Skip to main content
Glama

20 Best YouTube MCP Servers, Compared (October 2026)

Updated 20 of 890 YouTube servers in the Glama registryRebuilt weekly

The short answer

Most readers should reach for YouTube Skills for AI Agents: it is a Community favourite with 1,080 GitHub stars, 166 stars gained per 30 days, and 15 commits in the last 12 weeks, and it installs as Agent Skills for Claude Code, Cursor, OpenClaw, and Hermes. If your client needs a conventional MCP transcript server with measured tools, YouTube Transcript MCP Server (jkawamoto/mcp-youtube-transcript) is the better answer: it exposes 4 tools, has an A tool description grade, had a commit 15 days ago, and has 35 commits in the last 12 weeks. If you also need search, comments, and channel statistics, mcp-youtube (kirbah/mcp-youtube) is the better answer: it exposes 9 tools, has an A tool description grade, and had a commit 7 days ago.

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 : Agents needing YouTube transcripts, video search, channel browsing, and playlist extraction: it installs as Agent Skills for Claude Code, Cursor, OpenClaw, and Hermes.
  • 2YouTube Transcript MCP Server : When you need YouTube transcript and metadata extraction inside an MCP client: it exposes four tools for raw text, timed segments, languages, and video info.
  • 3mcp-youtube : LLM agents analyzing YouTube content while conserving context: it exposes nine tools for transcripts, video details, search, comments, and channel statistics.
  • 4YouTube MCP Server : For agents that must search YouTube, list subtitle languages, and download subtitles as VTT, this server exposes ytdlp_ tools for those tasks.
  • 5YouTube MCP Server : Summarizing a specific YouTube video inside Claude: the server exposes download_youtube_url to fetch that video's subtitles.

Which one, for your situation

Your situationWhat to use
I need transcripts inside Goose or a similar MCP clientYouTube Transcript MCP Server (jkawamoto/mcp-youtube-transcript) is the fit: it exposes 4 tools for raw text, timed segments, languages, and video info, has an A tool description grade, and had a commit 15 days ago.
I need structured search, comments, and channel statisticsmcp-youtube (kirbah/mcp-youtube) is the fit: it exposes 9 tools for transcripts, video details, search, comments, and channel statistics, has an A tool description grade, and its @kirbah/mcp-youtube package had 399 npm downloads in a typical week.
I need Agent Skills for Claude Code or CursorYouTube Skills for AI Agents is the fit: it is a Community favourite with 1,080 GitHub stars and 166 stars gained per 30 days, and it installs as Agent Skills for Claude Code, Cursor, OpenClaw, and Hermes.
I need to upload videos and manage playlistsyutu is the fit: it automates YouTube video uploads, comments, playlists, and channel branding through an MCP server, CLI, agent, and skill, had a commit 0 days ago, and has 88 commits in the last 12 weeks.
I need private channel analytics and SEO metadata writesyoutube-marketing-skills is the fit: it connects agents to real YouTube channel analytics and SEO management via OAuth, including titles, descriptions, and tags.
I need hosted read-only YouTube data with no API keyHasData/youtube-mcp is the fit: it provides read-only search, video/channel data, and transcripts with no Google Cloud project or YouTube Data API key required, and it exposes 4 tools with an A tool description grade.

