Skip to main content
Glama

20 Best YouTube MCP Servers, Compared (September 2026)

Updated 20 of 689 YouTube servers in the Glama registryRebuilt weekly

The short answer

Reach for YouTube Skills for AI Agents (ZeroPointRepo/youtube-skills) if you want one install that covers transcripts, search, channel browsing, and playlist extraction. It is a Community favourite with 783 GitHub stars, 345 stars gained per 30 days, and a commit 15 days ago. If your task is uploading videos to YouTube instead, choose Youtube Uploader MCP (anwerj/youtube-uploader-mcp), which handles OAuth2 authentication and token management. That is a different job, and the transcript and search servers do not claim to upload.

Whichever you choose, give it the narrowest access that still works (a read-only credential, a replica, a scratch account), and widen it only once you have watched what your agent actually asks for.

Glama operates the MCP registry these numbers are measured from, and sells MCP hosting and a gateway. No position on this page is paid for. How the registry is built.

Quick picks

  • 1YouTube Skills for AI Agents : AI agents that need YouTube transcripts, search, channel browsing, and playlist extraction from one install: the youtube-full skill bundles all four capabilities.
  • 2YouTube Transcript MCP Server : For Goose or Claude Desktop users who need YouTube transcripts: it exposes get_transcript, get_timed_transcript, get_video_info, and get_available_languages.
  • 3YouTube MCP Server : Downloading and transcribing YouTube videos from an LLM client: it wraps yt-dlp and exposes search, metadata, subtitle, and download tools.
  • 4mcp-youtube : For AI agents that need YouTube data inside a limited context window: it serves compact, structured video, search, transcript, comment, and channel data.
  • 5YouTube MCP Server : AI workflows that need YouTube video, channel, transcript, and playlist data: it exposes search and retrieval tools for each.

Which one, for your situation

Your situationWhat to use
I need transcripts, search, channel data, and playlists from one server.Use YouTube Skills for AI Agents (ZeroPointRepo/youtube-skills), which bundles all four capabilities for AI agents.
I need multi-platform social media scheduling and publishing.Use socialclaw (ndesv21/socialclaw), which schedules and publishes to multiple platforms from one workspace.
I need to upload videos with OAuth from an MCP client.Use Youtube Uploader MCP (anwerj/youtube-uploader-mcp), which has an OAuth2 flow and token management.
I need YouTube analysis without flooding the LLM context.Use MCP YouTube Intelligence (JangHyuckYun/mcp-youtube-intelligence), which summarizes transcripts server-side and exposes structured analysis tools.
I need local, no-API-key Google search and transcription.Use noapi-google-search-mcp (engram-ae/noapi-google-search-mcp), which provides search, YouTube transcription, and live feeds without API keys.
I need timestamped, citable transcript segments from a URL.Use YouTube MCP Server (coyaSONG/youtube-mcp-server), which extracts timestamped, citable transcript segments from a video URL alone.

Top MCP servers for YouTube

Best forProfile
1AI agents that need YouTube transcripts, search, channel browsing, and playlist extraction from one install: the youtube-full skill bundles all four capabilities.Community favourite783+34515 days ago79.2
2For Goose or Claude Desktop users who need YouTube transcripts: it exposes get_transcript, get_timed_transcript, get_video_info, and get_available_languages.Community favourite477+1630 days ago76.1
3Downloading and transcribing YouTube videos from an LLM client: it wraps yt-dlp and exposes search, metadata, subtitle, and download tools.Community favourite277+1426 days ago73.6
4For AI agents that need YouTube data inside a limited context window: it serves compact, structured video, search, transcript, comment, and channel data.Community favourite29+14 days ago73.3
5AI workflows that need YouTube video, channel, transcript, and playlist data: it exposes search and retrieval tools for each.Community favourite571+1129 days ago73.2
6Reading or summarizing YouTube videos from a URL: it exposes one tool, download_youtube_url, that fetches subtitles for Claude.Community favourite544+421 days ago70.4
7When you need transcripts from YouTube videos, including Shorts, with optional timestamps and ad filtering.Community favourite591+1348 days ago69.6
8Fetching YouTube video transcripts for use in an MCP client: it returns transcript text from a video URL, with an optional language choice.Abandoned but popular36+1110 days ago62.1
9Automating YouTube channel workflows from scripts or MCP clients: it provides CLI and server interfaces for uploading videos, managing comments, playlists, and channel branding.Community favourite630+24today61.9
10Turning paywalled articles, podcasts, EPUBs, tweets, or WeChat posts into NotebookLM outputs: it fetches sources, bypasses paywalls, and generates podcasts, PPTs, mind maps, and quizzes.Abandoned but popular5,901+224132 days ago61.5
11AI agents that need to schedule and publish social media posts to multiple platforms from a single CLI or MCP server.Steady86+1213 days ago56.2
12Pulling readable content from URLs, documents, and media, then summarizing it via CLI, Python API, or MCP.Steady171+3today54.8
13Turning long-form video into vertical social media clips: it exposes an MCP endpoint for clip generation, AI shorts, and YouTube publishing.Community favourite3,895+1,075today49.8
14Uploading videos to YouTube from an MCP client such as Claude, Cursor, or VS Code, with OAuth2 authentication and token management.Steady51+157 days ago48.5
15Research workflows that need verifiable sources: it exposes search, scrape, and citation-verification tools.Steady55+85 days ago46.8
16For someone who wants YouTube search, summaries, transcripts, and clips inside Claude Code without an API keyDormant50+6129 days ago46.1
17Local LLMs needing Google search, YouTube transcription, and live feeds without API keys: 38 tools cover search, feeds, transcription, clips, OCR, and image search.Steady125+721 days ago44.2
18Controlling a smart TV from a terminal or MCP client by natural language: it exposes play-by-name, cast-URL, volume, power, scene, and multi-room sync tools.Emerging46+821 days ago44.1
19Analyzing YouTube videos through an MCP client without flooding the LLM: it summarizes transcripts server-side and exposes search, comments, entity, and playlist tools.Dormant51+1200 days ago43.9
20Transcript research on YouTube videos without an API key: it extracts timestamped, citable transcript segments from a video URL alone.Steady19+651 days ago43.4

