data & Analytics Governance Platforms (Visionary to Leader in one year):** "Leveraging the metadata lakehouse, the Atlan App Framework provides a structured toolkit and a marketplace to help developers, customers, and partners build, deploy, and share a wide range of applications, including custom connectors, data quality apps, and governance agents." [Report](https://atlan.com/gartner-magic-quadrant-data-governance-2026/)
- **Leader, 2025 Gartner Magic Quadrant for Metadata Management Solutions (#1 for enabling modern data architectures):** "Atlan's Metadata Lakehouse forms the core foundation, built on an open and highly performant architecture. It is designed to be Iceberg native and includes a knowledge graph and event stream engine." [Report](https://atlan.com/gartner-magic-quadrant-metadata-management-solutions-2025/)

## Explore the platform

- [Context Agents](https://atlan.com/context-agents/): AI teammates that enrich your catalog automatically.
- [Data Lineage](https://atlan.com/data-lineage/): column-level provenance across every system.
- [Context Lakehouse](https://atlan.com/context-lakehouse/): deliver context to every AI agent.
- [Data Marketplace](https://atlan.com/data-marketplace/): help every human find what they need.

## FAQ: data catalog for AI agents

**Is Atlan a data catalog?**
Atlan is the context layer for AI: the infrastructure that makes every AI agent in your stack accurate, trustworthy, and production-ready. Data catalogs were the context layer for data; they made data findable for humans. Atlan is what comes next.

**What's the difference between a data catalog and a context layer?**
A data catalog makes data findable for humans. A context layer makes AI agents accurate. Atlan builds the Enterprise Data Graph automatically and delivers it to every AI agent via MCP, A2A, or SQL, and every human through the Data Marketplace.

**How does Atlan deliver context to AI agents?**
Atlan's Context Lakehouse exposes the full Enterprise Data Graph through every protocol agents speak: MCP for LLM tools like Claude and Snowflake Cortex, A2A for multi-agent orchestration, and SQL for agents that already query data.

**What is the Enterprise Data Graph?**
What Atlan's data catalog becomes when everything is automated. Connectors pull metadata from every system, Data Lineage reconstructs column-level provenance, and Context Agents write descriptions, glossary terms, quality scores, and domain classifications continuously. Every asset, every system, fully documented and machine-readable.

**Can Atlan replace our existing data catalog?**
Yes. Atlan replaces your data catalog with the context layer for AI: connecting every system, documenting every asset through Context Agents, and mapping every dependency through Data Lineage, automatically. Everything your catalog did for humans, Atlan does for humans and AI agents.

Connectors pull every system in. Lineage maps every dependency. Context Agents enrich every asset. Every AI agent reads it via MCP, A2A, or SQL; every human finds it in the Marketplace. [Book a Demo](https://atlan.com/forms/talk-to-sales-contact/) (30-min call).