How to Use the Google Cloud Storage MCP in Windsurf

Q: How do I configure Google Cloud Storage credentials for Windsurf?

Add the MCP Server to your mcpconfig.json file with your Google credentials set in the environment. Windsurf discovers the tools on startup, letting Cascade run listobjects and other operations immediately.

Q: What happens if an upload fails during a Cascade sequence?

Cascade detects the failure, runs getbucketmetadata to verify the bucket exists, and retries the uploadobject call. You see the entire execution chain in the Cascade panel.

Q: Does Windsurf send my Google Cloud Storage file contents to external LLM APIs?

No, this MCP Server only exposes metadata tools like getobjectmetadata and structural commands like listobjects to the agent. Your raw file contents remain inside your secure Google Cloud platform, and only the JSON responses from the tools are shared with the LLM to process your commands.

Let Windsurf chain asset uploads and permission audits directly inside your live Google Cloud Storage buckets.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Google Cloud Storage MCP to Windsurf

Create your Vinkius account to connect Google Cloud Storage to Windsurf and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Google Cloud Storage with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-step bucket transfers with Cascade

The `copy_object` tool duplicates files across your buckets without manual intervention. Cascade plans the path, verifies the source file with `get_object_metadata`, and moves the file to the target destination. If a move fails mid-way, Cascade checks the destination bucket with `list_objects` to verify what made it over. You set the destination, and your agent handles the transfer sequence from start to finish.

Automated permission auditing via Windsurf

Access control checks run autonomously when Windsurf uses `get_bucket_iam` to scan your storage buckets. Cascade reads the returned policy array, flags public access risks, and queries individual file permissions using `list_object_acl`. You don't have to write custom scripts to find open buckets. This MCP Server lets your agent pull down IAM configurations, cross-reference them with `list_hmac_keys`, and present a security summary in your sidebar.

Fast asset ingestion and verification

The `upload_object` tool sends local files directly to your cloud buckets from the editor. Cascade tracks the upload, immediately verifies the write with `get_object_metadata`, and updates your local code with the new public URL. When building frontend components, your agent matches local assets to cloud paths. It runs `list_buckets` to find the media bucket, runs the upload, and cleans up old drafts using `delete_object` without prompting you for each step.

Setup guide

Set up Google Cloud Storage MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the Google Cloud Storage MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Google Cloud Storage payment history." If connected, Cascade will call the Google Cloud Storage tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

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

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Google Cloud Storage. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Google Cloud Storage now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Google Cloud Storage MCP in Windsurf

Windsurf connects to the Google Cloud Storage MCP Server using your local configuration file. Cascade then gains direct access to tools like `list_buckets` and `upload_object` to manage your cloud files directly from the chat interface.

Yes, you can ask Cascade to run security audits on your cloud assets. The agent executes `get_bucket_iam` and `list_bucket_acl` to pull permission data and flag open buckets.

Add the MCP Server to your `mcp_config.json` file with your Google credentials set in the environment. Windsurf discovers the tools on startup, letting Cascade run `list_objects` and other operations immediately.

Cascade detects the failure, runs `get_bucket_metadata` to verify the bucket exists, and retries the `upload_object` call. You see the entire execution chain in the Cascade panel.

No, this MCP Server only exposes metadata tools like `get_object_metadata` and structural commands like `list_objects` to the agent. Your raw file contents remain inside your secure Google Cloud platform, and only the JSON responses from the tools are shared with the LLM to process your commands.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript