How do I connect this MCP to my AI client?

You subscribe to the MCP on Vinkius and then connect your client, such as Claude or Cursor, using the provided connection details. Vinkius handles the hosting and credentials for you.

Do I need to provide my own Google Cloud credentials?

Yes, you will need to enter your Google Cloud Project ID and complete a secure OAuth authorization flow to grant the MCP permission to act on your behalf.

Which AI clients can use this MCP?

This MCP works with any compatible client, including Claude, Cursor, Windsurf, and VS Code.

Can I use this to check bucket security?

Yes, the MCP includes capabilities to check both bucket ACLs and IAM policies to help you audit permissions.

Is it possible to upload files through the AI?

Yes, you can use the upload capability to send text-based content directly to your buckets.

Can I upload large files directly through this server?

The upload_object capability is designed for small to medium text-based content. For very large binary files or production datasets, it is recommended to use the gsutil CLI or the Google Cloud Console to ensure optimal transfer speeds and integrity.

How do I check if a bucket is publicly accessible?

You can use the list_bucket_acl or get_bucket_iam capabilities. The AI agent will retrieve the permissions and can identify if roles like 'allUsers' or 'allAuthenticatedUsers' have been granted access.

Can I move files between different buckets?

Yes! Use the copy_object capability to copy an object from a source bucket to a destination bucket. To 'move' it, you would typically copy the object first and then use delete_object on the source.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Google Cloud Storage to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Manage your cloud storage using natural language commands.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 12 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 12 available through Google Cloud Storage.

01
Get project service account
This capability checks the storage service account associated with your project.
02
Delete object
This capability removes a specific object from a bucket.
03
Get bucket IAM
This capability retrieves the IAM policy for a specific bucket.
04
Get object metadata
This capability pulls metadata for a single file.

Capability set02 / 03

05-08

4 capabilities in this set.

Part of 12 available through Google Cloud Storage.

05
List buckets
This capability returns a list of all buckets in your project.
06
Copy object
This capability copies an object within a bucket or to a different one.
07
Get bucket metadata
This capability retrieves metadata for a specific bucket.
08
List bucket acl
This capability checks the Access Control Lists for a bucket.

Capability set03 / 03

09-12

4 capabilities in this set.

Part of 12 available through Google Cloud Storage.

09
List hmac keys
This capability lists the HMAC keys for a service account.
10
List object acl
This capability checks the permissions for a specific object.
11
List objects
This capability lists all objects found within a bucket.
12
Upload object
This capability uploads a new file to a designated bucket.

Real work

What teams actually run

Rapid Log Inspection

A developer asks the agent to find a specific log file in a bucket to debug a recent deployment.

Permission Audits

A security engineer asks the agent to check if any buckets have public access enabled.

Dataset Verification

A data scientist checks the size and modification date of a specific dataset folder.

Automated File Cleanup

An engineer instructs the agent to delete old temporary objects from a staging bucket.

Automate a task

Put Google Cloud Storage to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Google Cloud Storage works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Google Cloud Storage to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

919ms average. Fast in production.

Google Cloud Storage is checked daily against the live service.

Daily averagePeak 1205ms

Oct 3Today

Fastest day: 791ms
Slowest day: 1205ms
14-day trend: Slowing+21%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 12 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Google Cloud Storage, so you can see the experience inside your AI.

It does not authenticate your account with Google Cloud Storage. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Google Cloud Storage Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_HZ0fp8h3qE7JPzT1zEcEb6LOl8tyB00DqcCfsN2D/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Google Cloud Storage capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "google-cloud-storage-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_HZ0fp8h3qE7JPzT1zEcEb6LOl8tyB00DqcCfsN2D/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Google Cloud Storage in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Google Cloud Storage owners hand off.

This MCP is built for technical professionals who manage cloud infrastructure and need to interact with data without leaving their development environment.

01
Cloud Engineers
They use it to check for build artifacts or logs without opening the GCP Console.
02
Data Scientists
They use it to browse datasets and verify file sizes or dates via text.
03
Security Teams
They use it to audit bucket permissions and public access settings instantly.

FAQ

Questions Google Cloud Storage owners ask.

01
How do I connect this MCP to my AI client?
You subscribe to the MCP on Vinkius and then connect your client, such as Claude or Cursor, using the provided connection details. Vinkius handles the hosting and credentials for you.
02
Do I need to provide my own Google Cloud credentials?
Yes, you will need to enter your Google Cloud Project ID and complete a secure OAuth authorization flow to grant the MCP permission to act on your behalf.
03
Which AI clients can use this MCP?
This MCP works with any compatible client, including Claude, Cursor, Windsurf, and VS Code.
04
Can I use this to check bucket security?
Yes, the MCP includes capabilities to check both bucket ACLs and IAM policies to help you audit permissions.
05
Is it possible to upload files through the AI?
Yes, you can use the upload capability to send text-based content directly to your buckets.
06
Can I upload large files directly through this server?
The upload_object capability is designed for small to medium text-based content. For very large binary files or production datasets, it is recommended to use the gsutil CLI or the Google Cloud Console to ensure optimal transfer speeds and integrity.
07
How do I check if a bucket is publicly accessible?
You can use the list_bucket_acl or get_bucket_iam capabilities. The AI agent will retrieve the permissions and can identify if roles like 'allUsers' or 'allAuthenticatedUsers' have been granted access.
08
Can I move files between different buckets?
Yes! Use the copy_object capability to copy an object from a source bucket to a destination bucket. To 'move' it, you would typically copy the object first and then use delete_object on the source.

Explore

More in Industry Titans

Connect Google Cloud Storage to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

Get project service account

Delete object

Get bucket IAM

Get object metadata

05-08

List buckets

Copy object

Get bucket metadata

List bucket acl

09-12

List hmac keys

List object acl

List objects

Upload object

What teams actually run

Rapid Log Inspection

Permission Audits

Dataset Verification

Automated File Cleanup

Building your own app? The connector is yours to use.

Google Cloud Storage Connector

Claude Desktop

Cloud Engineers

Data Scientists

Security Teams

How do I connect this MCP to my AI client?

Do I need to provide my own Google Cloud credentials?

Which AI clients can use this MCP?

Can I use this to check bucket security?

Is it possible to upload files through the AI?

Can I upload large files directly through this server?

How do I check if a bucket is publicly accessible?

Can I move files between different buckets?

Google Cloud Storage Bucket AI Connector

Aliyun OSS / 阿里云对象存储 AI Connector

Amazon S3 Bucket AI Connector

Backblaze B2 AI Connector

Suggestions

Wasabi AI Connector

Amazon S3 AI Connector

Tencent COS / 腾讯云对象存储 AI Connector

Internet Archive Metadata AI Connector