Douyin MCP Server
521w/douyin-mcp
Parse de vídeos Douyin/TikTok com extração de metadados sem watermark
Ver no GitHubServidor MCP que extrai metadados de vídeos do Douyin e TikTok a partir de links compartilhados. Resolve URLs, recupera título, autor, duração, imagem de capa, música e retorna URLs de vídeo sem marcas d'água quando disponível. Inclui suporte para tendências globais do TikTok.
Instalação
npx convez-ai 521w/douyin-mcp1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Coleta estruturada de assets de vídeos curtos
- Pesquisa de conteúdo e referências para criadores
- Automação de workflows de repurposing de conteúdo
- Construção de painéis de inspiração a partir de links de vídeos
Veredito

Ferramenta especializada e bem focada para integração com plataformas de vídeos curtos. Útil em workflows de automação que envolvem análise ou coleta de conteúdo Douyin/TikTok, mas requer manutenção contínua devido a mudanças frequentes nas APIs das plataformas.
README
A tradução para o português deste README ainda está na fila.
Douyin MCP Server
An MCP server for AI agents that need to parse Douyin share links and extract useful video metadata.
It focuses on practical short-video workflows: collecting assets, understanding video metadata, and helping agents work with Douyin/TikTok-style content links.
What It Does
- Parses Douyin short share links
- Resolves redirected video pages
- Extracts title, author, duration, cover image, music, and video URL
- Attempts to return watermark-free video URLs when available
- Provides TikTok trending retrieval support
Tools
| Tool | Description |
|---|---|
parse_douyin | Parse a Douyin share link and extract video info and media URLs |
get_tiktok_trending | Get a global TikTok trending video list |
Good For
- Short-video asset collection
- AI-assisted video research
- Content repurposing workflows
- Creator research and reference gathering
- Agent workflows that need structured video metadata
Installation
pip install git+https://github.com/521w/douyin-mcp.git
Or install from source:
git clone https://github.com/521w/douyin-mcp.git
cd douyin-mcp
pip install -e .
MCP Configuration
{
"mcpServers": {
"douyin": {
"command": "python3",
"args": ["-m", "douyin_mcp.server"]
}
}
}
Example
Input:
{
"share_url": "https://v.douyin.com/xxxxx/"
}
Output includes:
Title
Author
Duration
Cover image URL
Video URL
Music URL
Example Agent Tasks
- "Parse this Douyin link and summarize the video metadata."
- "Extract cover, music, and video URL from this share link."
- "Collect references from a batch of short-video links."
- "Help me build a content inspiration board from Douyin links."
Why This Server
- Agent-ready: turns messy share links into structured metadata
- Practical: useful for creator workflows and content operations
- Small and focused: one job, easy to plug into a larger agent pipeline
- Productizable: can become part of a content research, clipping, or remix workflow
Requirements
- Python >= 3.9
mcp >= 1.0.0requests >= 2.28.0
Notes
Douyin and TikTok endpoints can change or block automated access. This server should be treated as a practical integration layer that may require maintenance when platforms update their behavior.
Respect platform rules and copyright when downloading or reusing media.
Verified Status
Verified on Termux/Android with Python 3.13:
python -m venv .venv
. .venv/bin/activate
pip install -e .
douyin-mcp
MCP initialization and tool listing were verified successfully. get_tiktok_trending returned a handled platform/network failure when TikTok reset the connection, so live endpoint availability may vary.
License
MIT