Top MCP servers for YouTube

Best forProfile
1
ZeroPointRepo/youtube-skills
Agents needing YouTube transcripts, video search, channel browsing, and playlist extraction: it installs as Agent Skills for Claude Code, Cursor, OpenClaw, and Hermes.Community favourite1,080+16627 days ago82.4
2
jkawamoto/mcp-youtube-transcript
When you need YouTube transcript and metadata extraction inside an MCP client: it exposes four tools for raw text, timed segments, languages, and video info.Community favourite489+715 days ago73.6
3
kirbah/mcp-youtube
LLM agents analyzing YouTube content while conserving context: it exposes nine tools for transcripts, video details, search, comments, and channel statistics.Community favourite30+17 days ago72.4
4
kevinwatt/yt-dlp-mcp
For agents that must search YouTube, list subtitle languages, and download subtitles as VTT, this server exposes ytdlp_ tools for those tasks.Community favourite288+1168 days ago72.2
5
anaisbetts/mcp-youtube
Summarizing a specific YouTube video inside Claude: the server exposes download_youtube_url to fetch that video's subtitles.Community favourite551+763 days ago70.1
6
ZubeidHendricks/youtube-mcp-server
Creator discovery research: it searches videos and channels and filters results by subscriber band, recent upload activity, and creator-only heuristics.Community favourite587+1471 days ago68.0
7
kimtaeyoon83/mcp-server-youtube-transcript
Retrieving captions or subtitles from YouTube videos or Shorts: get_transcript accepts URLs or IDs and falls back to available languages.Abandoned but popular603+790 days ago64.8
8
joeseesun/qiaomu-anything-to-notebooklm
Turning YouTube videos into NotebookLM podcast, slide deck, or mind map outputs: it extracts YouTube captions and uploads the content to NotebookLM.Abandoned but popular6,229+117174 days ago59.6
9
eat-pray-ai/yutu
Automating YouTube video uploads, comments, playlists, and channel branding via a CLI or AI agent: it provides an MCP server, CLI, agent, and skill.Community favourite699+9today59.5
10
sinco-lab/mcp-youtube-transcript
Local transcript extraction for YouTube videos in MCP clients: it exposes a get_transcripts tool that takes a video URL or ID.Abandoned but popular39+3151 days ago58.7
11
mutonby/openshorts
Turning a long video into vertical clips from a link: it accepts a URL, transcribes, picks moments and renders 9:16 clips.Community favourite6,727+1,497yesterday57.6
12
adityaarsharma/youtube-marketing-skills
Solo educators running tutorial content who want their agent to read private YouTube Analytics and write titles, descriptions, and tags back to YouTube via OAuth.Emerging60+239 days ago57.3
13
anwerj/youtube-uploader-mcp
Uploading videos to YouTube from an MCP client with OAuth2 multi-channel accounts: its README documents upload_video and update_video for metadata, playlists, thumbnails, and captions.Steady59+728 days ago55.7
14
HasData/youtube-mcp
When a client needs read-only YouTube search, video/channel data, and transcripts without a Google Cloud project or YouTube Data API key: it exposes four tools.Steady606 days ago52.1
15
lfnovo/content-core
Pulling YouTube transcripts and other media into an agent pipeline without an API key: extract_content handles URLs, documents, and audio or video files.Steady173-115 days ago50.6
16
engram-ae/noapi-google-search-mcp
Working with YouTube content locally: it transcribes videos with Whisper, searches stored transcripts, and extracts clips by topic, without API keys.Steady131+463 days ago50.5
17
zlatkoc/youtube-summarize
Summarizing a YouTube video while keeping the prompt visible for review: it exposes transcript, summarization, metadata, playlist, search, and language tools.Steady6080 days ago49.8
18
zoharbabin/web-researcher-mcp
Researchers who need YouTube transcripts alongside web, PDF, and academic sources: it exposes scrape_page, web_search, and academic_search.Emerging68+94 days ago48.1
19
JangHyuckYun/mcp-youtube-intelligence
When a user needs YouTube video summaries, transcripts, comments, RSS channel monitoring, entity extraction, or reports, it exposes ten tools including get_transcript and generate_report.Steady52040 days ago47.3
20
tubeagentkit/youtube-mcp
Teams needing YouTube transcripts plus channel and playlist search without local install: it exposes remote transcript, search, channel browsing, in-channel search, and playlist extraction.Emerging27+272 days ago47.3

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.
  • 1

    YouTube Skills for AI Agents

    Community favouriteNo change
    ZeroPointRepo/youtube-skills ↗

    Best for: Agents needing YouTube transcripts, video search, channel browsing, and playlist extraction: it installs as Agent Skills for Claude Code, Cursor, OpenClaw, and Hermes.

    The repository ships Agent Skills for the skills.sh format (youtube-full plus focused skills for transcripts, search, channels, and playlists) that agents install with npx skills add, clawhub, or hermes skills install, and its README points to a separate MCP server repository rather than documenting MCP tools here. The requirement worth knowing before choosing it is an account: each skill authenticates against TranscriptAPI with an API key the agent registers by email and stores as TRANSCRIPT_API_KEY, so it is a hosted API client rather than a local extractor.

    GitHub stars
    1,080
    Stars over the last 90 days: 442 at the earliest of 15 readings and 1,080 at the latest, up 638.
    Stars / 30 days
    +166
    npm / typical week
    Ships no npm package
    PyPI / typical week
    no attributed package
    Tools exposed
    never inspected
    Last commit
    27 days ago
    Commits / 12 weeks
    15
    Weekly commits over the last 12 weeks, oldest first: 0, 0, 5, 1, 1, 0, 0, 0, 8, 0, 0, 0. 15 in total, and the last figure is the current week so far.
    Maintenance grade
    C
    Tool descriptions
    Not graded
    Score 82.4: show every number behind it
    • Adoption76 / 100 · weight 40%
      • GitHub stars76
      • npm downloadsnot measured
        no npm package
      • 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
    • Momentum96 / 100 · weight 14%
      • Stars gained, relative to size100
      • Stars gained, absolute90
      • npm download trendnot measured
        no download history for the selected registry
    • Tool quality≈70 / 100 · weight 13%
      • Tool description quality≈70
        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
    82.4
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    82.4
  • 2

    YouTube Transcript MCP Server

    Community favouriteNo change
    jkawamoto/mcp-youtube-transcript ↗

    Best for: When you need YouTube transcript and metadata extraction inside an MCP client: it exposes four tools for raw text, timed segments, languages, and video info.

    The server communicates over stdio and registers four tools for transcript and metadata retrieval: get_transcript, get_timed_transcript, get_video_info, and get_available_languages. Its quick start requires uv installed for the uvx command, although a Docker image is also available.