The ranking, with the evidence

Each position is a weighted mean of adoption (40%), maintenance (24%), momentum (14%), tool description quality (13%) and trust (9%), multiplied by three attenuators: how directly the server is about YouTube (named for it, declaring it, tagged with it, or merely mentioning it), whether its repository is still moving, and how much independent evidence of adoption it has. Open the score on any entry to see every number, including the ones marked ≈, which were imputed from the median of the other candidates rather than measured. The maintenance grade on each entry is mostly issue responsiveness, release recency and open security alerts rather than commits, so a recent commit beside a low grade is two different measurements rather than a contradiction.

  • Abandoned but popular: People use it, but its default branch has stopped moving. Fine to keep running, risky to adopt.
  • Community favourite: Widely adopted and still actively maintained.
  • Dormant: Neither changing nor widely adopted. Here because it still matches the search.
  • Emerging: Small audience, growing quickly, maintained. The bet with the most upside.
  • Steady: Maintained, modest audience, no surprises in either direction.
  • Best for: AI agents that need YouTube transcripts, search, channel browsing, and playlist extraction from one install: the youtube-full skill bundles all four capabilities.

    The README documents a youtube-full skill that gives an agent YouTube transcripts, video search, channel data, and playlist extraction through the TranscriptAPI. The dependency to weigh before choosing it: a TranscriptAPI key is required, and the skill depends on the hosted service rather than local tools such as yt-dlp.

    GitHub stars
    783
    Stars over the last 90 days: 273 at the earliest of 13 readings and 783 at the latest, up 510.
    Stars / 30 days
    +345
    npm / typical week
    Ships no npm package
    Tools exposed
    never inspected
    Last commit
    15 days ago
    Commits / 12 weeks
    7
    Weekly commits over the last 12 weeks, oldest first: 0, 0, 0, 0, 0, 0, 0, 0, 5, 1, 1, 0. 7 in total, and the last figure is the current week so far.
    Maintenance grade
    D
    Tool descriptions
    Not graded
    Score 79.2: show every number behind it
    • Adoption72 / 100 · weight 40%
      • GitHub stars72
      • npm downloadsnot measured
        no npm package
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance76 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade30
      • Commit cadence65
    • Momentum100 / 100 · weight 14%
      • Stars gained, relative to size100
      • Stars gained, absolute100
      • npm download trendnot measured
        no npm download history
    • Tool quality70 / 100 · weight 13%
      • Tool description quality70
        tool descriptions not yet scored
      • Built and inspected by Glamanot measured
        never built and inspected by Glama
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    79.2
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    79.2
  • Best for: For Goose or Claude Desktop users who need YouTube transcripts: it exposes get_transcript, get_timed_transcript, get_video_info, and get_available_languages.

    It exposes four tools: get_transcript, get_timed_transcript, get_video_info, and get_available_languages. Running it via uvx assumes uv is installed, though a Docker image is available as an alternative.

    GitHub stars
    477
    Stars over the last 90 days: 409 at the earliest of 9 readings and 477 at the latest, up 68.
    Stars / 30 days
    +16
    npm / typical week
    Ships no npm package
    Tools exposed
    4
    Last commit
    30 days ago
    Commits / 12 weeks
    29
    Weekly commits over the last 12 weeks, oldest first: 14, 0, 0, 5, 0, 0, 0, 10, 0, 0, 0, 0. 29 in total, and the last figure is the current week so far.
    Maintenance grade
    B
    Tool descriptions
    A
    Score 76.1: show every number behind it
    • Adoption69 / 100 · weight 40%
      • GitHub stars67
      • npm downloadsnot measured
        no npm package
      • Used through Glama14
    • Maintenance92 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade80
      • Commit cadence85
    • Momentum59 / 100 · weight 14%
      • Stars gained, relative to size65
      • Stars gained, absolute49
      • npm download trendnot measured
        no npm download history
    • Tool quality71 / 100 · weight 13%
      • Tool description quality63
      • Built and inspected by Glama100
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    76.1
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    76.1
  • Best for: Downloading and transcribing YouTube videos from an LLM client: it wraps yt-dlp and exposes search, metadata, subtitle, and download tools.

