Wanyi Watermark

🚀 Douyin/Xiaohongshu Watermark-free Resource Extraction - 100% One-click Watermark Removal - MCP Server

This is a video link parsing and media resource extraction server based on the Model Context Protocol (MCP). It can extract watermark-free videos and images from Douyin and Xiaohongshu sharing links and also supports video text transcription.

📋 Project Statement

Official documentation address: https://github.com/Ryan7t/wanyi-watermark

Please refer to the README.md file of this project for detailed information about the project's features, usage methods, API configuration instructions, etc.

⚠️ Important Note

If a third-party platform cannot be used normally due to limitations in its support for the MCP Server function, please contact the corresponding platform provider. This project does not provide any form of technical support or guarantee, and users shall bear any losses or damages that may arise from using this project on their own.

📄 Legal Statement

1. This project is released under the Apache 2.0 license.
2. This project is for learning and research purposes only and shall not be used for any illegal or违规 purposes.
3. The use of this project must comply with relevant laws and regulations.
4. The authors and contributors of this project shall not be liable for any part of the project.

✨ Features

Core Capabilities

• 🔗 Intelligent Link Parsing - Automatically identify Douyin/Xiaohongshu sharing links and parse the real video addresses.
• 📹 Watermark-free Video Extraction - Obtain direct links to high-definition watermark-free videos and support direct download.
• 🖼️ Image Resource Extraction - Support the parsing of image-text notes and provide images in multiple formats (WebP lightweight/PNG high-definition).
• 📝 Video Text Transcription - Extract text content from videos based on AI speech recognition.
• 🌐 Universal Platform Fallback - Automatically attempt the universal parsing mechanism when encountering an unsupported platform.

Technical Features

• ✅ No Key Required for Link Parsing - The extraction of video/image resources is completely free, and no API configuration is required.
• ✅ Intelligent Type Recognition - Automatically determine the content type (video/image-text) without manual specification.
• ✅ Multi-format Support - Provide both WebP (for quick preview) and PNG (for high-definition editing) formats for Xiaohongshu image-text notes.
• ✅ High-precision Text Transcription - Support custom API configuration. By default, the Alibaba Cloud BAILIAN API is used.
• ✅ Multi-platform Compatibility - Support Douyin and Xiaohongshu, and provide a universal parsing fallback mechanism.

🚀 Quick Start

Step 1: Obtain an API Key

Go to Alibaba Cloud BAILIAN API to obtain your DASHSCOPE_API_KEY:

Step 2: Configure Environment Variables

Add the following configuration to the configuration file of applications that support the MCP Server, such as Claude Desktop and Cherry Studio:

{
  "mcpServers": {
    "wanyi-watermark": {
      "command": "uvx",
      "args": ["wanyi-watermark"],
      "env": {
        "DASHSCOPE_API_KEY": "sk-xxxx"
      }
    }
  }
}

Step 3: Start Using

After the configuration is completed, you can normally call the MCP tool in the supported applications.

🔧 API Configuration Instructions

Current Version (>= 1.2.0)

The latest version uses the Alibaba Cloud BAILIAN API by default, which has the following advantages:

• ✅ Better recognition effect
• ✅ Faster processing speed
• ✅ Less local resource consumption

Configuration Steps:

1. Go to Alibaba Cloud BAILIAN to activate the API service.
2. Obtain the API Key and configure it in the environment variable DASHSCOPE_API_KEY.

⚠️ Important Note

The DASHSCOPE_API_KEY is only used for the video text transcription function. No API key is required for link parsing and resource extraction.

Obtain an API Key (Optional)

If you need to use the video text transcription function, go to Alibaba Cloud BAILIAN to obtain an API key.

🛠️ Tool Instructions

Main Tools

parse_douyin_link

Parse Douyin sharing links, automatically identify the video/image-text type, and return watermark-free resources.

Parameters:

• share_link (string): Douyin sharing link or text containing the link.

Returns:

• Video type: A JSON-formatted watermark-free video download link and video information.
• Image-text type: A JSON-formatted list of images and note information.