    GitHub stars
    489
    Stars over the last 90 days: 462 at the earliest of 13 readings and 489 at the latest, up 27.
    Stars / 30 days
    +7
    npm / typical week
    Ships no npm package
    PyPI / typical week
    no attributed package
    Tools exposed
    4
    Last commit
    15 days ago
    Commits / 12 weeks
    35
    Weekly commits over the last 12 weeks, oldest first: 0, 2, 8, 0, 0, 0, 7, 6, 11, 0, 1, 0. 35 in total, and the last figure is the current week so far.
    Maintenance grade
    B
    Tool descriptions
    A
    Score 73.6: show every number behind it
    • Adoption67 / 100 · weight 40%
      • GitHub stars67
      • npm downloadsnot measured
        no npm package
      • Used through Glamanot measured
        not used through Glama in the last 30 days
    • Maintenance95 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade80
      • Commit cadence100
    • Momentum41 / 100 · weight 14%
      • Stars gained, relative to size43
      • Stars gained, absolute37
      • npm download trendnot measured
        no download history for the selected registry
    • 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
    73.6
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    73.6
  • 3

    mcp-youtube

    Community favourite▲ 9
    kirbah/mcp-youtube ↗

    Best for: LLM agents analyzing YouTube content while conserving context: it exposes nine tools for transcripts, video details, search, comments, and channel statistics.

    It exposes nine YouTube tools for video details, search, transcripts, comments, channel statistics, top videos, trending videos, categories, and outlier-channel discovery through the YouTube Data API v3. Deep search and analytics require a YouTube Data API v3 key, while zero-config mode supports transcript reads without one.

    GitHub stars
    30
    Stars over the last 90 days: 25 at the earliest of 18 readings and 30 at the latest, up 5.
    Stars / 30 days
    +1
    npm / typical week
    399
    PyPI / typical week
    no attributed package
    Tools exposed
    9
    Last commit
    7 days ago
    Commits / 12 weeks
    71
    Weekly commits over the last 12 weeks, oldest first: 13, 10, 3, 2, 0, 8, 6, 9, 0, 2, 14, 4. 71 in total, and the last figure is the current week so far.
    Maintenance grade
    A
    Tool descriptions
    A
    Score 72.4: show every number behind it
    • Adoption61 / 100 · weight 40%
      • GitHub stars37
      • npm downloads55
      • 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
    • Momentum28 / 100 · weight 14%
      • Stars gained, relative to size33
      • Stars gained, absolute14
      • npm download trend34
    • 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
    72.4
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    72.4
  • 4

    YouTube MCP Server

    Community favourite▼ 1
    kevinwatt/yt-dlp-mcp ↗

    Best for: For agents that must search YouTube, list subtitle languages, and download subtitles as VTT, this server exposes ytdlp_ tools for those tasks.

    YouTube MCP Server runs yt-dlp through an MCP interface and documents tools such as ytdlp_search_videos, ytdlp_list_subtitle_languages, and ytdlp_download_video_subtitles for searching, subtitle discovery, and subtitle downloads. Before choosing it, note that it assumes yt-dlp is installed separately on the system.

    GitHub stars
    288
    Stars over the last 90 days: 263 at the earliest of 11 readings and 291 at the latest, up 28.
    Stars / 30 days
    +11
    npm / typical week
    273
    PyPI / typical week
    no attributed package
    Tools exposed
    never inspected
    Last commit
    68 days ago
    Commits / 12 weeks
    1
    Weekly commits over the last 12 weeks, oldest first: 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0. 1 in total, and the last figure is the current week so far.
    Maintenance grade
    A
    Tool descriptions
    Not graded
    Score 72.2: show every number behind it
    • Adoption65 / 100 · weight 40%
      • GitHub stars62
      • 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
    • Maintenance81 / 100 · weight 24%
      • Last commit touching this server88
      • Repository maintenance grade100
      • Commit cadence40
    • Momentum60 / 100 · weight 14%
      • Stars gained, relative to size65
      • Stars gained, absolute43
      • npm download trend70
    • Tool quality≈70 / 100 · weight 13%
      • Tool description quality≈70
        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
    72.2
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    72.2
  • 5

    YouTube MCP Server

    Community favourite▼ 1
    anaisbetts/mcp-youtube ↗

    Best for: Summarizing a specific YouTube video inside Claude: the server exposes download_youtube_url to fetch that video's subtitles.

    YouTube MCP Server exposes a single tool, download_youtube_url, which uses yt-dlp to download subtitles from a YouTube URL so Claude can read them. It assumes yt-dlp is installed locally, for example via Homebrew, and it is set up by installing the npm package @anaisbetts/mcp-youtube through mcp-installer.

    GitHub stars
    551
    Stars over the last 90 days: 536 at the earliest of 86 readings and 551 at the latest, up 15.
    Stars / 30 days
    +7
    npm / typical week
    downloads not counted
    PyPI / typical week
    no attributed package
    Tools exposed
    1
    Last commit
    63 days ago
    Commits / 12 weeks
    13
    Weekly commits over the last 12 weeks, oldest first: 0, 0, 13, 0, 0, 0, 0, 0, 0, 0, 0, 0. 13 in total, and the last figure is the current week so far.
    Maintenance grade
    C
    Tool descriptions
    A
    Score 70.1: show every number behind it
    • Adoption69 / 100 · weight 40%
      • GitHub stars69
      • 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
    • Maintenance79 / 100 · weight 24%
      • Last commit touching this server88
      • Repository maintenance grade55
      • Commit cadence85
    • Momentum40 / 100 · weight 14%
      • Stars gained, relative to size41
      • Stars gained, absolute37
      • npm download trendnot measured
        no download history for the selected registry
    • 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
    70.1
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    70.1
  • 6

    YouTube MCP Server

    Community favourite▼ 1
    ZubeidHendricks/youtube-mcp-server ↗

    Best for: Creator discovery research: it searches videos and channels and filters results by subscriber band, recent upload activity, and creator-only heuristics.

