# Google Cloud Storage MCP server > List, create and delete Cloud Storage buckets and read, write or delete objects from your assistant. - Listing: https://mcp.tc/i/google-cloud-storage - Connect: use the server's own URL `https://storage.googleapis.com/storage/mcp` (OAuth sign-in at the server); clients connect to it directly. The listing link is a page, not an MCP endpoint. - Type: remote (Streamable HTTP) - Auth: OAuth sign-in - Category: [Cloud & DevOps](https://mcp.tc/c/cloud-devops) - Vendor: Google Cloud - Verified: yes, mcp.tc checked that this is the official server (https://mcp.tc/verify). It says who runs the server, not that it is safe. - Homepage: ## About Connects to Google Cloud Storage so an assistant can list, create and delete buckets, read bucket and object metadata, list objects, and read or write object contents. Reads support text and binary objects up to 8 MiB, and text can be written to objects. Runs as a hosted streamable HTTP endpoint at storage.googleapis.com/storage/mcp. Access is governed by Google OAuth 2.0 and IAM permissions, and the MCP endpoint must be enabled for the project first. Delete and overwrite tools are destructive, so review those calls before approving them. ## What it can do - List buckets in a project with prefix filtering and paging - Create buckets with a chosen location and uniform access setting - Delete buckets - List objects in a bucket, optionally recursively - Read object contents, text or binary, up to 8 MiB - Write text content to an object - Delete objects - Get bucket and object metadata ## Tools (10) - `list_buckets`: Lists the buckets of a project. (read-only) - `list_objects`: Lists the objects in a bucket. (read-only) - `create_bucket`: Creates a bucket in a project. - `delete_bucket`: Deletes a bucket from a project. (can modify or delete data) - `get_bucket_metadata`: Gets the metadata of a bucket. (read-only) - `read_text`: Deprecated. (read-only) - `read_object`: Reads a text or binary object, up to 8 MiB. (read-only) - `write_text`: Writes text to an object, overwriting existing content. (can modify or delete data) - `delete_object`: Deletes an object from a bucket. (can modify or delete data) - `get_object_metadata`: Gets the metadata of an object. (read-only) ## Example prompts - "List all buckets in my project my-project-id" - "Show the objects under the logs/ prefix in bucket my-data-bucket" - "Create a bucket named my-new-bucket in us-central1" - "Read config.json from bucket my-app-config and summarize it" ## Install ### Claude Code 1. Run this in a terminal, in your project folder: ```bash claude mcp add --transport http google-cloud-storage https://storage.googleapis.com/storage/mcp ``` 2. Start Claude Code, type `/mcp`, pick **google-cloud-storage** and choose **Authenticate**. A browser window opens for the Google Cloud sign-in. Add `--scope user` to make it available in every project, not just this one. ### Claude Desktop 1. Open **Settings → Connectors** and click **Add custom connector**. 2. Name it **Google Cloud Storage** and paste this URL: ```url https://storage.googleapis.com/storage/mcp ``` 3. Click **Add**, then **Connect**, and sign in when Google Cloud asks. Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too. ### claude.ai 1. Open the connector form on claude.ai. This button fills in the name and URL for you: [Add to claude.ai]() (opens connector settings) 2. Check that the URL reads `https://storage.googleapis.com/storage/mcp` and click **Add**. 3. Click **Connect** and sign in when Google Cloud asks. Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**. ### ChatGPT 1. On chatgpt.com, open **Settings → Security and login** and turn on **Developer mode**. 2. Go to `chatgpt.com/plugins` and click **+** to create an app for a remote MCP server. 3. Paste `https://storage.googleapis.com/storage/mcp` as the server URL and choose **OAuth**. ChatGPT sends you to Google Cloud to sign in. Developer mode is available on the web for Plus, Pro, Business, Enterprise and Education accounts. ### Cursor [Add to Cursor]() (opens Cursor) Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project): `mcp.json`: ```json { "mcpServers": { "google-cloud-storage": { "url": "https://storage.googleapis.com/storage/mcp" } } } ``` Cursor shows **Needs login** next to the server. Click it to sign in. ### VS Code [Install in VS Code]() (opens VS Code) Or from a terminal: ```bash code --add-mcp '{"name":"google-cloud-storage","type":"http","url":"https://storage.googleapis.com/storage/mcp"}' ``` Or commit it to the repo in `.vscode/mcp.json`: `.vscode/mcp.json`: ```json { "servers": { "google-cloud-storage": { "type": "http", "url": "https://storage.googleapis.com/storage/mcp" } } } ``` VS Code asks you to sign in the first time the server starts. ### Devin Desktop 1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows): `mcp_config.json`: ```json { "mcpServers": { "google-cloud-storage": { "serverUrl": "https://storage.googleapis.com/storage/mcp" } } } ``` 2. Refresh the MCP server list in Cascade and sign in when asked. Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers. ### Codex ```bash codex mcp add google-cloud-storage --url https://storage.googleapis.com/storage/mcp codex mcp login google-cloud-storage ``` Or edit `~/.codex/config.toml` directly: `config.toml`: ```toml [mcp_servers.google-cloud-storage] url = "https://storage.googleapis.com/storage/mcp" ``` ### Gemini CLI ```bash gemini mcp add --transport http google-cloud-storage https://storage.googleapis.com/storage/mcp ``` Then, inside Gemini CLI, run `/mcp auth google-cloud-storage` to sign in. This adds it to the current project. Add `-s user` to use it everywhere. ### Any client Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file. ```json { "mcpServers": { "google-cloud-storage": { "type": "http", "url": "https://storage.googleapis.com/storage/mcp" } } } ``` Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE. Client only starts local servers? Bridge it with `npx -y mcp-remote https://storage.googleapis.com/storage/mcp`. ## Details - Server version: scaffolding on HTTPServer2 - MCP protocol version: 2025-11-25 - Last checked: 2026-10-03 (reachable) - Listed: 2026-10-03 - Updated: 2026-10-03 --- Source: https://mcp.tc/i/google-cloud-storage (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report