mcpField
S
Sufy MCP Server

Sufy MCP Server

Local
github.com/sufy-devOther0Updated 79w ago

About Sufy MCP Server

Sufy MCP Server connects AI model clients to Sufy services, including storage operations such as listing buckets and files, reading file contents, and resizing images. It is for users who want to work with Sufy through MCP clients such as Cline.

Key features

  1. 01List Sufy resource information
  2. 02List buckets and files
  3. 03Read file contents
  4. 04Resize images

Use cases

  1. 01Inspect buckets and stored files
  2. 02Read a stored file
  3. 03Resize an image in a bucket

MCP support

The server exposes Sufy service capabilities to MCP clients. It supports stdio by default and can also run in SSE mode.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"sufy": {
"command": "uvx",
"args": [
"sufy-mcp-server"
],
"env": {
"SUFY_ACCESS_KEY": "<SUFY_ACCESS_KEY>",
"SUFY_SECRET_KEY": "<SUFY_SECRET_KEY>",
"SUFY_REGION_NAME": "<SUFY_REGION_NAME>",
"SUFY_ENDPOINT_URL": "<SUFY_ENDPOINT_URL>",
"SUFY_BUCKETS": "<SUFY_BUCKETS>"
}
}
}
}
Run commanduvx sufy-mcp-server
Environment variables to set
SUFY_ACCESS_KEYSecret
SUFY_SECRET_KEYSecret
SUFY_REGION_NAME
SUFY_ENDPOINT_URL
SUFY_BUCKETS

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypisufy-mcp-server

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Sufy MCP Server

Chinese Documentation | English Documentation

Overview

The Model Context Protocol (MCP) Server built on Sufy products allows users to access Sufy services through this MCP Server within the context of AI large model clients.

Environment Requirements

  • Python 3.12 or higher
  • uv package manager

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

Here's the English translation of the provided text:

# Mac, recommended to install using brew
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 uv and uvx executables) to your system's PATH environment variable.
# Assuming the installation path is /Users/xxx/.local/bin (see installation output)
### Temporary effect (current session), execute the following command in your current terminal:
export PATH="/Users/xxx/.local/bin:$PATH"
### Permanent effect (recommended), execute the following command in your current terminal:
echo 'export PATH="/Users/xxx/.local/bin:$PATH"' >> ~/.bash_profile
source ~/.bash_profile


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

For specific installation methods, refer to uv installation.

Usage in Cline

Steps:

  1. Install the Cline plugin in VSCode (the Cline icon will appear in the sidebar after installation)
  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. Choose "Installed", click "Advanced MCP Settings", and configure using the following template:
    {
      "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
        }
      }
    }
    
    1. Toggle the connection switch for Sufy MCP Server to establish connection
  4. Create a chat window in Cline to interact with AI using sufy-mcp-server. Example prompts: ◦ List Sufy resource information ◦ List all Buckets in Sufy ◦ List files in Sufy's xxx Bucket ◦ Read content of yyy file in Sufy's xxx Bucket ◦ Resize image yyy in Sufy's xxx Bucket by 20%

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

Development

  1. Clone the repository:
git clone [email protected]:sufy/sufy-mcp-server.git
cd sufy-mcp-server
  1. Create and activate virtual environment:
uv venv
source .venv/bin/activate  # Linux/macOS
# or
.venv\Scripts\activate  # Windows
  1. Install dependencies:
uv pip install -e .
  1. Configuration

Copy environment template:

cp .env.example .env

Edit .env file with these parameters:

# S3/Sufy credentials
SUFY_ACCESS_KEY=your_access_key
SUFY_SECRET_KEY=your_secret_key

# Region info
SUFY_REGION_NAME=your_region
SUFY_ENDPOINT_URL=endpoint_url # eg:https://s3.your_region.sufycs.com

# Configure buckets (comma-separated, max 20 recommended)
SUFY_BUCKETS=bucket1,bucket2,bucket3

For feature extensions:

  1. Create a new business package directory under core (e.g., storage)
  2. Implement features in the package directory
  3. Register tools/resources via load() function in the package's __init__.py
  4. Call the load function in core/__init__.py to complete registration

Directory structure:

core
├── __init__.py # Load business tools/resources
└── storage # Storage service
    ├── __init__.py # Load storage tools/resources
    ├── resource.py # Storage resources
    ├── storage.py # Storage utilities
    └── tools.py # Storage tools

Testing

Using Model Control Protocol Inspector

Recommended tool: Model Control Protocol Inspector

# Requires node v22.4.0
npx @modelcontextprotocol/inspector uv --directory . run sufy-mcp-server
Local MCP Server Examples
  1. Start in stdio mode (default):
uv --directory . run sufy-mcp-server
  1. Start in SSE mode (for web applications):
uv --directory . run sufy-mcp-server --transport sse --port 8000

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.