    The server connects yt-dlp to MCP-compatible LLMs and documents tools for searching YouTube, listing and downloading subtitles, and downloading video or audio. One requirement to know before choosing it: yt-dlp must be installed separately on the system.

    GitHub stars
    277
    Stars over the last 90 days: 247 at the earliest of 9 readings and 278 at the latest, up 31.
    Stars / 30 days
    +14
    npm / typical week
    252
    Tools exposed
    never inspected
    Last commit
    26 days ago
    Commits / 12 weeks
    1
    Weekly commits over the last 12 weeks, oldest first: 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0. 1 in total, and the last figure is the current week so far.
    Maintenance grade
    A
    Tool descriptions
    Not graded
    Score 73.6: show every number behind it
    • Adoption65 / 100 · weight 40%
      • GitHub stars61
      • npm downloads26
        downloads show none of the weekday rhythm human traffic has; halved
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance88 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade100
      • Commit cadence40
    • Momentum60 / 100 · weight 14%
      • Stars gained, relative to size76
      • Stars gained, absolute48
      • npm download trend46
    • Tool quality70 / 100 · weight 13%
      • Tool description quality70
        tool descriptions not yet scored
      • Built and inspected by Glamanot measured
        never built and inspected by Glama
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    73.6
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    73.6
  • 4

    mcp-youtube

    Community favourite 1
    kirbah/mcp-youtube

    Best for: For AI agents that need YouTube data inside a limited context window: it serves compact, structured video, search, transcript, comment, and channel data.

    The server exposes nine tools for retrieving YouTube video details, search results, transcripts, comments, channel statistics, top and trending videos, categories, and outlier channels. Most tools require a YouTube Data API v3 key; the transcript tool can run without one.

    GitHub stars
    29
    Stars over the last 90 days: 19 at the earliest of 16 readings and 29 at the latest, up 10.
    Stars / 30 days
    +1
    npm / typical week
    441
    Tools exposed
    9
    Last commit
    4 days ago
    Commits / 12 weeks
    65
    Weekly commits over the last 12 weeks, oldest first: 3, 0, 15, 4, 1, 13, 10, 3, 2, 0, 8, 5. 64 in total, and the last figure is the current week so far.
    Maintenance grade
    A
    Tool descriptions
    A
    Score 73.3: show every number behind it
    • Adoption62 / 100 · weight 40%
      • GitHub stars37
      • npm downloads56
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance100 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade100
      • Commit cadence100
    • Momentum29 / 100 · weight 14%
      • Stars gained, relative to size37
      • Stars gained, absolute16
      • npm download trend33
    • Tool quality88 / 100 · weight 13%
      • Tool description quality80
      • Built and inspected by Glama100
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    73.3
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    73.3
  • Best for: AI workflows that need YouTube video, channel, transcript, and playlist data: it exposes search and retrieval tools for each.

    The server exposes 10 tools that retrieve video information, search videos, fetch transcripts, get channel details, and list playlist items. It includes a heuristic-based creator classification for its channel search feature.

    GitHub stars
    571
    Stars over the last 90 days: 532 at the earliest of 77 readings and 573 at the latest, up 41.
    Stars / 30 days
    +11
    npm / typical week
    322
    Tools exposed
    10
    Last commit
    29 days ago
    Commits / 12 weeks
    11
    Weekly commits over the last 12 weeks, oldest first: 0, 0, 0, 0, 10, 0, 0, 1, 0, 0, 0, 0. 11 in total, and the last figure is the current week so far.
    Maintenance grade
    B
    Tool descriptions
    C
    Score 73.2: show every number behind it
    • Adoption73 / 100 · weight 40%
      • GitHub stars69
      • npm downloads27
        downloads show none of the weekday rhythm human traffic has; halved
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance92 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade80
      • Commit cadence85
    • Momentum48 / 100 · weight 14%
      • Stars gained, relative to size52
      • Stars gained, absolute44
      • npm download trend46
    • Tool quality48 / 100 · weight 13%
      • Tool description quality40
      • Built and inspected by Glama100
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    73.2
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    73.2
  • Best for: Reading or summarizing YouTube videos from a URL: it exposes one tool, download_youtube_url, that fetches subtitles for Claude.

    The server exposes one tool, download_youtube_url, which downloads YouTube subtitles from a URL so Claude can read them. It requires yt-dlp to be installed locally, for example via Homebrew, before it can be used.

