20 Best YouTube MCP Servers, Compared (November 2026)

The short answer

Which one, for your situation

Top MCP servers for YouTube

The ranking, with the evidence

• 1

  YouTube Skills for AI Agents

  Community favourite

  ZeroPointRepo/youtube-skills ↗

  Best for: Agents on cloud hosts that YouTube blocks: it fetches transcripts, search results, channel uploads and playlists over an HTTP API instead of yt-dlp.

  The repository ships Agent Skills packages, a youtube-full skill covering transcripts, search, channels and playlists plus smaller focused skills, installed via npx skills, ClawHub or Hermes and calling the TranscriptAPI HTTP service rather than yt-dlp. It requires a TranscriptAPI account and API key, which the agent obtains by registering an email address and entering a one-time code, so every retrieval depends on that third-party service.

  Score 81.0: show every number behind it

  • Adoption77 / 100 · weight 40%
    • GitHub stars77
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance79 / 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 5 days ago, which counts every ref; the stored date would have published 5 days ago
    • Repository maintenance grade55
    • Commit cadence85
  • Momentum95 / 100 · weight 14%
    • Stars gained, relative to size100
    • Stars gained, absolute86
    • 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

  81.0

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  81.0

• 2

  mcp-youtube

  Community favourite▲ 13

  kirbah/mcp-youtube ↗

  Best for: Fetching video transcripts without a YouTube API key: the server's zero-config mode supports reading transcripts from youtube://transcript/{videoId}.

  The server exposes nine tools for video details, video and channel search, transcript segments, comments, channel statistics, channel top videos, trending videos, video categories, and consistent outlier channel discovery. Unlocking all features requires a YouTube Data API v3 key, and optional MongoDB caching requires a MongoDB connection string.

  Score 76.4: show every number behind it

  • Adoption63 / 100 · weight 40%
    • GitHub stars38
    • npm downloads57
    • 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
  • Momentum59 / 100 · weight 14%
    • Stars gained, relative to size58
    • Stars gained, absolute27
    • npm download trend100
  • 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

  76.4

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  76.4

• 3

  YouTube MCP Server

  Community favourite▼ 1

  kevinwatt/yt-dlp-mcp ↗

  Best for: Downloading YouTube videos, audio, subtitles, or metadata from an MCP client: it wraps yt-dlp with tools for search, metadata, transcripts, and downloads.

  The server connects yt-dlp to MCP clients through documented tools for searching YouTube, extracting metadata, listing and downloading subtitles, downloading video, and extracting audio. It requires yt-dlp to be installed separately on the host system before the MCP server is configured.

  Score 76.0: show every number behind it

  • Adoption66 / 100 · weight 40%
    • GitHub stars62
    • 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
  • Maintenance88 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade80
    • Commit cadence65
  • Momentum74 / 100 · weight 14%
    • Stars gained, relative to size77
    • Stars gained, absolute49
    • npm download trend100
  • 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

  76.0

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  76.0

• 4

  YouTube Transcript MCP Server

  Community favourite▼ 1

  jkawamoto/mcp-youtube-transcript ↗

  Best for: Pulling transcripts and metadata from YouTube videos into an MCP workflow: it exposes transcript, timed transcript, language-list, and video-info tools with pagination.

  The server exposes four MCP tools for YouTube URLs: get_transcript, get_timed_transcript, get_available_languages, and get_video_info. The documented uvx installation requires uv to be installed first.

  Score 74.1: 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
  • Momentum44 / 100 · weight 14%
    • Stars gained, relative to size47
    • Stars gained, absolute40
    • 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

  74.1

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  74.1

• 5

  YouTube MCP Server

  Abandoned but popular

  ZubeidHendricks/youtube-mcp-server ↗

  Best for: Choosing and vetting individual YouTube creators by audience size and recent upload activity: it includes creator-discovery and channel search tools with subscriber and activity filters.

  YouTube MCP Server exposes 10 MCP tools for retrieving video and channel details, searching videos and channels, fetching transcripts, and reading playlist contents. The get tools require a YouTube video, channel, or playlist ID; only the search and find tools accept a query string.

  Score 66.7: 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
  • Maintenance63 / 100 · weight 24%
    • Last commit touching this server88
    • Repository maintenance grade55
    • Commit cadence5
  • Momentum50 / 100 · weight 14%
    • Stars gained, relative to size57
    • Stars gained, absolute48
    • npm download trend39
  • 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

  66.7

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  66.7

• 6

  YouTube MCP Server

  Community favourite▼ 2

  anaisbetts/mcp-youtube ↗

  Best for: Summarizing a specific YouTube video from its subtitles inside Claude: it exposes one download tool that pulls subtitles via yt-dlp for the URL given.

  The server exposes a single tool, download_youtube_url, which fetches subtitles for a YouTube URL using yt-dlp so Claude can read and summarize the video. It assumes yt-dlp is already installed locally (Homebrew and WinGet are both noted), and the README documents adding the server itself through mcp-installer under the name @anaisbetts/mcp-youtube.

