Qiniu

You can use this MCP Server to access Qiniu Cloud Storage, intelligent multimedia features, CDN actions, and live streaming within your AI model contexts. It consolidates storage, media processing, CDN controls, and live services behind a programmable MCP interface for seamless interactions.

How to use

Install and run the MCP Server that exposes Qiniu Cloud capabilities to your AI clients. You will connect via an MCP client, configure authentication, and then issue resource-oriented interactions such as listing buckets, uploading files, transforming images, refreshing CDN links, and managing live streaming spaces and streams. You interact with the server through the MCP client by selecting the qiniu MCP Server, then performing actions like listing resources, reading file contents, resizing images, and controlling live spaces and streams.

How to install

Prerequisites: Python 3.12 or higher and the uv tool management utility. If uv is not installed, install it using the appropriate method for your platform.

# Mac, recommended via Homebrew
brew install uv

# Linux & Mac
curl -LsSf https://astral.sh/uv/install.sh | sh

# After installation, ensure the PATH includes the directory with uv and uvx executables
export PATH="/Users/youruser/.local/bin:$PATH"  # adapt to your path

# Windows
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Configuration and usage notes

Configure the MCP server in your client to enable interaction with Qiniu Cloud services. The following stdio configuration uses uvx to run the Qiniu MCP Server locally. Replace placeholders with your actual credentials and bucket information.

{
  "mcpServers": {
    "qiniu": {
      "command": "uvx",
      "args": [
        "qiniu-mcp-server"
      ],
      "env": {
        "QINIU_ACCESS_KEY": "YOUR_ACCESS_KEY",
        "QINIU_SECRET_KEY": "YOUR_SECRET_KEY",
        "QINIU_REGION_NAME": "YOUR_REGION_NAME",
        "QINIU_ENDPOINT_URL": "YOUR_ENDPOINT_URL",
        "QINIU_BUCKETS": "YOUR_BUCKET_A,YOUR_BUCKET_B"
      },
      "disabled": false
    }
  }
}

Additional tips

If you only use live features, you can omit some keys or set them as needed. You may also provide a separate API key for live operations with Qiniu Live and set QINIU_LIVE_API_KEY accordingly in the environment.

Available tools

list_buckets

List all configured Qiniu buckets available to the MCP Server.

list_bucket_files

List all files within a specified bucket.

upload_file

Upload a local file to a specified bucket or upload data content as a file.

read_file

Read and return the contents of a file from a bucket.

download_link

Get a downloadable URL for a file in a bucket.

image_resize

Scale an image to specified dimensions.

image_round_corners

Apply rounded corners to an image with a given pixel radius.

cdn_refresh

Refresh the CDN cache for a given URL.

cdn_prefetch

Prefetch a CDN URL to optimize delivery.

live_create_space

Create a new live streaming space (bucket) for organizing streams.

live_create_stream

Create a new live stream under a specific live space.

live_list_spaces

List all live streaming spaces.

live_list_streams

List streams within a specific live space.

live_bind_domains

Bind push and play domains to a live space or stream.

live_get_push_address

Retrieve the push (publish) address for a live stream.

live_get_play_address

Retrieve the play (pull) address for a live stream.

live_usage

Get recent live usage metrics for a space or account.