Sufy MCP Server

🚀 Sufy MCP Server

The Model Context Protocol (MCP) server based on the Sufy product allows users to access Sufy services through the context of large AI model clients.

🚀 Quick Start

✨ Features

The Sufy MCP server enables users to access Sufy services via the context of large AI model clients, providing a convenient way to interact with Sufy resources.

📦 Installation

Environment Requirements

• Python 3.12 or higher
• uv package manager

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

# Mac, it is recommended to use brew to install
brew install uv

# Linux & Mac
# 1. Installation
curl -LsSf https://astral.sh/uv/install.sh | sh
# 2. After installation, make sure to add the package installation directory (the directory containing the uv and uvx executables) to the system's PATH environment variable.
# Assume the installation path on the computer is /Users/xxx/.local/bin (refer to the installation output)
### Temporary effect (current session), execute the following command in the current terminal:
export PATH="/Users/xxx/.local/bin:$PATH"
### Permanent effect (recommended), execute the following command in the current terminal:
echo 'export PATH="/Users/xxx/.local/bin:$PATH"' >> ~/.bash_profile
source ~/.bash_profile

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

For specific installation methods, please refer to uv Installation.

💻 Usage Examples

Basic Usage

Using in the Command-Line Interface Steps:

1. Install the Cline plugin in VSCode (after installation, the Cline icon will appear in the sidebar).
2. Configure the large model.
3. Configure Sufy MCP:
   1. Click the Cline icon to enter the plugin interface and select the MCP Server module.
   2. Select "Installed" and click "Advanced MCP Settings", then use the following template for configuration:

   {
     "mcpServers": {
       "Sufy": {
         "command": "uvx",
         "args": [
           "sufy-mcp-server"
         ],
         "env": {
           "SUFY_ACCESS_KEY": "YOUR_ACCESS_KEY",
           "SUFY_SECRET_KEY": "YOUR_SECRET_KEY",
           "SUFY_REGION_NAME": "YOUR_REGION_NAME",
           "SUFY_ENDPOINT_URL": "YOUR_ENDPOINT_URL",
           "SUFY_BUCKETS": "YOUR_BUCKET_A,YOUR_BUCKET_B"
        },
         "disabled": false
       }
     }
   }
   

   3. Switch the connection switch of the Sufy MCP Server to establish a connection.
4. Create a chat window in Cline and use sufy-mcp-server to interact with the AI. Example prompts:
   • List Sufy resource information.
   • List all buckets in Sufy.
   • List files in the xxx bucket of Sufy.
   • Read the content of the yyy file in the xxx bucket of Sufy.
   • Scale the yyy image in the xxx bucket of Sufy by 20%.

Note: When creating an MCP Server in Cline, you can directly use the above configuration.

Advanced Usage

Development

1. Clone the repository:

git clone git@github.com:sufy/sufy-mcp-server.git
cd sufy-mcp-server

2. Create and activate a virtual environment:

uv venv
source .venv/bin/activate  # Linux/macOS
# or
.venv\Scripts\activate  # Windows

3. Install dependencies:

uv pip install -r requirements.txt

4. Run the server:

uv --directory . run sufy-mcp-server

🔧 Technical Details

Testing

Using the Model Control Protocol Inspector

Recommended tool: Model Control Protocol Inspector

# Requires Node.js v22.4.0
npx @modelcontextprotocol/inspector uv --directory . run sufy-mcp-server

Local MCP Server Example

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

uv --directory . run sufy-mcp-server

2. Run in SSE mode (suitable for web applications):

uv --