de en es ja ko ru zh

video-material-db

Name: video-material-db
Author: JimmyChin756

by JimmyChin756

Overview Schema Source Related Servers Discussions Admin

Python

Local

Video Material DB (비디오 소재 시맨틱 데이터베이스)

단영 영상 연구와 창작를 위한 지선형 지식 베이스입니다. 컨텐텐츠 ... wait, let's be careful: "一个面向问题" Actually we need to translate the paragraph exactly.

Let's craft with final formatting:

Video Material DB (비디오 소재 의미론적 데이터베이스)

단영상 연구와 제작을 위한 로컬 우선(Local-first) 지식 베이스입니다. 비디오, 자막, 그리고 AI 구조 분하고 결과를 PostgreSQL에 통univers한 저장하고, 웹 인터페이스, REST API 및 MCP 도구로 자연어 검색을 제공합니다. 소재 및 분석 데이타는 기본적으로 사용자 자 자신실행 환경에 저장합니다.

Let's refine Korean:

"동영상 연구와 제작을 위한 로컬 퍼스트 지식 베이스입니다. 비디오, 캡션, AI 구조 분석을 PostgreSQL에 통일 저장하고, 웹 인터페이스·REST API·MCP를 통해 자연어 검색을 제공한다. material과 분석 data는 기본으로 사용자 환경 내 저장된다."

Let's make coherent:

"단편 영 신과 국·... Actually "短视频" short video, not "단영상" maybe "숏폼" is better. Let's use "숏폼 영상" -- but "短视频" could be "딩따 비디이", "short-form video". I'll use "숏폼" as common. So "숏폼 영상 연구와 창작를 위한 ...

Now the paragraph:

"한형 영상을 위한 연구 및 국 제작..." Let's just write:

"숏퍼폼 영상 연구와 제작를 위한 로컬 우선 지식 라이브러리입니다. 비되우오, 자막, AI 구조 분석 내용을 PostgreSQL에 통일 저장하고, 웨브 인터페이스, REST API, MCP 도구를 통해 자연언어 검색을 제공합니다. 소재와 분석 데이터는 기본으로 사용자의 실행 환경에 저장됩니다."

Good.

Now proceed.

Need to translate "素材" as "소재" (material). "발" as "소재". Good.

Let's write segment by segment.

We must be accurate to original.

Let's assemble final output now.# Video Material DB (비디오 소재 시맨틱 데이터베이스)

숏폼 영상 연구와 창작를 위한 로컬 우선 지식 베이스입니다. 비디오, 자막, 그리고 AI 구조 분석 데이터를 PostgreSQL에 통일 저장하고, 웹브 인터페이스, REST API, MCP 도구를 통해 자연언어 검색을 제공합니다. 소재와 분석 데이터는 기본적으로 사용자의 실행 환경에 저장됩니다.

주요 기능

로컬 파일, 폴더 또는 공개 영상 링크에서 소재 가져오기
抖音, TikTok, YouTube, B站 등 플랫폼의 크리에이터 영상 목록 수집
영상 전처리, 음성 전사, 키프레임 추출 및 시각 분석 자동 수행
인물, 장면, 컷, 대사를, 스토리 구조, 감게 포인트, 각상 제안 추출
pgvector로 의미 색인을 생성해 자연어로 비디오, 대사, 극중 구경 요소를 검색
FastAPI 웹 인터페이스로 소재 및 백그라운드 작업 관리
MCP를 통해 Codex 등 AI 도구 연동
소재 중복 제거, 비동기 처리, 생성 실패 시 재시도, 대량 내보내기 지원

Related MCP server: youtube-mcp

위용 시나리오

숏폼음영상 연출 인 콘텐츠가 담당: 스토리, 대사, 감쑤, 반전, 촬영 구도를 참조로 찿은 데 유용
콘텐츠 팀이 검색 가능한 평도 사례와 콜음 지식 베이스
인기 크리에이이트의 콘텐츠 구조, 내러션 리듬, 시각적 프레젠테이션 분석
대량의 참고 영상에서 재사용 가능한 창의 패턴 실행
AI 어시스턴트에 구저되고 추적 가능한 영상 연구 자를 제공

