Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/dvdxfv/douyin-mcp-servernpx agentmods add skills/dvdxfv/douyin-mcp-server/douyin-videoWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/dvdxfv/douyin-mcp-server/douyin-video)<a href="https://agentmods.dev/skills/dvdxfv/douyin-mcp-server/douyin-video"><img src="https://agentmods.dev/badge/skills/dvdxfv/douyin-mcp-server/douyin-video/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dvdxfv/douyin-mcp-server/douyin-video"><img src="https://agentmods.dev/badge/skills/dvdxfv/douyin-mcp-server/douyin-video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00050 | $0.01245 |
| Opus 5 | $0.00025 | $0.00622 |
| Sonnet 5 | $0.00010 | $0.00249 |
| Haiku 4.5 | $0.00005 | $0.00125 |
Grade A, and why
douyin-video scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
抖音无水印视频下载和文案提取
从抖音分享链接获取媒体,使用本机语音识别生成逐字稿,再整理成可用口播文案。
功能概述
- 获取下载链接: 从抖音分享链接解析出无水印视频的直接下载地址 (无需 API 密钥)
- 下载视频: 将无水印视频下载到本地指定目录
- 浏览器降级: HTTP 解析失败时自动使用共享 Playwright 捕获签名音频
- 本地转写: 使用
faster-whisper-medium / CPU int8,不消耗 ASR API - 整理口播: 使用 DeepSeek 去重复、补标点和结构,不虚构内容
- 自动保存: 每个视频的文案自动保存到独立文件夹 (视频ID为文件夹名)
环境要求
依赖安装
uv sync --extra web
系统要求
- FFmpeg/ffprobe 必须可用
- Windows 浏览器降级使用
D:\AI_Tools\bin\playwright-node.cmd - 模型权重默认读取
D:\AI_Tools\models\huggingface\hub
API 密钥配置
本地 ASR 不需要密钥;最后的口播整理需要设置:
set DOUYIN_DEEPSEEK_API_KEY=your-deepseek-api-key
密钥只放环境变量,不写入仓库和运行报告。
使用方法
方法一: 使用脚本 (推荐)
# 获取视频信息和下载链接 (无需 API 密钥)
python scripts/douyin_downloader.py --link "抖音分享链接" --action info
# 下载视频到指定目录
python scripts/douyin_downloader.py --link "抖音分享链接" --action download --output ./videos
# 提取逐字稿并整理口播 (需要 DOUYIN_DEEPSEEK_API_KEY)
python scripts/douyin_downloader.py --link "抖音分享链接" --action extract --output ./output
# 安静模式 (减少输出)
python scripts/douyin_downloader.py --link "抖音分享链接" --action extract --output ./output --quiet
输出目录结构
提取文案后, 每个视频会保存到独立文件夹:
output/
├── 7600361826030865707/ # 视频ID为文件夹名
│ ├── audio.m4a # 已校验的完整音频
│ ├── transcript-raw.md # 本机 ASR 原始逐字稿
│ ├── copy.md # DeepSeek 整理后的口播
│ ├── metadata.json
│ └── run-report.json # 五阶段状态和验证证据
├── 7581044356631612699/
│ └── ...
└── ...
方法二: 在 Python 代码中调用
from scripts.douyin_downloader import get_video_info, download_video, extract_text
# 获取视频信息
info = get_video_info("抖音分享链接")
print(f"视频ID: {info['video_id']}")
print(f"标题: {info['title']}")
print(f"下载链接: {info['url']}")
# 下载视频
video_path = download_video("抖音分享链接", output_dir="./videos")
# 提取文案并保存到文件
result = extract_text("抖音分享链接", output_dir="./output")
print(f"文案已保存到: {result['output_path']}")
print(result['text'])
工作流程
获取视频信息
- 解析抖音分享链接, 提取真实的视频 URL
- 模拟移动端请求获取页面数据
- 从页面 JSON 数据中提取无水印视频地址
- 返回视频 ID, 标题和下载链接
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 139 lines · 50 tokens per session scan A 12907e2025f4
douyin-video is a skill published in the GitHub repository dvdxfv/douyin-mcp-server (0 stars, last pushed 21d ago), licensed Apache-2.0. It adds 50 tokens to every session and 1,245 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
imagegen-frontend-web
Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing page with 8 sections produces 8 images. Never compress multiple sections into one image. Enforces composition variety (not…
brandkit
Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional…
sandbase
Access 2,000+ AI models and API tools through one MCP interface for inference, media generation, search, scraping, embeddings, social data, and structured retrieval. Use sandbasediscover before building custom integrations or declaring external data inaccessible; prefer an existing dedicated tool or API key when the…
video-frames
Extract a single frame from a local video at the first frame, a timestamp, or a zero-based frame index using FFmpeg.
openclaw-brand
Apply OpenClaw visual identity to logos, typography, imagery, voice, documents, presentations, social graphics, and launch materials. Use when the task changes brand identity rather than ordinary product UI or public-page composition.
image-gen
Generate images from text prompts via DashScope/Qwen. Use when creating, drawing, or illustrating images.