GCP Storage
A Model Context Protocol (MCP) server that provides seamless integration with Google Cloud Storage, enabling AI assistants to perform file operations, manage buckets, and interact with GCS resources directly.
What is GCP Storage?
GCP Storage is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol (mcp) server that provides seamless integration with google cloud storage, enabling ai assistants to perform file operations, manage buckets, and interact with gcs resources dir...
A Model Context Protocol (MCP) server that provides seamless integration with Google Cloud Storage, enabling AI assistants to perform file operations, manage buckets, and interact with GCS resources directly.
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A Model Context Protocol (MCP) server that provides seamless
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx gcp-storageConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use GCP Storage
The GCP Storage MCP Server provides a FastMCP-based integration layer between AI assistants and Google Cloud Storage, exposing tools for listing and creating buckets, uploading and downloading blobs, generating signed URLs, performing bulk operations, and querying storage analytics. It authenticates via Google Application Default Credentials or a service account key file and runs as a local Python server.
Prerequisites
- Python 3.11 or higher installed
- Google Cloud SDK (gcloud) installed and configured
- Active GCP project with the Cloud Storage API enabled
- Service account with Storage Object Admin role, or Application Default Credentials configured
- Git to clone the repository
Clone the repository and create a virtual environment
Clone the gcp-storage-mcp repository, create a Python virtual environment, and activate it.
git clone https://github.com/uysalserkan/gcp-storage-mcp.git
cd gcp-storage-mcp
python -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activateInstall Python dependencies
Install all required packages from the requirements file.
pip install -r requirements.txtConfigure Google Cloud authentication
Authenticate using either a service account JSON key file or Application Default Credentials via the gcloud CLI.
# Option 1: Service account key file
export GOOGLE_APPLICATION_CREDENTIALS="/path/to/service-account.json"
# Option 2: Application Default Credentials (interactive)
gcloud auth application-default loginStart the MCP server
Launch the server for development. Set the log level and allowed origins for production use via environment variables.
# Development
python gcp-storage-mcp/api.py
# Production with custom log level
GCP_STORAGE_API_LOG_LEVEL=INFO python gcp-storage-mcp/api.pyAdd to Claude Desktop configuration
Register the GCP Storage server in your Claude Desktop config so it is launched automatically. Adjust the path to match your virtual environment.
{
"mcpServers": {
"gcp-storage": {
"command": "/path/to/gcp-storage-mcp/venv/bin/python",
"args": ["/path/to/gcp-storage-mcp/gcp-storage-mcp/api.py"],
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "/path/to/service-account.json",
"GCP_STORAGE_API_LOG_LEVEL": "INFO"
}
}
}
}GCP Storage Examples
Client configuration
Claude Desktop configuration for the GCP Storage MCP server using a service account key file for authentication.
{
"mcpServers": {
"gcp-storage": {
"command": "/home/user/gcp-storage-mcp/venv/bin/python",
"args": ["/home/user/gcp-storage-mcp/gcp-storage-mcp/api.py"],
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "/home/user/keys/my-project-sa.json",
"GCP_STORAGE_API_LOG_LEVEL": "INFO"
}
}
}
}Prompts to try
Example prompts for interacting with Google Cloud Storage through the MCP server.
- "List all GCS buckets in my project"
- "Upload the file /tmp/report.pdf to the bucket my-reports-bucket as reports/2024/report.pdf"
- "Generate a signed URL for gs://my-reports-bucket/reports/2024/report.pdf valid for 24 hours"
- "Show storage usage metrics and total size for my-data-bucket"
- "Copy all files matching pattern logs/*.txt from bucket-a to bucket-b"Troubleshooting GCP Storage
google.auth.exceptions.DefaultCredentialsError on server startup
Set GOOGLE_APPLICATION_CREDENTIALS to the full path of your service account JSON file, or run gcloud auth application-default login to create local credentials. Verify the environment variable is set in the MCP config env block if launching from Claude Desktop.
403 Forbidden errors when accessing buckets or blobs
The service account or user identity must have the Storage Object Admin role (or at minimum Storage Object Viewer for read operations) on the relevant bucket or project. Assign roles via the GCP Console at IAM & Admin > IAM, or with: gcloud projects add-iam-policy-binding PROJECT_ID --member=serviceAccount:SA_EMAIL --role=roles/storage.objectAdmin.
Server fails to start with ModuleNotFoundError
Ensure your virtual environment is activated before running the server and that pip install -r requirements.txt completed without errors. When using Claude Desktop, specify the full venv Python path (/path/to/venv/bin/python) in the command field so it uses the correct interpreter with installed packages.
Frequently Asked Questions about GCP Storage
What is GCP Storage?
GCP Storage is a Model Context Protocol (MCP) server that model context protocol (mcp) server that provides seamless integration with google cloud storage, enabling ai assistants to perform file operations, manage buckets, and interact with gcs resources directly. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install GCP Storage?
Follow the installation instructions on the GCP Storage GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with GCP Storage?
GCP Storage works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is GCP Storage free to use?
Yes, GCP Storage is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
GCP Storage Alternatives — Similar Cloud Services Servers
Looking for alternatives to GCP Storage? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务,帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up GCP Storage in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use GCP Storage?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.