    YouTube MCP Server exposes 10 tools covering video details and search, transcripts, channel details and search, creator discovery from video mentions, channel video listings, and playlist retrieval. Before choosing it, note that the transcript tool returns English by default unless a language is passed or YOUTUBE_TRANSCRIPT_LANG is set.

    GitHub stars
    587
    Stars over the last 90 days: 555 at the earliest of 82 readings and 587 at the latest, up 32.
    Stars / 30 days
    +14
    npm / typical week
    371
    PyPI / typical week
    no attributed package
    Tools exposed
    10
    Last commit
    71 days ago
    Commits / 12 weeks
    1
    Weekly commits over the last 12 weeks, oldest first: 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0. 1 in total, and the last figure is the current week so far.
    Maintenance grade
    C
    Tool descriptions
    C
    Score 68.0: 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
    • Maintenance70 / 100 · weight 24%
      • Last commit touching this server88
      • Repository maintenance grade55
      • Commit cadence40
    • Momentum47 / 100 · weight 14%
      • Stars gained, relative to size57
      • Stars gained, absolute48
      • npm download trend27
    • 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
    68.0
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    68.0
  • 7

    mcp-server-youtube-transcript

    Abandoned but popularNo change
    kimtaeyoon83/mcp-server-youtube-transcript ↗

    Best for: Retrieving captions or subtitles from YouTube videos or Shorts: get_transcript accepts URLs or IDs and falls back to available languages.

    The server exposes one tool, get_transcript, which extracts captions or subtitles from a YouTube video URL, Shorts URL, or video ID and accepts optional language, timestamp, and ad-filtering inputs. It requires Node.js 18 or higher and is configured through npx, and the transcript tool needs no API key.

    GitHub stars
    603
    Stars over the last 90 days: 574 at the earliest of 84 readings and 603 at the latest, up 29.
    Stars / 30 days
    +7
    npm / typical week
    downloads not counted
    PyPI / typical week
    no attributed package
    Tools exposed
    1
    Last commit
    90 days ago
    Commits / 12 weeks
    0
    Maintenance grade
    F
    Tool descriptions
    A
    Score 64.8: show every number behind it
    • Adoption70 / 100 · weight 40%
      • GitHub stars70
      • 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
    • Maintenance51 / 100 · weight 24%
      • Last commit touching this server88
      • Repository maintenance grade5
      • Commit cadence5
    • Momentum39 / 100 · weight 14%
      • Stars gained, relative to size40
      • Stars gained, absolute37
      • npm download trendnot measured
        no download history for the selected registry
    • 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
    64.8
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    64.8
  • 8

    Anything-to-NotebookLM

    Abandoned but popularNo change
    joeseesun/qiaomu-anything-to-notebooklm ↗

    Best for: Turning YouTube videos into NotebookLM podcast, slide deck, or mind map outputs: it extracts YouTube captions and uploads the content to NotebookLM.

    It is an MCP server and Claude Code Skill that ingests sources such as YouTube videos, WeChat articles, podcasts, PDFs, EPUBs, Office documents, images, and audio, then uploads them to Google NotebookLM to produce outputs including podcasts, slide decks, mind maps, quizzes, reports, infographics, and flashcards. Before choosing it, note that it requires Python 3.9+ and a one-time NotebookLM login, and because no npm or PyPI package is published, installation is by cloning the repository and running install.sh.

    GitHub stars
    6,229
    Stars over the last 90 days: 5,653 at the earliest of 10 readings and 6,229 at the latest, up 576.
    Stars / 30 days
    +117
    npm / typical week
    Ships no npm package
    PyPI / typical week
    no attributed package
    Tools exposed
    never inspected
    Last commit
    174 days ago
    Commits / 12 weeks
    0
    Maintenance grade
    D
    Tool descriptions
    Not graded
    Score 59.6: show every number behind it
    • Adoption95 / 100 · weight 40%
      • GitHub stars95
      • 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
        dated from the last commit on the default branch, re-read from GitHub at publication; github.com shows a push 14 days ago, which counts every ref; the stored date would have published 14 days ago
      • Repository maintenance grade30
      • Commit cadence5
    • Momentum67 / 100 · weight 14%
      • Stars gained, relative to size56
      • Stars gained, absolute84
      • npm download trendnot measured
        no download history for the selected registry
    • Tool quality≈70 / 100 · weight 13%
      • Tool description quality≈70
        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
    76.4
    × relevance: the keyword is declared here
    0.78
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    59.6
  • 9

    yutu

    Community favourite▼ 3
    eat-pray-ai/yutu ↗

    Best for: Automating YouTube video uploads, comments, playlists, and channel branding via a CLI or AI agent: it provides an MCP server, CLI, agent, and skill.

    The README documents a CLI, an MCP server, an AI agent, and a skill for YouTube operations including uploading and optimizing videos, managing comments and playlists, and channel branding. Using it requires a Google Cloud Platform project with the YouTube Data API v3 enabled and OAuth desktop-app credentials, plus an initial yutu auth run to cache a token.

