Model context protocol (MCP)
The Model Context Protocol (MCP) is an open standard that enables AI agents to access contextual metadata from external systems. It provides a consistent way for large language models and automation frameworks to retrieve the context they need to generate accurate and reliable results.
Atlan MCP is based on this standard and provides a reference implementation through the Atlan MCP server. The server acts as a secure bridge between Atlan's metadata platform and AI tools such as Claude, Cursor, Windsurf, and Microsoft Copilot Studio. With Atlan MCP, you can search and discover assets, explore lineage, update metadata, manage classification tags and custom metadata, govern the asset lifecycle, create glossaries, enforce data quality, and more, all using real-time context from Atlan.
Atlan MCP tools
The Atlan MCP server provides a set of tools that enable AI agents to work directly with Atlan metadata. These tools supply real-time context to AI environments, making it easier to search, explore, and update metadata without leaving your workflow.
The latest version of the server includes all of the tools listed below. If you don't see a tool in your environment, update to the latest Atlan MCP server version.
Search & discovery
Semantic search
Find relevant assets using natural-language queries and intent-aware ranking so AI agents surface the right context faster.
Search assets
Find assets using structured filters such as type, certification status, and creation date to return precise, targeted results.
Count assets
Count assets matching specific filters to answer aggregation questions like "how many certified tables exist?" without fetching full result sets.
Get asset
Retrieve complete details for a specific asset by GUID, including metadata, owners, tags, and custom attributes.
Resolve metadata
Discover users, tags, glossary terms, custom metadata schemas, and domains by name using vector search across five namespaces so AI agents can resolve the right values before writing metadata.
Get groups
List all groups in Atlan and their members so AI agents can resolve group names to actual identities for governance and ownership tasks.
Lineage & exploration
Traverse lineage
Trace upstream or downstream lineage for an asset to understand dependencies, data flows, and impact across your environment.
Query assets
Run SQL queries directly on connected data sources such as Snowflake to retrieve sample data for analysis and validation.
Asset metadata
Update assets
Modify asset metadata such as descriptions, certification status, and README content so AI workflows keep asset context up to date.
Update custom metadata
Set or update custom metadata attribute values on any asset to capture governance, quality, or business context defined by your organization.
Add Atlan tags
Apply one or more classification tags to assets, with optional propagation to downstream lineage so governed classifications stay consistent across related assets.
Remove Atlan tag
Remove a specific classification tag from an asset to keep tagging accurate and reflect changes in data sensitivity or governance state.
Manage announcements
Add or remove announcements (informational, warning, or issue) on assets to communicate status changes, deprecation notices, or known problems to your team.
Custom metadata
Create custom metadata set
Define a new custom metadata set with typed attributes so teams can capture structured governance, quality, or business context on assets.
Add attributes to CM set
Add new typed attributes to an existing custom metadata set to extend its schema without needing to recreate it.
Remove attributes from CM set
Remove specific attributes from a custom metadata set when they are no longer needed for your governance model.
Remove custom metadata
Clear all custom metadata values from an asset for a specific metadata set, removing the captured context without deleting the set itself.
Delete custom metadata set
Permanently delete an entire custom metadata set and all its attribute definitions when the schema is no longer needed.
Asset lifecycle
Manage asset lifecycle
Archive, restore, or purge assets to manage the end-of-life state of deprecated or replaced data assets and keep your catalog clean.
Business glossary
Create glossaries
Define new business glossaries with metadata and descriptions so teams can organize terms by domain or function.
Create glossary categories
Add categories and subcategories inside glossaries so business terms are grouped into clear, navigable hierarchies.
Create glossary terms
Create individual business terms with names, definitions, and certificate status so AI agents can align prompts with shared language.
Data domains
Create domains
Define data domains and subdomains to organize assets and data products by business area and ownership.
Create data products
Create data products linked to assets within a domain so teams can publish and discover business-ready datasets and contracts.
Data quality
Create DQ rules
Define column, table, and SQL-based rules on critical assets so AI workflows can enforce baseline data quality checks.
Update DQ rules
Adjust thresholds, priorities, and conditions on existing rules so quality checks stay aligned with evolving data patterns.
Schedule DQ rules
Configure cron-based schedules for rules on tables and views so data quality checks run automatically alongside ETL workflows.
Delete DQ rules
Remove deprecated or noisy rules so your data quality rule set remains focused and maintainable.
Deployment options
You can connect to Atlan MCP in two ways:
Hosted, per-tenant MCP server managed by Atlan, with OAuth and API Key authentication. Ideal for production setups and available in private preview for eligible tenants.
Locally hosted MCP server you run with Docker or uv. Ideal for development, testing, and custom environments before moving to a managed option.