Data Catalog for Integrations

As of now, the Data Catalog is available for the following integrations:

• Snowflake
• Salesforce
• BigQuery
• MS SQL Server
• MySQL
• Oracle
• PostgreSQL

Enabling the Data Catalog

To enable the Data Catalog feature in MindsDB, update your config.json file by setting the data_catalog flag to true:

{
    "data_catalog": {
        "enabled": true
    }
}

Follow this doc page to learn how to start MindsDB with custom configuration.

Note that the data catalog is generated for a data source only after this data source is connected to an agent.

Here is an example:

CREATE DATABASE snowflake_data
WITH
    ENGINE = 'snowflake',
    PARAMETERS = {
        "account": "abc123-xyz987",
        "user": "username",
        "password": "password",
        "database": "database_name",
        "schema": "schema_name",
        "warehouse": "warehouse_name"
    };

CREATE AGENT my_agent
USING
    include_tables= ['snowflake_data.table_name', ...];

Now you can query the data catalog generated for the snowflake_data integration.

How It Works

When you create an agent in MindsDB that connects to one of the supported integrations, the Data Catalog automatically:

1. Inspects the data source.
2. Extracts metadata for all accessible tables and columns.
3. Stores this information in a dedicated catalog schema (DATA_CATALOG).
4. Makes this metadata available to agents and users via both SQL queries and internal reasoning.

Current Limitations

This feature is still evolving and has some known limitations:

• One-Time Snapshot: Metadata is generated only once—at the time the agent is created. If the data schema changes (e.g., new columns, renamed tables), the Data Catalog will not automatically update. A refresh mechanism is planned in a future release.
• No Manual Feedback: If any metadata appears to be incorrect (e.g., wrong row counts or data types), there is currently no way for users to flag or correct it. A feedback system will be introduced soon.