    GitHub stars
    699
    Stars over the last 90 days: 596 at the earliest of 30 readings and 699 at the latest, up 103.
    Stars / 30 days
    +9
    npm / typical week
    Ships no npm package
    PyPI / typical week
    no attributed package
    Tools exposed
    never inspected
    Last commit
    today
    Commits / 12 weeks
    88
    Weekly commits over the last 12 weeks, oldest first: 7, 8, 2, 4, 10, 9, 2, 5, 8, 14, 13, 6. 88 in total, and the last figure is the current week so far.
    Maintenance grade
    A
    Tool descriptions
    Not graded
    Score 59.5: show every number behind it
    • Adoption71 / 100 · weight 40%
      • GitHub stars71
      • 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
    • Momentum41 / 100 · weight 14%
      • Stars gained, relative to size41
      • Stars gained, absolute40
      • npm download trendnot measured
        no download history for the selected registry
    • Tool quality≈70 / 100 · weight 13%
      • Tool description quality≈70
        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
    76.3
    × relevance: the keyword is declared here
    0.78
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    59.5
  • 10

    mcp-youtube-transcript

    Abandoned but popular▼ 1
    sinco-lab/mcp-youtube-transcript ↗

    Best for: Local transcript extraction for YouTube videos in MCP clients: it exposes a get_transcripts tool that takes a video URL or ID.

    mcp-youtube-transcript exposes one tool, get_transcripts, which extracts and processes transcripts from a YouTube video given a URL or ID. Before choosing it, note that it requires Node.js 18 or higher and is intended for local npx configuration, so transcript requests run from the user's own machine rather than a remote proxy.

    GitHub stars
    39
    Stars over the last 90 days: 34 at the earliest of 11 readings and 39 at the latest, up 5.
    Stars / 30 days
    +3
    npm / typical week
    389
    PyPI / typical week
    no attributed package
    Tools exposed
    1
    Last commit
    151 days ago
    Commits / 12 weeks
    0
    Maintenance grade
    D
    Tool descriptions
    A
    Score 58.7: show every number behind it
    • Adoption61 / 100 · weight 40%
      • GitHub stars40
      • npm downloads55
      • 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
    • Momentum31 / 100 · weight 14%
      • Stars gained, relative to size50
      • Stars gained, absolute24
      • npm download trend6
    • 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
    58.7
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    58.7
  • 11

    mcp-openshorts

    Community favourite▼ 1
    mutonby/openshorts ↗

    Best for: Turning a long video into vertical clips from a link: it accepts a URL, transcribes, picks moments and renders 9:16 clips.

    mcp-openshorts exposes 8 tools that carry a source video through to posted shorts: process_video and create_upload start jobs from a URL or an uploaded file, get_job_status and list_clips report progress and finished clips, and add_subtitles, recut_clip and publish_clip restyle, re-cut and post them. Before choosing it, note that processing draws on a plan quota that get_quota reports and process_video fails against with quota_exceeded, publishing requires a connected social profile, and installation comes from the repository since no npm or PyPI package is published.

    GitHub stars
    6,727
    Stars over the last 90 days: 2,933 at the earliest of 32 readings and 6,849 at the latest, up 3,916.
    Stars / 30 days
    +1,497
    npm / typical week
    Ships no npm package
    PyPI / typical week
    no attributed package
    Tools exposed
    8
    Last commit
    yesterday
    Commits / 12 weeks
    308
    Weekly commits over the last 12 weeks, oldest first: 21, 19, 2, 67, 48, 21, 15, 10, 40, 11, 32, 21. 307 in total, and the last figure is the current week so far.
    Maintenance grade
    A
    Tool descriptions
    A
    Score 57.6: show every number behind it
    • Adoption96 / 100 · weight 40%
      • GitHub stars96
      • 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 download history for the selected registry
    • Tool quality83 / 100 · weight 13%
      • Tool description quality75
      • 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
    96.0
    × relevance: the keyword is tagged here
    0.60
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    57.6
  • 12

    youtube-marketing-skills

    Emerging▲ 1
    adityaarsharma/youtube-marketing-skills ↗

    Best for: Solo educators running tutorial content who want their agent to read private YouTube Analytics and write titles, descriptions, and tags back to YouTube via OAuth.

    The repository documents an MCP server plus agent commands such as /youtube-strategy, /youtube-ideate, /youtube-seo, and /youtube-wp-post that read private channel analytics over OAuth, push metadata changes back to YouTube, and publish companion WordPress posts. Before installing, note that it assumes Node.js 18+, a Google Cloud project with the YouTube Data API v3 and YouTube Analytics API enabled, and OAuth 2.0 desktop credentials, and that the npm package its README points to is not published, so setup runs from a cloned repository.

    GitHub stars
    60
    Stars over the last 90 days: 32 at the earliest of 10 readings and 60 at the latest, up 28.
    Stars / 30 days
    +23
    npm / typical week
    Ships no npm package
    PyPI / typical week
    no attributed package
    Tools exposed
    never inspected
    Last commit
    9 days ago
    Commits / 12 weeks
    2
    Weekly commits over the last 12 weeks, oldest first: 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2. 2 in total, and the last figure is the current week so far.
    Maintenance grade
    B
    Tool descriptions
    Not graded
    Score 57.3: show every number behind it
    • Adoption45 / 100 · weight 40%
      • GitHub stars45
      • 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
    • Momentum82 / 100 · weight 14%
      • Stars gained, relative to size100
      • Stars gained, absolute56
      • npm download trendnot measured
        no download history for the selected registry
    • Tool quality≈70 / 100 · weight 13%
      • Tool description quality≈70
        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
    67.4
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: modest but real audience
    0.85
    Composite score
    57.3
  • 13

    Youtube Uploader MCP

    Steady▼ 2
    anwerj/youtube-uploader-mcp ↗

    Best for: Uploading videos to YouTube from an MCP client with OAuth2 multi-channel accounts: its README documents upload_video and update_video for metadata, playlists, thumbnails, and captions.

