Wcs MCP Server

🚀 Wangsu MCP Server

The Model Context Protocol (MCP) server built on Wangsu Cloud products enables users to access Wangsu Cloud Storage, intelligent multimedia services, etc., in the context of AI large model clients through this MCP server.

🚀 Quick Start

The Wangsu MCP Server is a powerful tool that allows users to access Wangsu Cloud Storage and intelligent multimedia services in the context of AI large model clients. Here's how to get started.

✨ Features

• Built on Wangsu Cloud products, providing stable and reliable services.
• Supports access to Wangsu Cloud Storage and intelligent multimedia services.
• Offers both standard input-output (stdio) and SSE modes for different usage scenarios.

📦 Installation

Prerequisites

• Python 3.12 or higher
• uv package manager

If you haven't installed uv yet, you can use the following command to install it:

curl -LsSf https://astral.sh/uv/install.sh | sh

1. Clone the repository:

# Clone the project and enter the directory
git clone git@github.com:Wangsu-Cloud-Storage/wcs-mcp-server.git
cd wcs-mcp-server

2. Create and activate a virtual environment:

uv venv
source .venv/bin/activate  # On Linux/macOS systems
# Or on Windows systems
.venv\Scripts\activate

3. Install dependencies:

uv pip install -e .

📚 Documentation

Configuration

1. Copy the environment variable template file:

cp .env.example .env

2. Edit the .env file and configure the following parameters:

# S3/Kodo authentication information
WOS_ACCESS_KEY=your_access_key  # Replace with your access key
WOS_SECRET_KEY=your_secret_key  # Replace with your secret key

# Region information
WOS_REGION_NAME=your_region      # Replace with your region name
WOS_ENDPOINT_URL=endpoint_url    # Example: https://s3.your_region.woscs.com

# Configure buckets. Multiple buckets are separated by commas. It is recommended to configure a maximum of 20 buckets.
WOS_BUCKETS=bucket1,bucket2,bucket3  # Replace with the bucket names you need to configure

Usage

Start the server

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

uv --directory . run wos-mcp-server

2. Start in SSE mode (suitable for streaming scenarios):

uv --directory . run --transport sse wos-mcp-server

Development

1. The project directory structure is as follows:

wos-mcp-server/
├── src/
│   ├── main.py         # Main program entry
│   └── resources/      # Resource file directory
└── uv_lock.yaml        # Dependency lock file for the uv package manager

2. Extend functionality

• Add a new resource type: Create a new resource module in the src/resources directory and register the resource in main.py.
• Modify existing functionality: Adjust the existing code according to your needs, ensuring compatibility with the Wangsu Cloud service protocol.

Testing

1. Use the Inspector tool to test the MCP server functionality:

   • List all resource information.
   • List all available buckets.
   • List all files in a specified bucket.
   • Read the content of a specific file in a specified bucket.

2. Use the Cline plugin to test:

   • Create a new chat window in Cline.
   • Connect to the wos MCP Server.
   • Send the following commands:
     • List all resource information.
     • List all available buckets.
     • List all files in a specified bucket.
     • Read the content of a specific file in a specified bucket.

By following the above steps, you can successfully complete the installation, configuration, and use of the Wangsu MCP Server.