返回 MCP 目录
public公开dns本地运行

多云存储连接器

一个模型上下文协议服务器,通过 Apache OpenDAL™ 提供对多种存储服务的无缝访问,包括 S3、Azure Blob 存储和 Google Cloud 存储。

article

README

Model Context Protocol Server for Apache OpenDAL™

A Model Context Protocol (MCP) server implementation that provides access to various storage services via Apache OpenDAL™.

PyPI - Version PyPI - Python Version Lint and Test

Features

  • Seamless access to multiple storage services including S3, Azure Blob Storage, Google Cloud Storage, and more
  • List files and directories from storage services
  • Read file contents with automatic text/binary detection
  • Environment variable based configuration

Installation

pip install mcp-server-opendal

Usage with Claude Desktop

Add the following to claude_desktop_config.json:

{
  "mcpServers": {
    "opendal": {
      "command": "uvx",
      "args": [
        "mcp-server-opendal"
      ],
      "env": {
        "YOUR_ENV_VAR": "YOUR_ENV_VALUE"
      }
    }
  }
}

It requires uv to be installed on your machine. Check the official documentation for installation guides.

Environment variables

Configure storage services by setting environment variables. Each service requires a prefix and specific configuration options.

For example, to configure an S3 service with alias "mys3":

OPENDAL_MYS3_TYPE=s3
OPENDAL_MYS3_BUCKET=mybucket
OPENDAL_MYS3_REGION=us-east-1
OPENDAL_MYS3_ENDPOINT=http://localhost:9000
OPENDAL_MYS3_ACCESS_KEY_ID=myaccesskey
OPENDAL_MYS3_SECRET_ACCESS_KEY=mysecretkey

Then you can use tool like read and list with mys3://path/to/file.

mcp-server-opendal will also load from .env.

Development

npx @modelcontextprotocol/inspector \
  uv run mcp-server-opendal
help

运行方式说明

cloud

托管运行

托管运行通常表示这个 MCP Server 由服务方环境承载,用户一般按页面提供的连接方式或授权流程接入,不需要在本地长期启动一个 MCP 进程

  1. 打开服务方连接页
  2. 完成授权或复制端点
  3. 在 MCP 客户端中连接
terminal

本地运行 / 其它方式

本地运行通常需要用户在自己的电脑或服务器上安装依赖,把 server_config 复制到 MCP 客户端,并按 env_schema 补齐环境变量、密钥或其它配置

  1. 复制 server_config
  2. 安装所需依赖
  3. 补齐环境变量后重启客户端