    The README documents tools for OAuth2 authentication, token refresh, channel listing, video upload, post-upload updates, and video listing. Before adoption, the server requires a Google OAuth client_secret.json and a local OAuth login, while subtitle upload depends on the force-ssl scope.

    GitHub stars
    59
    Stars over the last 90 days: 49 at the earliest of 10 readings and 59 at the latest, up 10.
    Stars / 30 days
    +7
    npm / typical week
    Ships no npm package
    PyPI / typical week
    no attributed package
    Tools exposed
    never inspected
    Last commit
    28 days ago
    Commits / 12 weeks
    3
    Weekly commits over the last 12 weeks, oldest first: 0, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0. 3 in total, and the last figure is the current week so far.
    Maintenance grade
    A
    Tool descriptions
    Not graded
    Score 55.7: 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
    • Maintenance88 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade100
      • Commit cadence40
    • Momentum61 / 100 · weight 14%
      • Stars gained, relative to size76
      • Stars gained, absolute37
      • npm download trendnot measured
        no download history for the selected registry
    • Tool quality≈70 / 100 · weight 13%
      • Tool description quality≈70
        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
    65.5
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: modest but real audience
    0.85
    Composite score
    55.7
  • 14

    YouTube MCP Server

    SteadyNew
    HasData/youtube-mcp ↗

    Best for: When a client needs read-only YouTube search, video/channel data, and transcripts without a Google Cloud project or YouTube Data API key: it exposes four tools.

    YouTube MCP Server is a hosted streamable HTTP MCP server that exposes four read-only tools for YouTube search, video and channel data, and transcripts. It requires a HasData API key, sent as an x-api-key header for remote clients or supplied to the npm/PyPI stdio launcher, even though no Google Cloud project or YouTube Data API key is needed.

    GitHub stars
    6
    Stars over the last 90 days: 0 at the earliest of 14 readings and 6 at the latest, up 6.
    Stars / 30 days
    0
    npm / typical week
    25
    PyPI / typical week
    67
    hasdata-youtube-mcp
    Tools exposed
    4
    Last commit
    6 days ago
    Commits / 12 weeks
    35
    Weekly commits over the last 12 weeks, oldest first: 0, 0, 0, 0, 14, 4, 0, 7, 5, 2, 0, 3. 35 in total, and the last figure is the current week so far.
    Maintenance grade
    A
    Tool descriptions
    A
    Score 52.1: show every number behind it
    • Adoption42 / 100 · weight 40%
      • GitHub stars21
      • PyPI downloads39
      • 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
    • Momentum0 / 100 · weight 14%
      • Stars gained, relative to size0
      • Stars gained, absolute0
      • PyPI download trendnot measured
        no download history for the selected registry
    • 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
    61.3
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: modest but real audience
    0.85
    Composite score
    52.1
  • 15

    content-core

    Steady▼ 1
    lfnovo/content-core ↗

    Best for: Pulling YouTube transcripts and other media into an agent pipeline without an API key: extract_content handles URLs, documents, and audio or video files.

    content-core exposes two MCP tools, extract_content and summarize_content, and the README also documents a CLI and an async Python API for pulling content out of web pages, PDFs, office documents, YouTube videos, and audio or video files. Extraction needs no API key for most sources, but summarization requires an LLM provider key such as OPENAI_API_KEY to be configured.

    GitHub stars
    173
    Stars over the last 90 days: 166 at the earliest of 12 readings and 175 at the latest, up 9.
    Stars / 30 days
    -1
    npm / typical week
    Ships no npm package
    PyPI / typical week
    no attributed package
    Tools exposed
    2
    Last commit
    15 days ago
    Commits / 12 weeks
    34
    Weekly commits over the last 12 weeks, oldest first: 6, 0, 0, 0, 0, 16, 0, 0, 0, 8, 0, 0. 30 in total, and the last figure is the current week so far.
    Maintenance grade
    A
    Tool descriptions
    A
    Score 50.6: 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
    • Momentum0 / 100 · weight 14%
      • Stars gained, relative to size0
      • Stars gained, absolute0
      • npm download trendnot measured
        no download history for the selected registry
    • 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
    64.9
    × relevance: the keyword is declared here
    0.78
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    50.6
  • 16

    noapi-google-search-mcp

    SteadyNew
    engram-ae/noapi-google-search-mcp ↗

    Best for: Working with YouTube content locally: it transcribes videos with Whisper, searches stored transcripts, and extracts clips by topic, without API keys.

    It exposes 38 tools covering Google search, news, images, maps, shopping and flights through headless Chromium, alongside local OCR, Whisper transcription of video and audio, document reading, and feed subscriptions stored in SQLite with full-text search. Nothing is published to npm or PyPI, so it has to be run from the repository, and it assumes a local Chromium install plus on-device Whisper and ONNX model downloads, with Google scraping subject to CAPTCHAs and rate limiting.

