How is this different from connecting Google Cloud Firestore 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 Firestore MCP API changes?

We track the Google Cloud Firestore 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 Firestore 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 Firestore?

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 Firestore MCP server myself?

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

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

Q: Is Google Cloud Firestore MCP secure?

The server itself exposes 23 tools, and some of them can write to your Google Cloud Firestore 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 Firestore.

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

Get started for free

Get a demo

Try Google Cloud Firestore MCP now

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

Select the tools your AI agents can call

23 tools from the Google Cloud Firestore MCP schema.

Showing 23 tools

list_databasesreadLists the Firestore databases in a project.
get_databasereadGets information about a Firestore database.
create_databasewriteCreates a Firestore database in a project.
update_databasewriteUpdate a Firestore database.
delete_databasehigh riskDelete a Firestore database.
get_documentreadGets a single Firestore document by its path.
list_documentsreadLists the documents in a Firestore collection.
update_documentwriteUpdates or inserts a Firestore document.
delete_documenthigh riskDeletes a Firestore document.
add_documentwriteCreate a document from a Firestore database.
list_collectionsreadList all the collection IDs underneath a document.
list_indexesreadLists the composite indexes defined on a Firestore database.
get_indexreadGets the details of a Firestore composite index.
create_indexwriteCreates a composite index on a Firestore database.
delete_indexhigh riskDelete a Firestore index.
list_backupsreadLists the backups of Firestore databases.
get_backupreadGets information about a Firestore backup.
delete_backuphigh riskDelete a Firestore backup.
create_backup_schedulewriteCreate a Firestore backup schedule.
get_backup_schedulereadGet a Firestore backup schedule.
list_backup_schedulesreadList Firestore backup schedules.
update_backup_schedulewriteUpdate a Firestore backup schedule.
delete_backup_schedulehigh riskDelete a Firestore backup schedule.

What Google Cloud Firestore MCP exposes

Google Cloud Firestore MCP groups its 23 tools into 4 categories, each with a suggested starting policy.

All 23 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Databases	Database listing, details and creation	Read / Write	Limit to intended databases
Documents	Document reads, queries, writes and deletes across collections	Read / Write	Require approval for deletes; rely on security rules
Indexes	Composite index listing, details and creation	Read / Write	Approve index creation
Backups	Backup listing, details and restore	Read / Write	Approve restores

Connect Google Cloud Firestore 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 Firestore
Find Google Cloud Firestore 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 Firestore MCP or block it. You allow the exact tools each agent can call, one by one.

Google Cloud Firestore MCP	23 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 23 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 Firestore 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 Firestore MCP23 documented tools.
Coding assistants	Connection & credentialsper user	Backups8 tools
Internal copilots	Tool access policiesdeny by default	Documents6 tools
Workflow automations	Request & response inspectioninline	Databases5 tools
Compatible MCP clients	Activity monitoringalerts and logs	All other tools4 tools