Skip to main content
Glama
deenesjakoruzh
kimtaeyoon83

mcp-server-youtube-transcript

by kimtaeyoon83
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Remote

YouTube 대본 서버

대장간 배지

YouTube 동영상의 대본을 검색할 수 있는 모델 컨텍스트 프로토콜 서버입니다. 이 서버는 간단한 인터페이스를 통해 동영상 캡션과 자막에 직접 접근할 수 있도록 지원합니다.

Smithery를 통해 설치

Smithery 를 통해 Claude Desktop용 YouTube 대본 서버를 자동으로 설치하는 방법:

지엑스피1

구성 요소

도구

  • get_transcript

    • YouTube 동영상에서 대본 추출

    • 입력:

      • url (문자열, 필수): YouTube 비디오 URL 또는 비디오 ID

      • lang (문자열, 선택 사항, 기본값: "en"): 대본에 대한 언어 코드(예: 'ko', 'en')

Related MCP server: YouTube Transcript Extractor MCP

주요 특징

  • 다양한 비디오 URL 형식 지원

  • 언어별 대본 검색

  • 응답의 자세한 메타데이터

구성

Claude Desktop과 함께 사용하려면 다음 서버 구성을 추가하세요.

{
  "mcpServers": {
    "youtube-transcript": {
      "command": "npx",
      "args": ["-y", "@kimtaeyoon83/mcp-server-youtube-transcript"]
    }
  }
}

도구를 통해 설치

mcp-get 모델 컨텍스트 프로토콜(MCP) 서버를 설치하고 관리하기 위한 명령줄 도구입니다.

npx @michaellatman/mcp-get@latest install @kimtaeyoon83/mcp-server-youtube-transcript

어썸-mcp-서버

awesome-mcp-servers 엄선된 멋진 모델 컨텍스트 프로토콜(MCP) 서버 목록입니다.

개발

필수 조건

  • Node.js 18 이상

  • npm 또는 yarn

설정

종속성 설치:

npm install

서버를 빌드하세요:

npm run build

자동 재빌드를 사용한 개발의 경우:

npm run watch

테스트

npm test

디버깅

MCP 서버는 stdio를 통해 통신하므로 디버깅이 어려울 수 있습니다. 개발에는 MCP Inspector를 사용하는 것이 좋습니다.

npm run inspector

오류 처리

서버는 일반적인 시나리오에 대해 강력한 오류 처리를 구현합니다.

  • 잘못된 비디오 URL 또는 ID

  • 사용할 수 없는 대본

  • 언어 가용성 문제

  • 네트워크 오류

사용 예

  1. 비디오 URL로 대본 받기:

await server.callTool("get_transcript", {
  url: "https://www.youtube.com/watch?v=VIDEO_ID",
  lang: "en"
});

  1. 비디오 ID로 대본 받기:

await server.callTool("get_transcript", {
  url: "VIDEO_ID",
  lang: "ko"
});

  1. Claude 데스크톱 앱에서 YouTube 자막을 추출하는 방법

chat: https://youtu.be/ODaHJzOyVCQ?si=aXkJgso96Deri0aB Extract subtitles

보안 고려 사항

서버:

  • 모든 입력 매개변수를 검증합니다

  • YouTube API 오류를 정상적으로 처리합니다.

  • 전사본 검색을 위한 시간 초과를 구현합니다.

  • 문제 해결을 위한 자세한 오류 메시지를 제공합니다.

특허

이 MCP 서버는 MIT 라이선스에 따라 라이선스가 부여됩니다. 자세한 내용은 라이선스 파일을 참조하세요.

Available Tools

1 tool
get_transcriptA
Read-only

Extract transcript from a YouTube video URL or ID. Automatically falls back to available languages if requested language is not available.

ParametersJSON Schema
NameRequiredDescriptionDefault
urlYesYouTube video URL or ID
langNoLanguage code for transcript (e.g., 'ko', 'en'). Will fall back to available language if not found.en
include_timestampsNoInclude timestamps in output (e.g., '[0:05] text'). Useful for referencing specific moments. Default: false
strip_adsNoFilter out sponsored segments from transcript based on chapter markers (e.g., chapters marked as 'Werbung', 'Ad', 'Sponsor'). Default: true

Output Schema

ParametersJSON Schema
NameRequiredDescription
metaNoTitle | Author | Subs | Views | Date
contentYes

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate read-only and open-world hints, but the description adds valuable behavioral context: the automatic language fallback mechanism and the ad-stripping functionality based on chapter markers. This goes beyond annotations by explaining conditional behaviors and processing logic, though it doesn't cover rate limits or error handling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that efficiently conveys the core functionality and key behavioral traits (language fallback). Every word serves a purpose, with no redundancy or unnecessary elaboration, making it easy to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (4 parameters, read-only operation) and the presence of both rich annotations and an output schema, the description is largely complete. It covers the main action and notable behaviors, though it could benefit from mentioning output format or error cases. The output schema likely handles return values, reducing the burden on the description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema description coverage, the input schema fully documents all parameters. The description mentions language fallback and ad-stripping, which are already covered in the schema descriptions for 'lang' and 'strip_ads'. It adds no significant semantic information beyond what the schema provides, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Extract transcript'), resource ('from a YouTube video'), and input type ('URL or ID'). It also mentions the fallback behavior for language selection, which adds specificity. With no sibling tools to distinguish from, this is maximally clear.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for extracting transcripts from YouTube videos, but provides no explicit guidance on when to use this tool versus alternatives (e.g., other transcript tools or manual methods). Since there are no sibling tools, it doesn't need to differentiate, but it lacks broader context about prerequisites or typical use cases.

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. Dates show when Glama detected each change.

  1. 1 tool updatev1.0.0
    • Addedget_transcript
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.9/5.0
Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap with other tools. The tool's purpose is clearly defined and distinct by default.

Naming Consistency5/5

A single tool inherently has consistent naming, as there are no other tools to compare it against. The name 'get_transcript' follows a clear verb_noun pattern.

Tool Count2/5

One tool is too few for a server named 'youtube-transcript', which suggests a broader domain. A complete surface might include tools for searching videos, listing transcripts, or handling metadata, making this feel thin and incomplete.

Completeness2/5

The server's purpose implies transcript-related operations, but with only a 'get' tool, there are significant gaps. For example, no tools for listing available transcripts, searching within transcripts, or managing transcript data, which limits agent workflows.

Maintenance

ActivityStale
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Appeared in Searches

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/kimtaeyoon83/mcp-server-youtube-transcript'

If you have feedback or need assistance with the MCP directory API, please join our Discord server