    GitHub stars
    131
    Stars over the last 90 days: 117 at the earliest of 12 readings and 131 at the latest, up 14.
    Stars / 30 days
    +4
    npm / typical week
    Ships no npm package
    PyPI / typical week
    no attributed package
    Tools exposed
    38
    Last commit
    63 days ago
    Commits / 12 weeks
    1
    Weekly commits over the last 12 weeks, oldest first: 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0. 1 in total, and the last figure is the current week so far.
    Maintenance grade
    B
    Tool descriptions
    A
    Score 50.5: show every number behind it
    • Adoption55 / 100 · weight 40%
      • GitHub stars53
      • npm downloadsnot measured
        no npm package
      • Used through Glama14
    • Maintenance76 / 100 · weight 24%
      • Last commit touching this server88
      • Repository maintenance grade80
      • Commit cadence40
    • Momentum42 / 100 · weight 14%
      • Stars gained, relative to size51
      • Stars gained, absolute29
      • npm download trendnot measured
        no download history for the selected registry
    • 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
    64.7
    × relevance: the keyword is declared here
    0.78
    × continuity: actively changing
    1.00
    × evidence: widely adopted
    1.00
    Composite score
    50.5
  • 17

    youtube-summarize

    Steady▼ 2
    zlatkoc/youtube-summarize ↗

    Best for: Summarizing a YouTube video while keeping the prompt visible for review: it exposes transcript, summarization, metadata, playlist, search, and language tools.

    youtube-summarize exposes six tools for fetching transcripts in text, JSON, SRT, or WebVTT, listing transcript languages, retrieving video metadata, listing playlist videos, searching videos, and returning transcripts with summarization instructions. Before choosing it, note that it requires Python 3.13+ and uv to install and run.

    GitHub stars
    6
    Stars over the last 90 days: 4 at the earliest of 12 readings and 6 at the latest, up 2.
    Stars / 30 days
    0
    npm / typical week
    Ships no npm package
    PyPI / typical week
    59
    youtube-summarize
    Tools exposed
    6
    Last commit
    80 days ago
    Commits / 12 weeks
    14
    Weekly commits over the last 12 weeks, oldest first: 14, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0. 14 in total, and the last figure is the current week so far.
    Maintenance grade
    A
    Tool descriptions
    A
    Score 49.8: show every number behind it
    • Adoption41 / 100 · weight 40%
      • GitHub stars21
      • PyPI downloads38
      • 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 16 days ago, which counts every ref; the stored date would have published 16 days ago
      • Repository maintenance grade100
      • Commit cadence85
    • Momentum0 / 100 · weight 14%
      • Stars gained, relative to size0
      • Stars gained, absolute0
      • PyPI download trendnot measured
        no download history for the selected registry
    • 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
    58.6
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: modest but real audience
    0.85
    Composite score
    49.8
  • 18

    Web Researcher MCP

    Emerging▼ 2
    zoharbabin/web-researcher-mcp ↗

    Best for: Researchers who need YouTube transcripts alongside web, PDF, and academic sources: it exposes scrape_page, web_search, and academic_search.

    Web Researcher MCP exposes 25 tools for web search, page and file scraping (including YouTube transcripts and PDFs), academic, patent, legal, clinical, news, economic, image, local, and company research, plus citation verification and bibliography formatting. For YouTube work specifically, transcript extraction is handled by the general scrape_page tool, not by a dedicated YouTube search tool.

    GitHub stars
    68
    Stars over the last 90 days: 43 at the earliest of 24 readings and 68 at the latest, up 25.
    Stars / 30 days
    +9
    npm / typical week
    Ships no npm package
    PyPI / typical week
    no attributed package
    Tools exposed
    25
    Last commit
    4 days ago
    Commits / 12 weeks
    317
    Weekly commits over the last 12 weeks, oldest first: 79, 54, 21, 10, 68, 9, 7, 1, 0, 15, 0, 53. 317 in total, and the last figure is the current week so far.
    Maintenance grade
    A
    Tool descriptions
    A
    Score 48.1: show every number behind it
    • Adoption46 / 100 · weight 40%
      • GitHub stars46
      • 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
    • Momentum67 / 100 · weight 14%
      • Stars gained, relative to size85
      • Stars gained, absolute41
      • npm download trendnot measured
        no download history for the selected registry
    • Tool quality91 / 100 · weight 13%
      • Tool description quality83
      • 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
    72.5
    × relevance: the keyword is declared here
    0.78
    × continuity: actively changing
    1.00
    × evidence: modest but real audience
    0.85
    Composite score
    48.1
  • 19

    MCP YouTube Intelligence

    Steady▼ 2
    JangHyuckYun/mcp-youtube-intelligence ↗

    Best for: When a user needs YouTube video summaries, transcripts, comments, RSS channel monitoring, entity extraction, or reports, it exposes ten tools including get_transcript and generate_report.

    MCP YouTube Intelligence is an MCP server and CLI that exposes ten tools for retrieving video metadata and transcripts, fetching comments, monitoring channels over RSS, searching transcripts and YouTube, extracting entities, segmenting topics, fetching playlist metadata, and generating markdown reports. It depends on yt-dlp for transcript extraction and an LLM provider for the report summary section, with Ollama documented as one setup option.

