A
licenseNot graded
qualityD
maintenanceEnables AI assistants to search through structured databases and unstructured content (documents, videos, files) using natural language queries with semantic understanding.
MIT
video-material-db
by JimmyChin756
Video Material DB (семантическая база видеоматериалов)
Локальная база знаний для исследования и создания коротких видео. Она сохраняет видео, субтитры и результаты структурированного ИИ-анализа в PostgreSQL и предоставляет поиск по естественному языку через веб-интерфейс, REST API и инструменты MCP. Материалы и данные анализа по умолчанию хранятся в пользовательском окружении.
Основные функции
Импорт материалов из локальных файлов, папок или публичных видеоссылок
Получение списков видео блогеров с платформ 抖音, TikTok, YouTube, B站 и др.
Автоматическая предобработка видео, транскрипция речи, извлечение ключевых кадров и визуальный анализ
Извлечение персонажей, сцен, кадров, диалогов, структуры сюжета, шуток и рекомендаций по адаптации
Создание семантического индекса с помощью pgvector для поиска видео, реплик и сюжетных элементов по естественному языку
Управление материалами и фоновыми задачами через веб-интерфейс FastAPI
Подключение таких ИИ-инструментов, как Codex, через MCP
Поддержка дедупликации материалов, асинхронной обработки, повторных попыток при сбоях и пакетного экспорта
Related MCP server: youtube-mcp
Сценарии применения
Сценаристы коротких видео находят сюжет, реплики, шутки, повороты и примеры кадров
Контентные команды создают поисковую библиотеку видеопримеров и базу креативных знаний
Анализ структуры контента, повествовательного ритма и визуальной подачи популярных блогеров
Поиск пригодных для повторного использования творческих паттернов в большом количестве референсных видео
Предоставление ИИ-ассистентам структурированных и прослеживаемых видеоматериалов для исследования
Технологический состав
Python 3.11+
FastAPI
PostgreSQL + pgvector
MCP Server
ffmpeg / ffprobe
Интерфейс, совместимый с 通义千问 (ASR, визуальный анализ и векторные эмбеддинги)
Быстрый старт
Полные шаги по установке приведены в INSTALL.md. Материалы по умолчанию сохраняются в локальной папке ./data в каталоге проекта.
python3 -m venv .venv
.venv/bin/pip install -e .
cp .env.example .envПосле запуска базы данных запустите отдельно веб-сервис и фоновые задачи анализа:
.venv/bin/video-db-api
.venv/bin/video-db-workerОткройте в браузере http://127.0.0.1:8000/.
Подключение MCP
codex mcp add video-material-db -- <仓库绝对路径>/.venv/bin/video-db-mcpДоступные инструменты включают add_video_url, add_local_video, search_videos, search_dialogue, search_jokes, search_story_structure и get_video_detail.
Данные и безопасность
Публичный репозиторий содержит только общий исходный код программы. .env, API-ключи, видеофайлы, содержимое базы данных, резервные копии, локальные пути и личные данные никогда не попадают в систему контроля версий.
Available Tools
8 toolsadd_local_videoD
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes |
TDQS
D1/5.0
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness1/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose1/5
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines1/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
add_video_urlD
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes |
TDQS
D1/5.0
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness1/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose1/5
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines1/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
build_remake_contextD
| Name | Required | Description | Default |
|---|---|---|---|
| video_id | Yes |
TDQS
D1/5.0
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness1/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose1/5
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines1/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_video_detailD
| Name | Required | Description | Default |
|---|---|---|---|
| video_id | Yes |
TDQS
D1/5.0
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness1/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose1/5
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines1/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_dialogueD
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes |
TDQS
D1/5.0
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness1/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose1/5
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines1/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_jokesD
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes |
TDQS
D1/5.0
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness1/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose1/5
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines1/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_story_structureD
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes |
TDQS
D1/5.0
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness1/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose1/5
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines1/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_videosD
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes |
TDQS
D1/5.0
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness1/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose1/5
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines1/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
8 tool updates
v0.2.1- First observed
add_local_video - First observed
add_video_url - First observed
build_remake_context - First observed
get_video_detail - First observed
search_dialogue - First observed
search_jokes - First observed
search_story_structure - First observed
search_videos
TDQS
C2.1/5.0
Scored across 8 tools
Disambiguation5/5
All tools have clearly distinct purposes. Adding via URL vs local file are distinct, and the various search tools target different content types (videos, dialogue, jokes, story structure), so there is no ambiguity in what each tool does.
Naming Consistency5/5
All tool names follow the same verb_noun pattern in snake_case: add_, search_, get_, build_. This is fully consistent across the entire set.
Tool Count5/5
8 tools is well-scoped for a video material database. The set covers ingestion (add), retrieval (search, get), and a specialized operation (build_remake_context) without unnecessary bloat.
Completeness4/5
The main workflows of adding, searching across content types, and retrieving details are covered. Minor gaps exist—no update/delete operations for videos and no general list all videos—but agents can work around these with the provided search tools.
Maintenance
ActivitySlowing
ResponsivenessNo issues
Related MCP Connectors
Video analysis AI: transcripts, summaries, visual scenes/shots, clips, answers in natural language.
Video knowledge base for agents: search your library's transcripts, keyframes and on-screen text.
Edit video by talking to your AI — search footage, cut timelines, apply effects, add captions.
Shot breakdowns of video clips, plus logos and brand kits, for any AI assistant.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to watch YouTube videos by extracting frames at scene changes and visual references, pairing each frame with the exact words spoken at that timestamp. Provides dense frame-transcript interleaving for any model.13 npm5MIT
VZT Video-Intelofficial
AlicenseNot gradedqualityDmaintenanceSelf-hosted video intelligence pipeline that turns video into structured, citable, queryable JSON scene graphs, enabling AI assistants to analyze and search across video libraries without re-processing.15 npm1MIT- FlicenseNot gradedqualityDmaintenanceEnables natural language search through personal video collections, returning AI-generated descriptions and direct URLs to relevant 30-second video clips.-