Install
$ agentstack add mcp-521w-douyin-mcp ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
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
Source & license
This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: 521w
- Source: 521w/douyin-mcp
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.