    GitHub stars
    52
    Stars over the last 90 days: 49 at the earliest of 11 readings and 52 at the latest, up 3.
    Stars / 30 days
    0
    npm / typical week
    Ships no npm package
    PyPI / typical week
    downloads not counted
    mcp-youtube-intelligence
    Tools exposed
    10
    Last commit
    40 days ago
    Commits / 12 weeks
    1
    Weekly commits over the last 12 weeks, oldest first: 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0. 1 in total, and the last figure is the current week so far.
    Maintenance grade
    B
    Tool descriptions
    A
    Score 47.3: 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
    • Maintenance83 / 100 · weight 24%
      • Last commit touching this server100
      • Repository maintenance grade80
      • Commit cadence40
    • Momentum0 / 100 · weight 14%
      • Stars gained, relative to size0
      • Stars gained, absolute0
      • npm download trendnot measured
        no download history for the selected registry
    • 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
    55.6
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: modest but real audience
    0.85
    Composite score
    47.3
  • 20

    YouTube Transcript + Search MCP

    Emerging▼ 2
    tubeagentkit/youtube-mcp ↗

    Best for: Teams needing YouTube transcripts plus channel and playlist search without local install: it exposes remote transcript, search, channel browsing, in-channel search, and playlist extraction.

    The server is a hosted MCP endpoint for retrieving YouTube transcripts, searching videos and channels, browsing a channel's uploads, searching within a channel, and extracting playlist videos. It assumes a free getyoutubetranscript.com account and either an API key or OAuth 2.1 sign-in.

    GitHub stars
    27
    Stars over the last 90 days: 0 at the earliest of 9 readings and 27 at the latest, up 27.
    Stars / 30 days
    +27
    npm / typical week
    Ships no npm package
    PyPI / typical week
    no attributed package
    Tools exposed
    never inspected
    Last commit
    2 days ago
    Commits / 12 weeks
    27
    Weekly commits over the last 12 weeks, oldest first: 0, 0, 0, 0, 0, 0, 0, 5, 0, 7, 15, 0. 27 in total, and the last figure is the current week so far.
    Maintenance grade
    A
    Tool descriptions
    Not graded
    Score 47.3: show every number behind it
    • Adoption36 / 100 · weight 40%
      • GitHub stars36
      • npm downloadsnot measured
        no npm package
      • 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
    • Momentum83 / 100 · weight 14%
      • Stars gained, relative to size100
      • Stars gained, absolute58
      • npm download trendnot measured
        no download history for the selected registry
    • Tool quality≈70 / 100 · weight 13%
      • Tool description quality≈70
        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
    67.6
    × relevance: the keyword is dedicated here
    1.00
    × continuity: actively changing
    1.00
    × evidence: small audience
    0.70
    Composite score
    47.3

Questions people ask

How do I choose between YouTube Transcript MCP Server and mcp-youtube?

Pick YouTube Transcript MCP Server (jkawamoto/mcp-youtube-transcript) when you need transcript and metadata extraction inside an MCP client: it exposes 4 tools with an A tool description grade for raw text, timed segments, languages, and video info. Pick mcp-youtube (kirbah/mcp-youtube) when the agent also needs search, comments, and channel statistics: it exposes 9 tools with an A tool description grade and its @kirbah/mcp-youtube package had 399 npm downloads in a typical week.

What does YouTube Skills for AI Agents require before it will run?

It installs as Agent Skills for Claude Code, Cursor, OpenClaw, and Hermes. There is no npm package published and no PyPI package attributed, so plan for that skill installation path rather than an npm or PyPI command.

Can these servers upload videos or manage playlists?

If you need uploads with OAuth2 multi-channel accounts, Youtube Uploader MCP documents upload_video and update_video for metadata, playlists, thumbnails, and captions. If you need broader YouTube operation, yutu automates uploads, comments, playlists, and channel branding through an MCP server, CLI, agent, and skill.

What should I check before using an abandoned but popular transcript server?

Check the activity figures: mcp-server-youtube-transcript (kimtaeyoon83/mcp-server-youtube-transcript) is Abandoned but popular, its last commit was 90 days ago, and it had 0 commits in the last 12 weeks. mcp-youtube-transcript (sinco-lab/mcp-youtube-transcript) is also Abandoned but popular, with its last commit 151 days ago and 0 commits in the last 12 weeks. If you need a maintained option, YouTube Transcript MCP Server (jkawamoto/mcp-youtube-transcript) had a commit 15 days ago and 35 commits in the last 12 weeks.

Which server can I use without a Google Cloud project or YouTube Data API key?

HasData/youtube-mcp provides read-only YouTube tools for search, video/channel data, and transcripts with no Google Cloud project or API key required. It exposes 4 tools and has an A tool description grade. content-core is another option: extract_content handles YouTube transcripts without an API key.

How active are the main transcript options?

mcp-youtube (kirbah/mcp-youtube) had a commit 7 days ago and 71 commits in the last 12 weeks. YouTube Transcript MCP Server (jkawamoto/mcp-youtube-transcript) had a commit 15 days ago and 35 commits in the last 12 weeks. YouTube Skills for AI Agents had a commit 27 days ago and 15 commits in the last 12 weeks.

Other comparisons