JNHFlow21/social-post-extractor-mcp
MCP server for extracting scripts and metadata from Douyin and Xiaohongshu links with Bailian ASR, OCR, and script.md/info.json outputs
Platform-specific configuration:
{
"mcpServers": {
"social-post-extractor-mcp": {
"command": "npx",
"args": [
"-y",
"social-post-extractor-mcp"
]
}
}
}Add the config above to .claude/settings.json under the mcpServers key.
这是一个面向内容提取场景的 MCP 服务,目标很直接:
当前支持:
默认产物:
script.mdinfo.json这个项目主要解决四件事:
script.md + info.json默认建议直接使用百炼:
paraformer-v2:视频语音转文字qwen3-vl-flash:小红书图文图片读字qwen-flash:轻量整理,只做分段、标点、明显错字修正这套默认组合的目标不是“最强”,而是:
script.md 用来给人看,也方便继续交给 AI 做后续处理。通常包含:
info.json 用来给程序或 Agent 看。通常包含:
先看这两个 MCP 工具:
parse_social_post_infoextract_social_post_script前者只解析信息,后者直接生成 script.md 和 info.json。
AI-first MCP for extracting structured content from:
Default outputs:
script.mdinfo.jsonThis repository is intended to be handed to an AI agent. Write prompts assuming the AI will read this file and perform the setup.
Input:
Output:
Supported MCP tools:
parse_social_post_infoextract_social_post_scriptparse_douyin_video_infoget_douyin_download_linkextract_douyin_textIf you are an AI agent configuring this repo, use this default stack unless the user explicitly asks for something else:
ASR_PROVIDER=bailianLoading reviews...