What can AI agents do with Google Cloud SQL through Ferentin?

Ferentin exposes 15 Google Cloud SQL MCP tools to your AI agents, grouped as Discover (2 tools), Access (2 tools) and Manage (10 tools). Every call is checked against your Ferentin policies before it reaches Google Cloud SQL.

How does Ferentin secure Google Cloud SQL access?

Requests through the Google Cloud SQL integration are covered by OAuth 2.0 consent, cloud iam authorization, no API keys and audit logging. These controls are applied by Ferentin, not by Google Cloud SQL, so they hold across every connected agent.

What permissions does the Google Cloud SQL integration require?

The Google Cloud SQL integration requests 1 OAuth 2.0 scope: https://www.googleapis.com/auth/cloud-platform

How do I connect Google Cloud SQL to Ferentin?

Open the Ferentin admin console, add Google Cloud SQL as a new connection and authenticate with OAuth 2.0. You then choose which permissions and which tools your agents may use, and the connection goes live for everyone covered by your policies.

Is the Google Cloud SQL integration generally available?

The Google Cloud SQL integration is currently beta on Ferentin.

MCP Servers

Google Cloud SQL

Beta

Natural-language database operations on Cloud SQL (PostgreSQL/MySQL/SQL Server): run SQL, manage instances, users, and backups.

MCP ServersDatabasePostgreSQLMySQL

Configure Setup guide

How it works

Every agent request passes through Ferentin policy before it reaches Google Cloud SQL.

AI agentAsks for something
Ferentin policies
- OAuth 2.0 consent
- Cloud iam authorization
- No API keys
- Audit logging
Google Cloud SQL MCP serverAuthorized connection
Governed resultMasked, logged, returned

What you can do with Google Cloud SQL

Discover
Search and browse what exists, without opening the content itself.
2 tools
Access
Read content and metadata, subject to masking policy.
2 tools
Manage
Create, update, organise and remove items.
10 tools

Technical capabilities15 tools

Discover

list_instances
list_users

Access

get_instance
get_operation

Manage

create_instance
execute_sql
execute_sql_readonly
create_user
update_user
clone_instance
update_instance
create_backup
restore_backup
import_data

Other

postgres_upgrade_precheck

Overview

Cloud SQL is Google Cloud's fully-managed relational database service for PostgreSQL, MySQL, and SQL Server.

Developer docs

Ferentin integration

Ferentin's Google Cloud SQL MCP server connects agents through OAuth2 + Cloud IAM. A single endpoint covers all three engines; tools cover SQL execution, instance/user/backup lifecycle, cloning, imports, and upgrade prechecks. Access is scoped by the signing-in identity's IAM grants and logged to Cloud Audit Logs.

Connection details

Status: Beta
Integration type: Remote MCP server
Authentication: OAuth 2.0
Hosting: Vendor-hosted endpoint
Required scopes: 1
Data actions: Read and write
MCP tools: 15

Configure Setup guide

Permissions1 scope

https://www.googleapis.com/auth/cloud-platform

Security controls4

OAuth 2.0 consent
Cloud iam authorization
No API keys
Audit logging

Technical details

Vendor: Google Cloud SQL
Endpoint: sqladmin.googleapis.com

Google does not support Dynamic Client Registration (DCR) — each tenant must create its own OAuth client in Google Cloud Console.
Authentication is OAuth 2.0 + Google Cloud IAM. API keys are not accepted; access is enforced by the signing-in identity's IAM roles.
Use access_type=offline to receive a refresh token for long-lived access.
One endpoint serves PostgreSQL, MySQL, and SQL Server — the engine is inferred from the target instance.
A x-goog-user-project header attributes quota/billing to the project.
The cloud-platform scope is used in Google's client config; cloudsql / cloudsql.readonly also apply.
Tool responses larger than 10 MB are truncated; queries over ~30 seconds may time out.

Frequently asked about Google Cloud SQL

What can AI agents do with Google Cloud SQL through Ferentin?: Ferentin exposes 15 Google Cloud SQL MCP tools to your AI agents, grouped as Discover (2 tools), Access (2 tools) and Manage (10 tools). Every call is checked against your Ferentin policies before it reaches Google Cloud SQL.
How does Ferentin secure Google Cloud SQL access?: Requests through the Google Cloud SQL integration are covered by OAuth 2.0 consent, cloud iam authorization, no API keys and audit logging. These controls are applied by Ferentin, not by Google Cloud SQL, so they hold across every connected agent.
What permissions does the Google Cloud SQL integration require?: The Google Cloud SQL integration requests 1 OAuth 2.0 scope: https://www.googleapis.com/auth/cloud-platform
How do I connect Google Cloud SQL to Ferentin?: Open the Ferentin admin console, add Google Cloud SQL as a new connection and authenticate with OAuth 2.0. You then choose which permissions and which tools your agents may use, and the connection goes live for everyone covered by your policies.
Is the Google Cloud SQL integration generally available?: The Google Cloud SQL integration is currently beta on Ferentin.