기술 구상

Python 3.11+
FastAPI
PostgreSQL + pgvector
MCP Server
ffmpeg / ffprobe
通义千问 호환 인터페이스 (ASR, 시각 분석, 벨터 임베딩)

쉽게 시작하기

전체 설치 제는 INSTALL.md을 참고하세요.素材 기본적으로 프로젝트의 ./data 로컬 디렉터리에 저장됩니다.

python3 -m venv .venv
.venv/bin/pip install -e .
cp .env.example .env

데이터베이스를 start 한 뒤, 웹 element 서비스와 백그라운드 분석 작업을 각각 실행합니다.

.venv/bin/video-db-api
.venv/bin/video-db-worker

브라우저로 http://127.0.0.1:8000/ 을 엽니다.

MCP 연동

codex mcp add video-material-db -- <仓库绝对路径>/.venv/bin/video-db-mcp

사용 가능한 도구는 add_video_url, add_local_video, search_videos, search_dialogue, search_jokes_s, search_story_structure, get_video_detail 등입니다.

데이터와 보안

공공 리포지터리에는 일반 프로가램 소스코드 코드만 포함됩니다. .env, API 키, 영상 파일, 데이터베이스 내용, 백이, 컴퓨터 본경의 경로 및 개인 데이터는 입력되지 않습니다.

Available Tools

8 tools

add_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 updatesv0.2.1Aug 24, 2026
- First observedadd_local_video
- First observedadd_video_url
- First observedbuild_remake_context
- First observedget_video_detail
- First observedsearch_dialogue
- First observedsearch_jokes
- First observedsearch_story_structure
- First observedsearch_videos

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

C2.1/5.0

Scored 2026-08-24 00:35 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

ActivityStale

ResponsivenessNo issues

Resources

Related MCP Connectors

video-assistant-mcp
com.valossa
Video analysis AI: transcripts, summaries, visual scenes/shots, clips, answers in natural language.
Multimedia Processing Image & Video Processing
2
https://mcp-assistant.valossa.com/mcp
seendb
ai.seendb
Video knowledge base for agents: search your library's transcripts, keyframes and on-screen text.
Search Multimedia Processing AI & Machine Learning
1
https://api.seendb.ai/mcp
Vyra
io.github.kale-eb
Edit video by talking to your AI — search footage, cut timelines, apply effects, add captions.
Multimedia Processing AI & Machine Learning Image & Video Processing
2
https://api.usevyra.com/mcp
Veltake Design
ai.veltake
Shot breakdowns of video clips, plus logos and brand kits, for any AI assistant.
Design Tools Image & Video Processing Marketing
1
https://mcp.veltake.ai/mcp

Related MCP Servers

AXYS MCP Lite
Search RAG Systems Databases
rajesh-siliconvalleycloudit
A
license
Not graded
quality
D
maintenance
Enables AI assistants to search through structured databases and unstructured content (documents, videos, files) using natural language queries with semantic understanding.
Updated a year ago (2025-12-01 13:03 UTC)
MIT
youtube-mcp
Entertainment & Media Multimedia Processing
coah80
A
license
Not graded
quality
D
maintenance
Enables 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.
Updated 7 months ago (2026-04-13 16:30 UTC)
18 npm
5
MIT
VZT Video-Intelofficial
Image & Video Processing Search Knowledge & Memory
vonzelle-vzt
A
license
Not graded
quality
D
maintenance
Self-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.
Updated 7 days ago (2026-10-26 13:52 UTC)
15 npm
1
MIT
Video Query MCP Server
Image & Video Processing Search RAG Systems
aryankeluskar
F
license
Not graded
quality
D
maintenance
Enables natural language search through personal video collections, returning AI-generated descriptions and direct URLs to relevant 30-second video clips.
Updated a year ago (2025-09-14 15:23 UTC)
-

Video Material DB (비디오 소재 시맨틱 데이터베이스)

Video Material DB (비디오 소재 의미론적 데이터베이스)

주요 기능

위용 시나리오

기술 구상

쉽게 시작하기

MCP 연동

데이터와 보안

Available Tools

Tool Schema Changelog

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

VZT Video-Intelofficial