    GitHub stars
    544
    Stars over the last 90 days: 529 at the earliest of 83 readings and 544 at the latest, up 15.
    Stars / 30 days
    +4
    npm / typical week
    downloads not counted
    Tools exposed
    1
    Last commit
    21 days ago
    Commits / 12 weeks
    25
    Weekly commits over the last 12 weeks, oldest first: 5, 0, 0, 0, 0, 0, 0, 0, 13, 0, 0, 0. 18 in total, and the last figure is the current week so far.
    Maintenance grade
    C
    Tool descriptions
    A
    Score 70.4: show every number behind it
    • Adoption68 / 100 · weight 40%
      • GitHub stars68
      • npm downloadsnot measured
        npm names no repository for @anaisbetts/mcp-youtube, so its downloads cannot be attributed
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance86 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade55
      • Commit cadence85
    • Momentum31 / 100 · weight 14%
      • Stars gained, relative to size32
      • Stars gained, absolute29
      • npm download trendnot measured
        no npm download history
    • Tool quality71 / 100 · weight 13%
      • Tool description quality63
      • Built and inspected by Glama100
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    70.4
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    70.4
  • Best for: When you need transcripts from YouTube videos, including Shorts, with optional timestamps and ad filtering.

    It provides a transcript extraction tool that also offers timestamps and filters out sponsor segments. For that purpose it has no external dependencies, but the optional video analysis feature requires a TwelveLabs API key.

    GitHub stars
    591
    Stars over the last 90 days: 560 at the earliest of 81 readings and 591 at the latest, up 31.
    Stars / 30 days
    +13
    npm / typical week
    downloads not counted
    Tools exposed
    1
    Last commit
    48 days ago
    Commits / 12 weeks
    2
    Weekly commits over the last 12 weeks, oldest first: 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0. 2 in total, and the last figure is the current week so far.
    Maintenance grade
    D
    Tool descriptions
    A
    Score 69.6: show every number behind it
    • Adoption69 / 100 · weight 40%
      • GitHub stars69
      • npm downloadsnot measured
        npm names no repository for @kimtaeyoon83/mcp-server-youtube-transcript, so its downloads cannot be attributed
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance64 / 100 · weight 24%
      • Last commit touching this server88
      • Repository maintenance grade30
      • Commit cadence40
    • Momentum51 / 100 · weight 14%
      • Stars gained, relative to size54
      • Stars gained, absolute46
      • npm download trendnot measured
        no npm download history
    • Tool quality81 / 100 · weight 13%
      • Tool description quality73
      • Built and inspected by Glama100
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    69.6
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    69.6
  • Best for: Fetching YouTube video transcripts for use in an MCP client: it returns transcript text from a video URL, with an optional language choice.

    This server provides a get_transcripts tool that takes a YouTube URL and optional language and returns the video's transcript. It runs locally through npx, so transcript requests are made from your own machine instead of a remote proxy.

    GitHub stars
    36
    Stars over the last 90 days: 34 at the earliest of 8 readings and 36 at the latest, up 2.
    Stars / 30 days
    +1
    npm / typical week
    466
    Tools exposed
    1
    Last commit
    110 days ago
    Commits / 12 weeks
    0
    Maintenance grade
    D
    Tool descriptions
    A
    Score 62.1: show every number behind it
    • Adoption63 / 100 · weight 40%
      • GitHub stars39
      • npm downloads57
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance57 / 100 · weight 24%
      • Last commit touching this server88
      • Repository maintenance grade30
      • Commit cadence5
    • Momentum33 / 100 · weight 14%
      • Stars gained, relative to size33
      • Stars gained, absolute14
      • npm download trend56
    • Tool quality76 / 100 · weight 13%
      • Tool description quality68
      • Built and inspected by Glama100
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    62.1
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    62.1
  • 9

    yutu

    Community favourite 1
    eat-pray-ai/yutu

    Best for: Automating YouTube channel workflows from scripts or MCP clients: it provides CLI and server interfaces for uploading videos, managing comments, playlists, and channel branding.

    It is a CLI and MCP server that wraps YouTube Data and Analytics APIs, with commands for authentication and configuration via environment variables. Before using it, you must create a Google Cloud project, enable the YouTube APIs, and provide OAuth client secrets and tokens.

    GitHub stars
    630
    Stars over the last 90 days: 508 at the earliest of 30 readings and 634 at the latest, up 126.
    Stars / 30 days
    +24
    npm / typical week
    Ships no npm package
    Tools exposed
    never inspected
    Last commit
    today
    Commits / 12 weeks
    91
    Weekly commits over the last 12 weeks, oldest first: 16, 5, 7, 19, 4, 7, 7, 1, 2, 9, 14, 2. 93 in total, and the last figure is the current week so far.
    Maintenance grade
    A
    Tool descriptions
    Not graded
    Score 61.9: show every number behind it
    • Adoption70 / 100 · weight 40%
      • GitHub stars70
      • npm downloadsnot measured
        no npm package
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance100 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade100
      • Commit cadence100
    • Momentum66 / 100 · weight 14%
      • Stars gained, relative to size73
      • Stars gained, absolute57
      • npm download trendnot measured
        no npm download history
    • Tool quality70 / 100 · weight 13%
      • Tool description quality70
        tool descriptions not yet scored
      • Built and inspected by Glamanot measured
        never built and inspected by Glama
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    79.4
    × relevance: the keyword is declared here
    0.78
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    61.9
  • Best for: Turning paywalled articles, podcasts, EPUBs, tweets, or WeChat posts into NotebookLM outputs: it fetches sources, bypasses paywalls, and generates podcasts, PPTs, mind maps, and quizzes.

