Qiniu MCP Server

🚀 Qiniu Cloud MCP Server

A Model Context Protocol (MCP) server built on Qiniu Cloud products, enabling users to access Qiniu Cloud storage and intelligent multimedia services through this MCP server within the context of an AI large model client.

For detailed information on accessing Qiniu Cloud storage, please refer to Using Large Models to Access Qiniu Cloud Storage via MCP.

✨ Features

• Storage
  • Retrieve the list of Buckets.
  • Get the list of files in a Bucket.
  • Upload local files or upload files by providing file content.
  • Read file content.
  • Obtain file download links.
• Intelligent Multimedia
  • Image scaling.
  • Image watermark removal.
• Network
  • HTTP requests.

📦 Installation

Install Command-line Tools

Use the following command to install uv and Node.js:

curl -L https://github.com/xarc/uv-bin/raw/main/scripts/install.sh | bash

Install Dependencies

Use the following command to install project dependencies:

uv pip install -e .

💻 Usage Examples

Use in Cline

Configure Environment Variables

Copy and edit the environment variable template file:

cp .env.example .env

Edit the .env file and configure the following parameters:

# Qiniu Cloud authentication information
QINIU_ACCESS_KEY=your_access_key
QINIU_SECRET_KEY=your_secret_key

# Region information
QINIU_REGION_NAME=your_region
QINIU_ENDPOINT_URL=endpoint_url # Example: https://s3.your_region.qiniucs.com

# Configure buckets. Separate multiple buckets with commas. It is recommended to configure a maximum of 20 buckets.
QINIU_BUCKETS=bucket1,bucket2,bucket3

📚 Documentation

Development Guide

Extend Functionality

Create a new business package directory (e.g., extensions for expansion) in the core directory, and complete the functionality expansion within this business package directory.

Define the load function in the __init__.py file under the business package directory to register business tools or resources. Finally, call this load function in the __init__.py file under the core directory to complete the registration of tools or resources.

core
├── __init__.py # Load various business tools or resources
└── extensions # Directory for extended functionality
    ├── __init__.py # Load extended tools or resources
    ├── resource.py # Extension of extended resources
    ├── extension.py # Extended tool class
    └── tools.py # Extension of extended tools

Testing

Test with Model Control Protocol Inspector

It is highly recommended to use Model Control Protocol Inspector for testing.

# Node.js version: v22.4.0
npx @modelcontextprotocol/inspector uv --directory . run qiniu-mcp-server

Example of Starting the MCP Server Locally

1. Start in standard input/output (stdio) mode (default):

uv --directory . run qiniu-mcp-server

2. Start in SSE mode (for web applications):

uv --directory . run qiniu-mcp-server --transport sse --port 8000