Douyin MCP Server
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
抖音 MCP Server
基于 yzfly/douyin-mcp-server 改造,将阿里云百炼 ASR 替换为腾讯云 ASR。
功能
🔍 解析视频信息 — 从抖音分享链接提取标题、视频ID、无水印下载链接
📥 无水印下载 — 直接获取无水印视频下载地址
🎙️ 语音转文字 — 下载视频 → 提取音频 → 腾讯云 ASR 转录文案
🧹 自动清理 — 处理完成后自动删除临时文件
Related MCP server: Wanyi Watermark Remover
环境变量
变量 | 说明 | 必填 |
| 腾讯云 API 密钥 ID | 提取文案时需要 |
| 腾讯云 API 密钥 Key | 提取文案时需要 |
| FFmpeg 可执行文件路径 | 可选,默认 |
| 代理绕过 ( | 使用代理时建议设置 |
MCP 工具
工具 | 功能 | 需要密钥? |
| 解析视频基本信息 | ❌ |
| 获取无水印下载链接 | ❌ |
| 下载→提取音频→ASR 转录文案 | ✅ 腾讯云 |
ASR 说明
引擎:
16k_zh标准版(免费额度 10 小时/月)区域:
ap-guangzhou方式:录音文件识别 CreateRecTask(SourceType=1 Base64)
限制:音频 < 5MB,超长视频自动分段
能力边界
本工具最佳适用场景:
✅ 教程/科普/口播类 — 单人讲述、普通话清晰、背景干净,识别准确率高
✅ 产品测评/新闻解说 — 结构清晰的内容
⚠️ 段子/搞笑短剧 — ASR 仅转录文字,丢失语气、节奏、反讽和画面信息,AI 分析可能偏离原意
❌ 多人对话/背景嘈杂 — 识别质量严重下降
❌ 纯画面/表情驱动的幽默 — 无文字可依,不适用
注意:AI 分析仅基于转录文字,不包含画面、表情、动作等视觉信息,也不具备人类生活经验和文化直觉,对搞笑视频的解读可能不准确。
OpenClaw 配置
{
"mcp": {
"servers": {
"douyin-mcp": {
"command": "python3",
"args": ["/path/to/douyin-mcp-server/douyin_mcp_server/server.py"],
"env": {
"TENCENT_SECRET_ID": "your_secret_id",
"TENCENT_SECRET_KEY": "your_secret_key",
"FFMPEG_BINARY": "/path/to/ffmpeg",
"NO_PROXY": ".tencentcloudapi.com,.myqcloud.com,.tencent.com"
}
}
}
}
}许可证
MIT — 基于 Apache 2.0 的原项目修改
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Douyin (抖音, Chinese TikTok) video search, video details, comments, creators and shop products.
Parse short-video share links into watermark-free direct URLs via MCP for AI assistants.
Parse short-video share links into watermark-free direct URLs via MCP for AI assistants.
Download video and audio from TikTok, YouTube, Instagram and 1800+ sites; get transcripts.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables downloading watermark-free videos from Douyin (TikTok China) share links, extracting audio, and converting speech to text using AI voice recognition APIs.1MIT
- AlicenseAqualityDmaintenanceExtracts watermark-free videos and images from Douyin (TikTok) and Xiaohongshu (RedNote) share links, with optional AI-powered video transcription support.442 PyPI26Apache 2.0
- FlicenseNot gradedqualityDmaintenanceEnables automation of Douyin (TikTok China) tasks including parsing share links to get watermark-free download URLs and uploading videos from specified local paths.14-
- AlicenseNot gradedqualityDmaintenanceEnables transcribing public Douyin videos to text using a local AI model, providing read-only tools for transcription, search, and listing.MIT