    The server is an MCP interface that takes a URL, file, or search query, fetches and de-paywalls the source, uploads the extracted content to NotebookLM, and returns generated podcast, PPT, mind map, quiz, report, video, infographic, or flashcard outputs. Before choosing it, know the setup: Python 3.9+, Git, and a NotebookLM login are required, and podcast transcription from Xiaoyuzhou, Ximalaya, or Bilibili additionally requires a Get笔记 API key.

    GitHub stars
    5,901
    Stars over the last 90 days: 5,268 at the earliest of 9 readings and 5,970 at the latest, up 702.
    Stars / 30 days
    +224
    npm / typical week
    Ships no npm package
    Tools exposed
    never inspected
    Last commit
    132 days ago
    Commits / 12 weeks
    0
    Maintenance grade
    D
    Tool descriptions
    Not graded
    Score 61.5: show every number behind it
    • Adoption94 / 100 · weight 40%
      • GitHub stars94
      • npm downloadsnot measured
        no npm package
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance46 / 100 · weight 24%
      • Last commit touching this server68
      • Repository maintenance grade30
      • Commit cadence5
    • Momentum86 / 100 · weight 14%
      • Stars gained, relative to size80
      • Stars gained, absolute95
      • npm download trendnot measured
        no npm download history
    • Tool quality70 / 100 · weight 13%
      • Tool description quality70
        tool descriptions not yet scored
      • Built and inspected by Glamanot measured
        never built and inspected by Glama
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    78.8
    × relevance: the keyword is declared here
    0.78
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    61.5
  • Best for: AI agents that need to schedule and publish social media posts to multiple platforms from a single CLI or MCP server.

    SocialClaw provides a CLI and MCP server for scheduling, validating, and publishing social media posts across platforms, with commands for account management, asset upload, and post inspection. It requires a hosted SocialClaw workspace with an API key and an active trial or paid plan, so it is not a self-hosted solution.

    GitHub stars
    86
    Stars over the last 90 days: 22 at the earliest of 9 readings and 86 at the latest, up 64.
    Stars / 30 days
    +12
    npm / typical week
    147
    Tools exposed
    never inspected
    Last commit
    13 days ago
    Commits / 12 weeks
    26
    Weekly commits over the last 12 weeks, oldest first: 11, 0, 0, 0, 3, 0, 6, 2, 1, 1, 2, 0. 26 in total, and the last figure is the current week so far.
    Maintenance grade
    A
    Tool descriptions
    Not graded
    Score 56.2: show every number behind it
    • Adoption55 / 100 · weight 40%
      • GitHub stars48
      • npm downloads46
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance97 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade100
      • Commit cadence85
    • Momentum61 / 100 · weight 14%
      • Stars gained, relative to size94
      • Stars gained, absolute45
      • npm download trend19
    • Tool quality70 / 100 · weight 13%
      • Tool description quality70
        tool descriptions not yet scored
      • Built and inspected by Glamanot measured
        never built and inspected by Glama
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    72.1
    × relevance: the keyword is declared here
    0.78
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    56.2
  • Best for: Pulling readable content from URLs, documents, and media, then summarizing it via CLI, Python API, or MCP.

    The server provides extract_content and summarize_content tools through a Python API, a CLI, and an MCP server. Extract_content works without an API key for most sources; summarize_content requires an OpenAI or other LLM provider key to be configured.

    GitHub stars
    171
    Stars over the last 90 days: 160 at the earliest of 10 readings and 171 at the latest, up 11.
    Stars / 30 days
    +3
    npm / typical week
    Ships no npm package
    Tools exposed
    2
    Last commit
    today
    Commits / 12 weeks
    30
    Weekly commits over the last 12 weeks, oldest first: 0, 0, 0, 4, 0, 4, 6, 0, 0, 0, 0, 16. 30 in total, and the last figure is the current week so far.
    Maintenance grade
    A
    Tool descriptions
    A
    Score 54.8: show every number behind it
    • Adoption56 / 100 · weight 40%
      • GitHub stars56
      • npm downloadsnot measured
        no npm package
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance100 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade100
      • Commit cadence100
    • Momentum36 / 100 · weight 14%
      • Stars gained, relative to size43
      • Stars gained, absolute26
      • npm download trendnot measured
        no npm download history
    • Tool quality76 / 100 · weight 13%
      • Tool description quality68
      • Built and inspected by Glama100
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    70.3
    × relevance: the keyword is declared here
    0.78
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    54.8
  • 13

    mcp-openshorts

    Community favourite 1
    mutonby/openshorts

    Best for: Turning long-form video into vertical social media clips: it exposes an MCP endpoint for clip generation, AI shorts, and YouTube publishing.

