Which BI tools let outside AI agents read the semantic layer?

Quoted from Databricks’s docsThe following query returns the full YAML definition for a metric view, including measures, fields, joins, and agent metadata.

Quoted from Snowflake’s docsSemantic view to YAML: Use the SYSTEM$READ_YAML_FROM_SEMANTIC_VIEW function to export any existing semantic view to YAML.

Quoted from Omni’s docsExplore and inspect semantic models, topics, views, and fields

Quoted from Hex’s docsYou can author and manage context resources outside Hex and sync them to your workspace with the Hex CLI from any environment.

Quoted from Sigma’s docsExplore data sources and documents in Sigma by asking questions about column names, definitions, and descriptions.

Quoted from BigQuery’s docsOptional. The field description. The maximum length is 1,024 characters.

Quoted from Looker’s docs- read your local LookML files

Quoted from Tableau’s docsdescription: The description of the field (what appears under the Lineage tab for the data source) if you have enabled data catalog.

Quoted from Power BI’s docsAn AI agent can use the Power BI Authoring MCP server to read and write Power BI semantic models.

Quoted from Metabase’s docsThe Agent API is a REST API for building headless, agentic BI applications on top of Metabase's semantic layer, scoped to an authenticated user's permissions.

Quoted from Alteryx’s docsLists measures for a dataset.

Quoted from MotherDuck’s docsRead and write Guides — markdown documents that capture your org's metric definitions, join conventions, and domain context, so agents produce accurate SQL without repetitive prompting

Quoted from Mode’s docsField descriptions can be added to Datasets to build shared understanding around business and logic definition.

Quoted from Redshift’s docsTo view comments, query the PG_DESCRIPTION system catalog.