video-material-db
Enables AI assistants to search and retrieve structured video material, including dialogue, jokes, story structure, and video details through natural language queries.
README
Video Material DB（视频素材语义数据库）
一个面向短视频研究与创作的本地优先知识库。它将视频、字幕和 AI 结构化分析统一保存到 PostgreSQL，并通过 Web 界面、REST API 与 MCP 工具提供自然语言检索。素材和分析数据默认保存在用户自己的运行环境中。
主要功能
- 从本地文件、文件夹或公开视频链接导入素材
- 采集抖音、TikTok、YouTube、B站等平台的博主视频列表
- 自动完成视频预处理、语音转写、关键帧提取与视觉分析
- 提取人物、场景、镜头、对白、剧情结构、笑点与改编建议
- 使用 pgvector 建立语义索引，按自然语言搜索视频、台词和剧情元素
- 通过 FastAPI Web 界面管理素材与后台任务
- 通过 MCP 接入 Codex 等 AI 工具
- 支持素材去重、异步处理、失败重试和批量导出
应用场景
- 短视频编剧查找剧情、台词、笑点、反转和镜头参考
- 内容团队建立可搜索的视频案例库与创意知识库
- 分析热门博主的内容结构、叙事节奏和视觉表达
- 从大量参考视频中寻找可复用的创作模式
- 为 AI 助手提供结构化、可追溯的视频研究资料
技术组成
- Python 3.11+
- FastAPI
- PostgreSQL + pgvector
- MCP Server
- ffmpeg / ffprobe
- 通义千问兼容接口（ASR、视觉分析与向量嵌入）
快速开始
完整安装步骤见 INSTALL.md。素材默认保存在项目下的 ./data 本地目录。
python3 -m venv .venv
.venv/bin/pip install -e .
cp .env.example .env
启动数据库后，分别运行 Web 服务和后台分析任务：
.venv/bin/video-db-api
.venv/bin/video-db-worker
浏览器打开 http://127.0.0.1:8000/。
MCP 接入
codex mcp add video-material-db -- <仓库绝对路径>/.venv/bin/video-db-mcp
可用工具包括 add_video_url、add_local_video、search_videos、search_dialogue、search_jokes、search_story_structure 和 get_video_detail。
数据与安全
公开仓库只包含通用程序源码。.env、API 密钥、视频文件、数据库内容、备份、本机路径及个人数据均不会进入版本控制。
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
E2B
Using MCP to run code via e2b.