    The server exposes an MCP endpoint that creates vertical clips from uploaded long videos, and its README documents features for AI-generated shorts and YouTube publishing. Choosing it means either self-hosting with Docker and at least 8GB of RAM plus external API keys, or using the hosted service with an account.

    GitHub stars
    3,895
    Stars over the last 90 days: 2,933 at the earliest of 15 readings and 3,954 at the latest, up 1,021.
    Stars / 30 days
    +1,075
    npm / typical week
    Ships no npm package
    Tools exposed
    never inspected
    Last commit
    today
    Commits / 12 weeks
    286
    Weekly commits over the last 12 weeks, oldest first: 0, 0, 0, 6, 92, 30, 24, 6, 13, 76, 34, 15. 296 in total, and the last figure is the current week so far.
    Maintenance grade
    A
    Tool descriptions
    Not graded
    Score 49.8: show every number behind it
    • Adoption90 / 100 · weight 40%
      • GitHub stars90
      • npm downloadsnot measured
        no npm package
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance100 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade100
      • Commit cadence100
    • Momentum100 / 100 · weight 14%
      • Stars gained, relative to size100
      • Stars gained, absolute100
      • npm download trendnot measured
        no npm download history
    • Tool quality70 / 100 · weight 13%
      • Tool description quality70
        tool descriptions not yet scored
      • Built and inspected by Glamanot measured
        never built and inspected by Glama
    • Trust0 / 100 · weight 9%
      • License0
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    83.0
    × relevance: the keyword is tagged here
    0.60
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    49.8
  • Best for: Uploading videos to YouTube from an MCP client such as Claude, Cursor, or VS Code, with OAuth2 authentication and token management.

    The server exposes tools to authenticate with Google, retrieve channels, refresh tokens, upload videos, and update videos with playlists, thumbnails, and subtitles. The main requirement is a Google OAuth client secret file configured in the MCP client; subtitle uploads also need the youtube.force-ssl scope.

    GitHub stars
    51
    Stars over the last 90 days: 40 at the earliest of 9 readings and 53 at the latest, up 13.
    Stars / 30 days
    +1
    npm / typical week
    Ships no npm package
    Tools exposed
    never inspected
    Last commit
    57 days ago
    Commits / 12 weeks
    2
    Weekly commits over the last 12 weeks, oldest first: 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0. 2 in total, and the last figure is the current week so far.
    Maintenance grade
    B
    Tool descriptions
    Not graded
    Score 48.5: show every number behind it
    • Adoption43 / 100 · weight 40%
      • GitHub stars43
      • npm downloadsnot measured
        no npm package
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance76 / 100 · weight 24%
      • Last commit touching this server88
      • Repository maintenance grade80
      • Commit cadence40
    • Momentum24 / 100 · weight 14%
      • Stars gained, relative to size32
      • Stars gained, absolute14
      • npm download trendnot measured
        no npm download history
    • Tool quality70 / 100 · weight 13%
      • Tool description quality70
        tool descriptions not yet scored
      • Built and inspected by Glamanot measured
        never built and inspected by Glama
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    57.1
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: modest but real audience
    0.85
    Composite score
    48.5
  • Best for: Research workflows that need verifiable sources: it exposes search, scrape, and citation-verification tools.

    It exposes 25 tools covering web search, page scraping, academic and patent search, and citation verification, and documents a Python SDK. It assumes an MCP client such as Claude, Cursor, or Copilot to invoke its tools.

    GitHub stars
    55
    Stars over the last 90 days: 29 at the earliest of 38 readings and 55 at the latest, up 26.
    Stars / 30 days
    +8
    npm / typical week
    Ships no npm package
    Tools exposed
    25
    Last commit
    5 days ago
    Commits / 12 weeks
    381
    Weekly commits over the last 12 weeks, oldest first: 21, 51, 23, 29, 8, 69, 55, 38, 0, 57, 21, 9. 381 in total, and the last figure is the current week so far.
    Maintenance grade
    A
    Tool descriptions
    A
    Score 46.8: show every number behind it
    • Adoption44 / 100 · weight 40%
      • GitHub stars44
      • npm downloadsnot measured
        no npm package
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance100 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade100
      • Commit cadence100
    • Momentum64 / 100 · weight 14%
      • Stars gained, relative to size81
      • Stars gained, absolute38
      • npm download trendnot measured
        no npm download history
    • Tool quality85 / 100 · weight 13%
      • Tool description quality77
      • Built and inspected by Glama100
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    70.6
    × relevance: the keyword is declared here
    0.78
    × continuity: actively changing
    1.00
    × evidence: modest but real audience
    0.85
    Composite score
    46.8
  • Best for: For someone who wants YouTube search, summaries, transcripts, and clips inside Claude Code without an API key

    The server exposes tools for searching videos, channels, and playlists; fetching transcripts; summarizing content; downloading audio or video; cutting clips; and building highlight reels. It requires Node.js 18 or newer.

