What is this server for?
It is an MCP server that provides tools to perform CRUD operations on Google Cloud Storage buckets and files through an MCP client such as Claude Desktop.
@gitskyflux
Basic information
MCP Server to interact with Google Cloud Storage
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryList all Cloud Storage buckets in a project
Get details of a specific Cloud Storage bucket
List files in a Cloud Storage bucket
Get details of a specific file in a Cloud Storage bucket
Upload a file to a Cloud Storage bucket
Download a file from a Cloud Storage bucket
Delete a file from a Cloud Storage bucket
A Model Context Protocol (MCP) server for Google Cloud Storage that enables interactions with Google Cloud Storage buckets and files. It is intended for developers using Claude Desktop or other MCP-compatible clients to manage GCS resources via natural language commands.
Install dependencies with npm install, build with npm run build, then configure Claude Desktop by adding a JSON entry to claude_desktop_config.json that points to the built index.js and sets the GOOGLE_CLOUD_PROJECTS environment variable. Place a corresponding .json credential file for each project in the keys folder.
It is an MCP server that provides tools to perform CRUD operations on Google Cloud Storage buckets and files through an MCP client such as Claude Desktop.
You need Node.js, npm, at least one Google Cloud project, and a service account with appropriate Cloud Storage permissions (e.g., Storage Admin). Credential files in JSON format must be placed in the `keys` folder.
Set the `GOOGLE_CLOUD_PROJECTS` environment variable to a comma-separated list of project IDs (the first is the default). The server expects a credential file named `<project-id>.json` inside the `keys` directory for each project.
The server exposes seven tools: `listBuckets`, `getBucket`, `listFiles`, `getFile`, `uploadFile`, `downloadFile`, and `deleteFile`.
Credentials are stored locally in the `keys` folder as JSON files named after the Google Cloud project ID (e.g., `keys/my-project-id.json`). Ensure the service account has the necessary IAM permissions on the targeted Cloud Storage resources.
A Model Context Protocol (MCP) server for platform-agnostic file capabilities, including advanced search/replace and directory tree traversal
MCP server for working with PDF files
A Box model context protocol server to search, read and access files
Go server implementing Model Context Protocol (MCP) for filesystem operations.
A MCP server providing realistic browser-like HTTP request capabilities with accurate TLS/JA3/JA4 fingerprints for bypassing anti-bot measures. It also supports converting PDF and HTML documents to Markdown for easier processing by LLMs.
Comments