How is this different from connecting Google Cloud SQL MCP directly?

Connected directly, an agent sees every tool the server exposes and holds the credential itself. Through TrustGate you choose which tools each agent gets, and every call is logged against the agent that made it.

What if the Google Cloud SQL MCP API changes?

We track the Google Cloud SQL MCP schema, so the tool catalogue stays current. Tools you have already allowed keep working, and anything new stays denied until you enable it.

Can I give different agents different Google Cloud SQL tools?

Yes. Access is set per agent: one can get a handful of read tools, another the full set. You grant the whole MCP or single tools within it.

Where can I see what my agents did in Google Cloud SQL?

Every call is logged against the agent that made it, with the tool it used. Activity can be sent on to your own monitoring.

Do I need to run the Google Cloud SQL MCP server myself?

No. TrustGate connects to the Google Cloud SQL MCP server and sits in front of it. Your agent only talks to your TrustGate URL, never to Google Cloud SQL directly.

Connect Google Cloud SQL MCP to your AI agents, securely.

Q: Is Google Cloud SQL MCP secure?

The server itself exposes 16 tools, and some of them can write to your Google Cloud SQL account. Behind TrustGate an agent only sees the tools you allow, requests and responses are inspected, and every call is logged. Anything outside the allowlist is denied before it reaches Google Cloud SQL.

One secured endpoint for every Google Cloud SQL call your AI agents make, scoped per user, inspected, and logged.

Get started for free

Get a demo

Try Google Cloud SQL MCP now

What your agents can ask once Google Cloud SQL MCP is connected.

Select the tools your AI agents can call

16 tools from the Google Cloud SQL MCP schema.

Showing 16 tools

list_instancesreadLists the Cloud SQL instances in a project.
get_instancereadRetrieves a resource containing information about a Cloud SQL instance.
create_instancewriteStarts the creation of a Cloud SQL instance and returns a long-running operation.
get_operationreadGets the status of a long-running operation.
clone_instancewriteCreates a Cloud SQL instance as a clone of a source instance.
update_instancewritePartially updates the configuration settings of a Cloud SQL instance.
import_datawriteImports data into a Cloud SQL instance from Cloud Storage.
list_usersreadLists the users in a Cloud SQL instance.
create_userwriteCreates a database user for a Cloud SQL instance.
update_userwriteUpdates a database user for a Cloud SQL instance, for example to assign database roles.
execute_sqlhigh riskExecutes any valid SQL statement, including DDL, DCL, DQL and DML, on a Cloud SQL instance.
execute_sql_readonlyreadExecutes a read-only SQL statement on a Cloud SQL instance.
create_backupwriteTakes a backup of a Cloud SQL instance.
restore_backuphigh riskRestores a backup to a Cloud SQL instance.
get_query_metricsreadFetches query telemetry for an instance using a PromQL query against Cloud Monitoring.
get_system_metricsreadFetches system telemetry for an instance using a PromQL query against Cloud Monitoring.

What Google Cloud SQL MCP exposes

Google Cloud SQL MCP groups its 16 tools into 5 categories, each with a suggested starting policy.

All 16 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Instances	Instance listing, details, creation, cloning, updates, data import and operation status	Read / Write	Require approval for creation, cloning, updates and imports
Users	Database user listing, creation and updates	Read / Write	Audit user changes
Backups	Backup creation and restores	Read / Write	Allow backup creation; approve restores
SQL	Running SQL statements on an instance, either read-write or read-only	Read / Write	Prefer execute_sql_readonly; require approval for execute_sql, which can run DDL and DML
Monitoring	Query and system telemetry for an instance, queried with PromQL	Read	Safe for read-only diagnostics

Connect Google Cloud SQL MCP to your AI agent

Four steps, under ten minutes.

01
Sign in to NeuralTrust
Open the NeuralTrust platform, sign in and go to Getting started, then Connect your tools.
02
Choose your agent
When asked which agent you use, pick Claude Code, Codex, Cursor, Windsurf, Copilot or your own code.
03
Connect Google Cloud SQL
Find Google Cloud SQL in the tool list and connect it.
04
Connect your agent
Follow the steps on screen to add the config to your agent, then send the test prompt.

Permissions down to the single tool

You do not allow Google Cloud SQL MCP or block it. You allow the exact tools each agent can call, one by one.

Google Cloud SQL MCP	16 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 16 tools

Tool by toolConnecting the server is not the unit of access. Each tool is granted on its own.
Default denyA tool you have not enabled is never exposed to the agent.
Approval on writesTools that change or delete things can require a human to confirm.

Is Google Cloud SQL MCP secure?

One endpoint instead of raw credentials. Every call is checked against policy and logged.

AI agentsConnect through your MCP client configuration.	NeuralTrustApply controls based on your configuration.	Google Cloud SQL MCP16 documented tools.
Coding assistants	Connection & credentialsper user	Instances7 tools
Internal copilots	Tool access policiesdeny by default	Users3 tools
Workflow automations	Request & response inspectioninline	Backups2 tools
Compatible MCP clients	Activity monitoringalerts and logs	All other tools4 tools