    GitHub stars
    50
    Stars / 30 days
    +6
    npm / typical week
    14
    Tools exposed
    never inspected
    Last commit
    129 days ago
    Commits / 12 weeks
    0
    Maintenance grade
    D
    Tool descriptions
    Not graded
    Score 46.1: show every number behind it
    • Adoption45 / 100 · weight 40%
      • GitHub stars43
      • npm downloads13
        downloads show none of the weekday rhythm human traffic has; halved
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance46 / 100 · weight 24%
      • Last commit touching this server68
      • Repository maintenance grade30
      • Commit cadence5
    • Momentum52 / 100 · weight 14%
      • Stars gained, relative to size69
      • Stars gained, absolute33
      • npm download trend44
    • Tool quality70 / 100 · weight 13%
      • Tool description quality70
        tool descriptions not yet scored
      • Built and inspected by Glamanot measured
        never built and inspected by Glama
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    54.2
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: modest but real audience
    0.85
    Composite score
    46.1
  • Best for: Local LLMs needing Google search, YouTube transcription, and live feeds without API keys: 38 tools cover search, feeds, transcription, clips, OCR, and image search.

    The server exposes 38 MCP tools for Google search, news and social feeds, YouTube subscription and transcription, image search, OCR, and media/document handling. It needs no API keys, but it depends on headless Chromium and local ML models, and Google may still serve CAPTCHAs the built-in solver cannot handle.

    GitHub stars
    125
    Stars over the last 90 days: 112 at the earliest of 10 readings and 125 at the latest, up 13.
    Stars / 30 days
    +7
    npm / typical week
    Ships no npm package
    Tools exposed
    38
    Last commit
    21 days ago
    Commits / 12 weeks
    4
    Weekly commits over the last 12 weeks, oldest first: 0, 0, 0, 0, 0, 3, 0, 0, 0, 1, 0, 0. 4 in total, and the last figure is the current week so far.
    Maintenance grade
    B
    Tool descriptions
    A
    Score 44.2: show every number behind it
    • Adoption53 / 100 · weight 40%
      • GitHub stars53
      • npm downloadsnot measured
        no npm package
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance83 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade80
      • Commit cadence40
    • Momentum52 / 100 · weight 14%
      • Stars gained, relative to size63
      • Stars gained, absolute35
      • npm download trendnot measured
        no npm download history
    • Tool quality73 / 100 · weight 13%
      • Tool description quality65
      • Built and inspected by Glama100
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    66.7
    × relevance: the keyword is declared here
    0.78
    × continuity: actively changing
    1.00
    × evidence: modest but real audience
    0.85
    Composite score
    44.2
  • Best for: Controlling a smart TV from a terminal or MCP client by natural language: it exposes play-by-name, cast-URL, volume, power, scene, and multi-room sync tools.

    The server ships 23 MCP tools covering play by name, casting URLs, volume, power, TV status, scenes, multi-room sync, insights, display, and audio. Before using it, a TV must be connected via stv setup; without one, commands fall back to opening content in the browser.

    GitHub stars
    46
    Stars over the last 90 days: 34 at the earliest of 10 readings and 46 at the latest, up 12.
    Stars / 30 days
    +8
    npm / typical week
    Ships no npm package
    Tools exposed
    23
    Last commit
    21 days ago
    Commits / 12 weeks
    8
    Weekly commits over the last 12 weeks, oldest first: 0, 0, 0, 0, 0, 0, 0, 0, 0, 8, 0, 0. 8 in total, and the last figure is the current week so far.
    Maintenance grade
    A
    Tool descriptions
    A
    Score 44.1: show every number behind it
    • Adoption42 / 100 · weight 40%
      • GitHub stars42
      • npm downloadsnot measured
        no npm package
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance93 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade100
      • Commit cadence65
    • Momentum66 / 100 · weight 14%
      • Stars gained, relative to size85
      • Stars gained, absolute39
      • npm download trendnot measured
        no npm download history
    • Tool quality71 / 100 · weight 13%
      • Tool description quality63
      • Built and inspected by Glama100
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    66.5
    × relevance: the keyword is declared here
    0.78
    × continuity: actively changing
    1.00
    × evidence: modest but real audience
    0.85
    Composite score
    44.1
  • Best for: Analyzing YouTube videos through an MCP client without flooding the LLM: it summarizes transcripts server-side and exposes search, comments, entity, and playlist tools.

    The server exposes ten MCP tools for YouTube video metadata, server-side transcript summarization, comments, entities, topic segments, search, playlists, and channel monitoring via RSS. A requirement to know is that full report summaries need an LLM provider configured through environment variables, and transcript extraction depends on yt-dlp.

