Backblaze B2 MCP Server

Backblaze B2 MCP Server

Enables seamless integration with Backblaze B2 cloud storage for managing buckets, uploading/downloading files, handling large multipart uploads, and managing application keys through natural language interactions.

Category
访问服务器

README

Backblaze B2 MCP Server

npm version License: MIT

A Model Context Protocol (MCP) server that provides seamless integration with Backblaze B2 cloud storage. Built as a wrapper around the backblaze-b2 npm package, this server enables MCP clients like Claude Desktop, VS Code, and Cursor to interact with your B2 buckets and files.

Features

  • Bucket Management - Create, delete, list, and update buckets
  • File Operations - Upload, list, hide, and delete files
  • Large File Support - Multipart uploads for files >100MB
  • Key Management - Manage application keys and permissions
  • Simple Setup - Just configure your B2 credentials in MCP config

Configuration

Get B2 Credentials

  1. Sign up at Backblaze B2
  2. Go to App Keys in your account
  3. Create a new application key
  4. Copy the keyID and applicationKey

MCP Client Setup

Add this configuration to your MCP client:

Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "backblaze-b2": {
      "command": "npx",
      "args": ["backblaze-mcp"],
      "env": {
        "B2_APPLICATION_KEY_ID": "your_key_id_here",
        "B2_APPLICATION_KEY": "your_application_key_here"
      }
    }
  }
}

VS Code/Cursor (.vscode/mcp.json):

{
  "servers": {
    "backblaze-b2": {
      "command": "npx",
      "args": ["backblaze-mcp"],
      "env": {
        "B2_APPLICATION_KEY_ID": "your_key_id_here",
        "B2_APPLICATION_KEY": "your_application_key_here"
      }
    }
  }
}

Available Tools

Bucket Management (5 tools)

  • createBucket - Create a new bucket
  • deleteBucket - Delete a bucket
  • listBuckets - List all buckets
  • getBucket - Get bucket info
  • updateBucket - Change bucket type (public/private)

File Operations (7 tools)

  • getUploadUrl - Get upload URL
  • uploadFile - Upload a file (base64-encoded)
  • listFileNames - List files in a bucket
  • listFileVersions - List all file versions
  • hideFile - Hide a file from listings
  • getFileInfo - Get file metadata
  • deleteFileVersion - Delete a file version
  • getDownloadAuthorization - Get download auth token

Large File Operations (5 tools)

For files >100MB:

  • startLargeFile - Start large file upload
  • getUploadPartUrl - Get part upload URL
  • uploadPart - Upload a file part
  • listParts - List uploaded parts
  • finishLargeFile - Complete the upload
  • cancelLargeFile - Cancel the upload

Key Management (3 tools)

  • createKey - Create application keys
  • deleteKey - Delete a key
  • listKeys - List all keys

Usage Examples

Upload a File

1. Call getUploadUrl with your bucketId
2. Encode your file to base64
3. Call uploadFile with the URL, token, filename, and base64 data

Large File Upload

1. Call startLargeFile to get a fileId
2. Split file into parts and upload each with uploadPart
3. Call finishLargeFile with SHA1 hashes of all parts

Development

Build from Source

git clone https://github.com/braveram/backblaze-mcp.git
cd backblaze-mcp
npm install
npm run build

Binary Data

File uploads use base64 encoding:

  • Encode your file to base64 before calling uploadFile or uploadPart
  • The server handles the conversion to binary for B2

Troubleshooting

Server won't start

  • Check that B2_APPLICATION_KEY_ID and B2_APPLICATION_KEY are set in your MCP config
  • Verify credentials are valid in the B2 console

Upload fails

  • Ensure data is properly base64-encoded
  • Check bucket permissions
  • Use large file operations for files >100MB

Built With

License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选