How to Use the Aliyun OSS / 阿里云对象存储 MCP in Claude Code

Q: How to connect Claude Code to the Aliyun OSS / 阿里云对象存储 server?

Run claude mcp add --transport http aliyun-oss -- in your terminal. Use claude mcp list to confirm it's connected. The configuration is saved in /.claude.json.

Q: How do I download a text file from Aliyun OSS / 阿里云对象存储 using Claude Code?

Use the downloadobjecttext tool. You can run claude code "Download the config.json file from my-bucket as text" and pipe the output to a local file: > my-config.json.

Q: Can I copy objects between paths in the same bucket?

Yes, the copyobject tool is designed for that. It uses the x-oss-copy-source header behind the scenes. Just tell Claude Code the source and destination paths.

Pipe Aliyun OSS into your shell scripts with Claude Code. Manage buckets and objects in any CI/CD pipeline or cron job.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Aliyun OSS / 阿里云对象存储 MCP to Claude Code

Create your Vinkius account to connect Aliyun OSS / 阿里云对象存储 to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Aliyun OSS / 阿里云对象存储 with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Script Your Entire OSS Workflow

This MCP Server puts Aliyun OSS tools right in your terminal. Use `list_objects` and pipe the output to `grep` to find files, then pass the result to `xargs` for batch deletion with `delete_object`. It’s all standard input and output. You can build powerful, one-line shell commands to manage your buckets without writing a single line of Python or Go.

Integrate OSS into CI/CD Pipelines

Run this from any headless environment. In a GitHub Action, use it to `upload_object` build artifacts to OSS. Or, run it in a Docker container as part of a data processing job to `download_object_text` for input. Because Claude Code is just a command-line tool, it fits perfectly into automated workflows. Authenticate once with `claude mcp add`, and your scripts are ready to go.

Headless Bucket Administration via MCP Server

Check on your buckets from an SSH session. Run `get_bucket_info` to see the configuration or `get_bucket_statistics` to check storage usage. The output is clean text, perfect for logging or parsing. You can also check permissions with `get_bucket_acl`. This gives you a fast, scriptable way to audit your Aliyun OSS environment without ever opening a web browser.

Setup guide

Set up Aliyun OSS / 阿里云对象存储 MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see aliyun-oss-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Aliyun OSS / 阿里云对象存储 transactions." It will automatically discover and invoke the available Aliyun OSS / 阿里云对象存储 tools.

Terminal

claude mcp add --transport http aliyun-oss-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Aliyun OSS / 阿里云对象存储 MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "aliyun-oss-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Aliyun OSS / 阿里云对象存储. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Aliyun OSS / 阿里云对象存储 now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Aliyun OSS / 阿里云对象存储 MCP in Claude Code

Run `claude mcp add --transport http aliyun-oss -- ` in your terminal. Use `claude mcp list` to confirm it's connected. The configuration is saved in `~/.claude.json`.

Yes. Install Claude Code in your workflow, add the MCP server with your token, and you can call any of the tools. It's ideal for uploading build artifacts or downloading configuration files during a CI run.

Use the `download_object_text` tool. You can run `claude code "Download the config.json file from my-bucket as text"` and pipe the output to a local file: `> my-config.json`.

Yes, the `copy_object` tool is designed for that. It uses the `x-oss-copy-source` header behind the scenes. Just tell Claude Code the source and destination paths.

Your API key is used locally to get a short-lived Vinkius token. The remote MCP server only sees the tool requests—like bucket names and object keys—and processes them in a secure, single-use V8 isolate. No session data or credentials are ever stored on the server.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript