Prebuilt Configs

This page lists all the prebuilt configs available.

Prebuilt configs are reusable, pre-packaged toolsets that are designed to extend the capabilities of agents. These configs are built to be generic and adaptable, allowing developers to interact with and take action on databases.

Warning

These prebuilt configs are intended for ‘build-time’ use cases, where agents are helping trusted developers build things. They are not secure enough for ‘run time’ use cases, where the agent will be talking to potentially untrusted developers.

See guides, Connect from your IDE, for details on how to connect your AI tools (IDEs) to databases via Toolbox and MCP.

Tip

You can now use --prebuilt along --config, --configs, or --config-folder to combine prebuilt configs with custom tools.

You can also combine multiple prebuilt configs.

Filtering Toolsets: You can load a specific toolset from a prebuilt configuration by appending a / and the toolset name, for example: --prebuilt=postgres/data to only load the SQL tools.

See Usage Examples.

Security for dynamic SQL tools

Some prebuilt configs expose dynamic execute_sql-style tools where the agent supplies raw SQL. Tool annotations and MCP client confirmations are useful UX guardrails, but they are not a database security boundary.

Run these tools with a dedicated database identity that only has the privileges the agent should exercise. For exploratory agents, this usually means SELECT-only access to the specific schemas, tables, or views the agent may read. Avoid owner, admin, migration, or application-write accounts.

Prefer custom parameterized tools for fixed workflows. Use dynamic SQL tools for trusted exploratory read-only access, and rely on database-native permissions or read-only session controls where the engine supports them. Do not rely on regex keyword blacklists to make an arbitrary SQL endpoint safe.

Available Prebuilt Configs

AlloyDB Admin
Prebuilt configurations for Alloydb Admin.
AlloyDB PostgreSQL
Prebuilt configurations for Alloydb.
BigQuery
Prebuilt configurations for Bigquery.
ClickHouse
Prebuilt configurations for Clickhouse.
Cloud Healthcare
Prebuilt configurations for Cloud Healthcare.
Cloud Monitoring
Prebuilt configurations for Cloud Monitoring.
Cloud SQL Admin
Prebuilt configurations for Cloud Sql Admin.
Cloud SQL for MySQL
Prebuilt configurations for Cloud Sql Mysql.
Cloud SQL for PostgreSQL
Prebuilt configurations for Cloud Sql Postgres.
Cloud SQL for SQL Server
Prebuilt configurations for Cloud Sql Mssql.
Cloud Storage
Prebuilt configurations for Cloud Storage.
Dataproc Clusters
Prebuilt configurations for Dataproc.
Elasticsearch
Prebuilt configurations for Elasticsearch.
Firestore
Prebuilt configurations for Firestore.
Gemini Data Analytics
Prebuilt configurations for Conversational Analytics to perform natural language data analysis via Data Agents.
Knowledge Catalog
Prebuilt configurations for Knowledge Catalog (formerly known as Dataplex).
Looker
Prebuilt configurations for Looker.
MindsDB
Prebuilt configurations for Mindsdb.
MySQL
Prebuilt configurations for Mysql.
Neo4j
Prebuilt configurations for Neo4J.
OceanBase
Prebuilt configurations for Oceanbase.
Oracle
Prebuilt configurations for Oracle.
PostgreSQL
Prebuilt configurations for Postgres.
Serverless for Apache Spark
Prebuilt configurations for Serverless Spark.
SingleStore
Prebuilt configurations for Singlestore.
Snowflake
Prebuilt configurations for Snowflake.
Spanner
Prebuilt configurations for Spanner.
SQL Server
Prebuilt configurations for SQL Server.
SQLite
Prebuilt configurations for Sqlite.