    GitHub stars
    51
    Stars over the last 90 days: 46 at the earliest of 9 readings and 51 at the latest, up 5.
    Stars / 30 days
    +1
    npm / typical week
    Ships no npm package
    Tools exposed
    10
    Last commit
    200 days ago
    Commits / 12 weeks
    0
    Maintenance grade
    C
    Tool descriptions
    A
    Score 43.9: show every number behind it
    • Adoption43 / 100 · weight 40%
      • GitHub stars43
      • npm downloadsnot measured
        no npm package
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance52 / 100 · weight 24%
      • Last commit touching this server68
      • Repository maintenance grade55
      • Commit cadence5
    • Momentum24 / 100 · weight 14%
      • Stars gained, relative to size32
      • Stars gained, absolute14
      • npm download trendnot measured
        no npm download history
    • Tool quality73 / 100 · weight 13%
      • Tool description quality65
      • Built and inspected by Glama100
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    51.6
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: modest but real audience
    0.85
    Composite score
    43.9
  • Best for: Transcript research on YouTube videos without an API key: it extracts timestamped, citable transcript segments from a video URL alone.

    The server exposes 12 tools for searching videos, retrieving timestamped transcripts, fetching video and channel statistics, comparing videos, and analyzing channel or video trends. Transcript tools work without an API key, but the search, statistics, comments, and analytics tools require YOUTUBE_API_KEY, and remote deployments should set a bearer token.

    GitHub stars
    19
    Stars over the last 90 days: 14 at the earliest of 18 readings and 19 at the latest, up 5.
    Stars / 30 days
    +6
    npm / typical week
    84
    Tools exposed
    12
    Last commit
    51 days ago
    Commits / 12 weeks
    18
    Weekly commits over the last 12 weeks, oldest first: 1, 0, 0, 0, 16, 1, 0, 0, 0, 0, 0, 0. 18 in total, and the last figure is the current week so far.
    Maintenance grade
    A
    Tool descriptions
    B
    Score 43.4: show every number behind it
    • Adoption36 / 100 · weight 40%
      • GitHub stars33
      • npm downloads21
        downloads show none of the weekday rhythm human traffic has; halved
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance90 / 100 · weight 24%
      • Last commit touching this server88
        dated from the last commit on the default branch, re-read from GitHub at publication; github.com shows a push 3 days ago, which counts every ref; the stored date would have published 3 days ago
      • Repository maintenance grade100
      • Commit cadence85
    • Momentum59 / 100 · weight 14%
      • Stars gained, relative to size76
      • Stars gained, absolute33
      • npm download trend58
    • Tool quality68 / 100 · weight 13%
      • Tool description quality60
      • Built and inspected by Glama100
    • Trust100 / 100 · weight 9%
      • License100
      • Published by the vendor it integratesnot measured
        not published by the vendor it integrates
    Weighted mean of the five
    62.0
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: small audience
    0.70
    Composite score
    43.4

Questions people ask

Which server should I use for YouTube transcripts only?

YouTube Transcript MCP Server (jkawamoto/mcp-youtube-transcript) is the focused choice: it exposes get_transcript, get_timed_transcript, get_video_info, and get_available_languages, and had a commit 30 days ago. YouTube Skills for AI Agents (ZeroPointRepo/youtube-skills) also covers transcripts and adds search, channel browsing, and playlist extraction. If you need timestamped, citable segments from a URL alone, YouTube MCP Server (coyaSONG/youtube-mcp-server) is built for that.

What is the difference between YouTube Skills and jkawamoto's transcript server?

ZeroPointRepo/youtube-skills is the broader package: it bundles transcript, search, channel browsing, and playlist extraction in one install. jkawamoto/mcp-youtube-transcript is narrower, with 4 tools for transcript and video info, and it had 29 commits in the last 12 weeks compared with 7 for the broader package. Choose the broader package if you expect to need more than transcripts; choose the narrower one if you want a small, transcript-focused surface.

Can any of these upload videos to YouTube?

Youtube Uploader MCP (anwerj/youtube-uploader-mcp) is the one for uploading: it has an OAuth2 authentication flow, access token and refresh token management, and multi-channel support. None of the transcript or search servers claim to upload. It had a commit 57 days ago and 2 commits in the last 12 weeks.

Does coyaSONG's YouTube server need an API key?

No, its description says it is for transcript research without an API key and it extracts timestamped, citable transcript segments from a video URL alone. It exposes 12 tools and had a commit 51 days ago. It does not list any API key requirement.

Which one can I use in Claude Code without an API key?

YouTube for AI Agents (JCodesMore/youtube-for-ai-agents) is described as enabling search, watching, summarizing, clipping, and transcript extraction without an API key or leaving the chat. It is Dormant, though: last commit 129 days ago and 0 commits in the last 12 weeks. If you want a more active alternative, YouTube Skills for AI Agents (ZeroPointRepo/youtube-skills) is a Community favourite with a commit 15 days ago.

Can mcp-openshorts publish generated clips to YouTube?

mcp-openshorts (mutonby/openshorts) turns long videos into vertical clips and is described as exposing an MCP endpoint for clip generation, AI shorts, and YouTube publishing. It had a commit 0 days ago and 286 commits in the last 12 weeks, so it is actively developed. It does not describe OAuth or token management, so check your YouTube account connection before relying on it.

Other comparisons