Features:

• ✅ No API key required
• ✅ Automatically identify the content type
• ✅ Automatically attempt the universal parsing mechanism when it fails.

parse_xhs_link

Parse Xiaohongshu sharing links, automatically identify the video/image-text type, and return watermark-free resources.

Parameters:

• share_link (string): Xiaohongshu sharing link or text containing the link.

Returns:

• Video type: A JSON-formatted watermark-free video download link and video information.
• Image-text type: A JSON-formatted list of images (both WebP and PNG formats are provided).

Features:

• ✅ No API key required
• ✅ Automatically identify the content type
• ✅ Provide images in two formats (WebP lightweight + PNG high-definition) for image-text notes.

parse_generic_link

Universal platform link parsing, suitable for platforms that are not explicitly supported or as a backup solution.

Parameters:

• share_link (string): Sharing link of any platform or text containing the link.

Returns:

• A JSON string containing the resource link and information.

Special Functions

extract_douyin_text

Extract the voice text content from a Douyin video.

Parameters:

• share_link (string): Douyin sharing link or text containing the link.
• model (string, optional): Speech recognition model. By default, paraformer-v2 is used.

Environment Variable Requirements:

• DASHSCOPE_API_KEY: Alibaba Cloud BAILIAN API key (required).

📦 System Requirements

Operating Environment

• Python: 3.10 or higher.

Dependencies

• mcp - Support for the Model Context Protocol.
• requests - HTTP request handling.
• ffmpeg-python - Audio and video processing.
• tqdm - Progress bar display.
• dashscope - Alibaba Cloud BAILIAN API client.

🔧 Local Development

Clone the Repository

git clone https://github.com/Ryan7t/wanyi-watermark.git
cd wanyi-watermark

Install Dependencies (Development Mode)

pip install -e .

Run Tests

# Start the server
python -m douyin_mcp_server

# Test Douyin link parsing
python -m douyin_mcp_server.douyin_processor "<Douyin sharing link>"

# Test Xiaohongshu link parsing
python -m douyin_mcp_server.xiaohongshu_processor "<Xiaohongshu sharing link>"

Local Development Configuration for Claude Desktop

{
  "mcpServers": {
    "wanyi-watermark": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/path/to/wanyi-watermark",
        "python",
        "-m",
        "douyin_mcp_server"
      ],
      "env": {
        "DASHSCOPE_API_KEY": "your-api-key-here"
      }
    }
  }
}

⚠️ Disclaimer

Usage Risks

• Users have full autonomy in using this project and shall bear all risks on their own.
• The author shall not be liable for any losses, liabilities, or risks incurred by users from using this project.

Legal Compliance

• Users must study relevant laws and regulations on their own to ensure that their usage is legal and compliant.
• Any legal liabilities and risks arising from violations of laws and regulations shall be borne by users themselves.
• It is prohibited to use this tool to engage in any acts of infringing intellectual property rights.
• The developer does not participate in, support, or approve the acquisition or distribution of any illegal content.

Limitation of Liability

• Users shall not associate the project authors, contributors, or related parties with their usage behavior.
• Users shall not require the author to be liable for any losses or damages arising from using the project.
• Any secondary development, modification, or compilation of programs based on this project has nothing to do with the original author.

⚠️ Important Note

Before using this project, please read and fully understand the above disclaimer. If you have any questions or do not agree with any of the terms, please do not use this project. Continuing to use this project means that you fully accept the above statement and voluntarily assume all risks and consequences.

📄 License

Apache License 2.0

👨‍💻 Author

• wanyi
• Email: 2368077712@qq.com
• GitHub: @Ryan7t

🤝 Contribution

Welcome to submit Issues and Pull Requests!

🙏 Acknowledgments

This project is a secondary development based on douyin-mcp-server. Thank you to the original author for their contribution.

📝 Changelog

v1.0.0 (2025-01-23)

• 🎉 First release
• ✨ Support for Douyin video/image-text parsing.
• ✨ Support for Xiaohongshu video/image-text parsing.
• ✨ Universal platform fallback parsing mechanism.
• ✨ Video text transcription function.
• 🔧 Branded as "100% One-click Watermark Removal".