MCP Trust Layer for External AI Agents

What is MCP trust layer?

This feature is currently in Research Preview. We recommend working with your Ataccama account team for configuration assistance.

Full SLA support is not guaranteed during the preview period.

The Ataccama Model Context Protocol (MCP) trust layer allows external AI tools and applications such as Claude, ChatGPT, and Copilot to access data quality and governance information from the Ataccama ONE platform. This way, you can query catalog metadata, ownership details, business terms, and quality metrics directly through your AI assistant.

The MCP server provides over 20 read-only tools that interface with Ataccama’s underlying APIs, including stewardship, search, data quality and profiling tools.

The MCP trust layer is:

Read-only: You can’t use it to modify platform data.
Authenticated: Your permissions determine which data you have access to. See Authentication for details.
Configurable: Turn individual tools on and off as needed in your AI application.

Why use MCP trust layer?

This integration is useful for business analysts and data consumers who need quick answers about their data without navigating the full platform. You can ask about data semantics and meaning, data quality metrics, data ownership and stewardship, and business term definitions and relationships.

Ask natural language questions directly to your AI assistant, which retrieves the relevant information from Ataccama.

Examples:

"Who owns the customer_orders catalog item?"
"What’s the data quality score for this dataset?"
"What does the term 'Qualified product list' mean in our glossary?"
"Show me catalog items with quality issues."

Authentication

The MCP server uses OAuth 2.0 authentication via Keycloak:

The authentication token is securely stored on your local computer.
Access is restricted to data you have permissions for in Ataccama.
Session timeout follows your organization’s Keycloak configuration.

On first use, you are prompted to log in with your Ataccama credentials.

Available tools

Stewardship and organization tools

Tool Description

Tool	Description
`list_stewardship_groups`	Retrieve stewardship groups responsible for data governance.
`list_groups`	List organizational groups for stewardship assignments.
`list_dq_dimensions`	View available data quality dimensions.

list_stewardship_groups

Retrieve stewardship groups responsible for data governance.

list_groups

List organizational groups for stewardship assignments.

list_dq_dimensions

View available data quality dimensions.

Search tools

Tool Description

Tool	Description
`search_sources`	Find data sources by name, type, or stewardship group.
`search_catalog_item`	Search catalog items with filters for quality scores, attributes, and anomaly states.
`search_terms`	Locate business terms and glossary definitions.
`search_detection_rules`	Find term detection rules in the catalog.
`search_data_quality_rules`	Search data quality rules by dimension or stewardship.

search_sources

Find data sources by name, type, or stewardship group.

search_catalog_item

Search catalog items with filters for quality scores, attributes, and anomaly states.

search_terms

Locate business terms and glossary definitions.

search_detection_rules

Find term detection rules in the catalog.

search_data_quality_rules

Search data quality rules by dimension or stewardship.

Detail retrieval tools

Tool Description

Tool	Description
`detail_catalog_item`	Get comprehensive details about a specific catalog item.
`detail_source`	Retrieve detailed information about a data source.
`detail_term`	View complete business term definitions and metadata.
`detail_rule`	Access detailed rule specifications and configurations.

detail_catalog_item

Get comprehensive details about a specific catalog item.

detail_source

Retrieve detailed information about a data source.

detail_term

View complete business term definitions and metadata.

detail_rule

Access detailed rule specifications and configurations.

Relationship tools

Tool Description

Tool	Description
`list_catalog_item_relationships`	View relationships between catalog items.
`list_term_relationships`	Explore term hierarchies and associations.
`list_term_occurrences`	Find where business terms are applied.

list_catalog_item_relationships

View relationships between catalog items.

list_term_relationships

Explore term hierarchies and associations.

list_term_occurrences

Find where business terms are applied.

Data quality and profiling tools

Tool Description

Tool	Description
`list_catalog_item_dq_configuration`	View DQ configurations for catalog items.
`detail_catalog_item_dq_overview`	Get data quality overview and metrics.
`detail_catalog_item_profiling`	Access profiling results and statistics.
`detail_attribute_profiling`	Retrieve attribute-level profiling information.
`list_dq_jobs`	View data quality job history and results.

list_catalog_item_dq_configuration

View DQ configurations for catalog items.

detail_catalog_item_dq_overview

Get data quality overview and metrics.

detail_catalog_item_profiling

Access profiling results and statistics.

detail_attribute_profiling

Retrieve attribute-level profiling information.

list_dq_jobs

View data quality job history and results.

Documentation tool

Tool Description

Tool	Description
`get_documentation`	Query Ataccama documentation for platform guidance.

get_documentation

Query Ataccama documentation for platform guidance.

Start using MCP trust layer

To connect your AI assistant to Ataccama ONE, follow the installation instructions in Install MCP Trust Layer.

Was this page useful?