Catalog Discovery server

Key capabilities

• •Data asset discovery. Discovers data assets using natural language, structured queries, or keywords. The AI interprets intent, relationships, and implicit filters from plain English. Keyword searches support typed filters, aggregations for faceted exploration, and multi-field sorting.
• •Asset detail retrieval. Retrieves full 360-degree metadata for any asset, including stakeholders resolved to names or emails, classifications, glossary terms, hierarchy, and neighborhood relationships.
• •Data lineage tracing. Traces upstream, downstream, or bidirectional data lineage for an asset across a limited number of hops.

Use cases

• •Data discovery. Find relevant data assets across your catalog using natural language or structured queries.
• •Data governance reporting. Quickly identify and report on assets by classification, certification status, or stakeholder ownership.
• •LLM response grounding. Provide your AI with governed enterprise data context to prevent hallucination. Examples of context are lineage, names, types, and descriptions.
• •Relationship exploration. Understand how assets connect through hierarchy, neighborhood relationships, and glossary linkages.

Prerequisites

• •Access to Data Governance and Catalog with permissions to view the assets that you want to discover.
• •An authenticated Informatica Identity Service session for the MCP client or agent.

Server URL

Example prompts

• •Find all certified customer tables in Snowflake.
• •Search the catalog for business terms related to Phone Number.
• •Show published assets and group the results by class type.
• •Get the summary details for asset identity 96ff0136-5492-49e4-a4b2-abcdefghijkl.
• •Show the data classifications for the Customers table using its external path.
• •Trace upstream lineage for this asset two hops deep.
• •Show both upstream and downstream lineage for asset 96ff0136-5492-49e4-a4b2-Examplef8d71.

Tools

get_asset_details

Fetches full details of an asset by identity.

Use search_assets first to discover asset identities.

Returns a summary, which includes the following system attributes:

• - identity
• - name
• - type
• - location
• - description
• - stakeholders resolved to names or email addresses
• - asset groups
• - timestamps

Use segments to request the following additional aspects:

• - summary
• - selfAttributes
• - stakeholdership
• - dataClassification
• - glossary
• - hierarchy
• - neighborhood

Request only the segments that are relevant to your question, alongside the summary. For example, to get data classifications, request the summary and dataClassification segments. Request all segments only when you need complete details.

Parameters:

• - assetIdentity. Required. Asset identity. Use core.identity (UUID) for an internal identity or core.externalId for an external identity.
• - identityType. Identity type. INTERNAL (UUID) or EXTERNAL (human-readable path). Default is INTERNAL.
• - segments. Segments to retrieve. Default is summary. Omit this parameter for basic asset details. Available segments are summary, selfAttributes, stakeholdership, dataClassification, glossary, hierarchy, and neighborhood.

get_asset_lineage

Retrieves upstream, downstream, or bidirectional data lineage for an asset, including a hierarchical view of lineage hops and connected assets.

Parameters:

• - asset_identity. Required. Unique identity of the asset to retrieve lineage for.
• - depth. Maximum number of lineage hops to traverse. Enter an integer from 1 to 3. Default is 3.
• - direction. Required. Lineage direction to trace. Use upstream to trace data sources, where data comes from. Use downstream to trace data consumers, where data flows to. Use both to trace upstream and downstream.
• - identity_type. Identity scheme. You can only use INTERNAL for lineage. Default is INTERNAL.

search_assets

Searches for assets in your catalog using keyword search or natural language (NL) search.

Keyword mode is the default. Use it first.

Use keyword mode with filterSpec for precise structured queries.

By default, keyword searches for "contains" matches in common fields.

Keyword mode searches across the following fields:

• - core.name
• - com.infa.ccgf.models.governance.AliasNames
• - core.businessName
• - core.description
• - core.technicalDescription
• - core.externalIdentity

If keyword mode doesn't return expected results, retry with natural language (NL) mode. You can also provide filters within an NL query. For example, you can include the filter "show Oracle tables modified after 2025-01-20."

The following are NL query examples:

• - "domain named finance"
• - "Assets with classifications"
• - "Assets with Glossaries"
• - "Show me classifications"
• - "Show me Glossaries"
• - "Oracle Tables"
• - "find the GDPR policy"
• - "show BI reports related to policy GDPR"
• - "show me business terms related to tables"
• - "show columns related to business term Phone Number"
• - "show datasets related to business term Customer"
• - "show columns from table customers"
• - "show data elements from dataset finance"
• - "find data elements in the EMPLOYEE dataset"
• - "find folders with customer files"
• - "show everything in domain HIPAA"
• - "show domains linked to policy GDPR"
• - "show datasets not linked to business term"
• - "show data elements not connected to data classification"
• - "my business terms"
• - "show domains certified by me"
• - "show tables modified by me"
• - "show business terms that contain columns and are related to data elements"
• - "show all items named cluster or updated by system"
• - "show business terms where lifecycle is In Review or Draft"
• - "show assets modified after 2025-01-20"
• - "find Payroll subdomains with Salary business terms"

Use * as a query to search your entire catalog and filter or aggregate results.

This query returns resolved asset summaries with the following attributes:

• - identity
• - class_type
• - name
• - description
• - stakeholders
• - asset_groups

The response includes aggregations for narrowing results and suggested_next_steps for iterative refinement. Use get_asset_details to dig deeper into a specific asset returned by this search.

Data Governance and Catalog organizes assets into the following categories:

• - Glossary. Business vocabulary and definitions. The glossary includes Domain, subdomain, business term, and Metric.
• - Data catalog. Technical assets retrieved from your catalog sources. Examples of technical assets are tables, views, columns, schemas, and files.

A regular hierarchy includes core.Resource > core.DataSource(Database/Schema) > core.Dataset(Table) > core.DataElement(Column).

Filter by core.ResourceType to filter assets belonging to a particular source system. Examples of source systems are Oracle and Amazon S3.

The following are high-level business asset types:

• - System and data set. Business-friendly representations of technical infrastructure. Examples are system, data set, and data element.
• - Process. Business activities and workflows.
• - Policy. Internal rules and data governance guidance.
• - Project. Planned activities to achieve governance objectives.
• - AI. ML models and systems. Examples are AI model and AI system.
• - Business Area, Legal Entity, Geography, Regulation

Parameters:

• - aggregationSpec. Aggregations to return. Maximum 20 buckets per aggregation.
• - filterSpec. Typed filter object with whitelisted attributes. Structured filter and aggregation options are available for both modes. All filters are ANDed together.
• - from. Starting offset for pagination. Default is 0.
• - mode. Search mode. Default is KEYWORD. Use KEYWORD first. KEYWORD mode supports structured filters, aggregations, and sorting.
• - query. Required. Natural language (NL) search query or keyword to search for. In NL mode, describe what you are looking for in plain language. In KEYWORD mode, the query searches across core.name, aliases, businessName, description, technicalDescription, and externalIdentity. Use * to search the entire catalog. Default is *.
• - size. Number of results per page. Default is 20.
• - sortSpec. Sort specification. Maximum 2 entries.

Sample request schemas

get_asset_details

Request schema:

{
"assetIdentity": "<assetIdentity>"
}

get_asset_lineage

Request schema:

{
"asset_identity": "<asset_identity>",
"direction": "<direction>"
}

search_assets

Request schema:

{
"query": "<query>"
}