  Score 65.5: 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
  • Maintenance73 / 100 · weight 24%
    • Last commit touching this server88
    • Repository maintenance grade30
    • Commit cadence85
  • Momentum17 / 100 · weight 14%
    • Stars gained, relative to size18
    • Stars gained, absolute16
    • 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

  65.5

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  65.5

• 7

  Anything-to-NotebookLM

  Abandoned but popular

  joeseesun/qiaomu-anything-to-notebooklm ↗

  Best for: Converting a YouTube video or paywalled article into a NotebookLM podcast or slide deck: the README documents source fetching, paywall bypass, upload, and generation workflows.

  The README documents a Claude Code skill with MCP setup that fetches content from sources such as YouTube, WeChat articles, podcasts, PDFs, and web pages, uploads it to Google NotebookLM, and generates outputs including podcasts, slides, mind maps, and quizzes. Before choosing it, note that setup requires Python 3.9+, cloning into the Claude skills directory, running install.sh, configuring MCP, and completing a one-time NotebookLM login.

  Score 62.6: 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 17 days ago, which counts every ref; the stored date would have published 17 days ago
    • Repository maintenance grade30
    • Commit cadence5
  • Momentum93 / 100 · weight 14%
    • Stars gained, relative to size89
    • Stars gained, absolute100
    • 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

  80.3

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  62.6

• 8

  yutu

  Community favourite

  eat-pray-ai/yutu ↗

  Best for: Automating YouTube channel workflows through an MCP client or CLI: it documents upload, comment, playlist, and branding operations.

  yutu documents a CLI, MCP server, and AI agent for YouTube workflows, including uploading videos and managing comments, playlists, and channel branding. Before choosing it, set up a Google Cloud project with the YouTube Data API v3 enabled and OAuth Desktop credentials; it reads client_secret.json and youtube.token.json by default.

  Score 61.2: 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
  • Maintenance95 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade80
    • Commit cadence100
  • Momentum65 / 100 · weight 14%
    • Stars gained, relative to size70
    • Stars gained, absolute57
    • 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

  78.5

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  61.2

• 9

  mcp-server-youtube-transcript

  Abandoned but popular▼ 3

  kimtaeyoon83/mcp-server-youtube-transcript ↗

  Best for: Fetching transcripts from YouTube videos with language fallback, optional timestamps, and default ad filtering: get_transcript accepts watch URLs, Shorts URLs, or video IDs.

  The server exposes get_transcript to extract YouTube captions and subtitles from watch URLs, Shorts URLs, or video IDs, with language fallback and optional timestamps. The README's optional analyze_video path is separate and requires a TwelveLabs API key plus a direct video URL, so a YouTube watch page will not work for it.

  Score 60.9: 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
  • Maintenance57 / 100 · weight 24%
    • Last commit touching this server88
    • Repository maintenance grade30
    • Commit cadence5
  • Momentum0 / 100 · weight 14%
    • Stars gained, relative to size0
    • Stars gained, absolute0
    • 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

  60.9

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  60.9

• 10

  mcp-openshorts

  Community favourite

  mutonby/openshorts ↗

  Best for: People turning long videos into vertical social clips: the server exposes process_video and tools for job status, clip listing, subtitles, recuts, quota and publishing.

  It exposes eight MCP tools for starting clip jobs from a video URL or an uploaded file, checking job status and quota, listing and recutting clips, restyling subtitles, and publishing clips to connected social accounts. Before choosing it, note that the self-hosted MCP endpoint requires Docker and the user's own Gemini, ElevenLabs, and fal.ai API keys, and it is reachable only while the host machine is on.

  Score 57.2: show every number behind it

  • Adoption97 / 100 · weight 40%
    • GitHub stars97
    • 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
  • 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

  95.3

  × relevance: the keyword is tagged here

  0.60

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  57.2

• 11

  youtube-marketing-skills

  Emerging▼ 2

  adityaarsharma/youtube-marketing-skills ↗

  Best for: Developers and consultants who want their agent to read private channel analytics and push updated titles, descriptions and tags back to YouTube via OAuth.

  It ships a Node MCP server alongside skill files that add slash commands such as /youtube-strategy and /youtube-seo, reading private channel analytics with YouTube Data API v3 and YouTube Analytics API credentials, writing metadata back to YouTube, and publishing a companion WordPress post. Setup assumes a local clone with Node.js 18+, a Google Cloud project with both YouTube APIs enabled, and a Desktop OAuth credentials file placed in the project directory before the one-time browser authentication runs.

  Score 57.1: show every number behind it

  • Adoption48 / 100 · weight 40%
    • GitHub stars48
    • npm downloadsnot measured
      no npm package
    • Used through Glamanot measured
      not used through Glama in the last 30 days
  • Maintenance77 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade55
    • Commit cadence40
  • 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

  67.2

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  57.1

• 12

  Youtube Uploader MCP

  Steady

  anwerj/youtube-uploader-mcp ↗

  Best for: Uploading and managing videos on your own YouTube channel from an MCP client: it exposes authenticate, upload_video, update_video, and list_videos tools.

  Youtube Uploader MCP documents OAuth2 tooling for authentication and token refresh (authenticate, accesstoken, channels, refreshtoken) alongside video tools: upload_video sets title, description, tags, category, privacy status and scheduled publish time, update_video handles playlists, thumbnails and caption tracks plus later visibility changes, and list_videos lists a channel's videos. Before installing, note that it ships as a downloadable release binary with no npm or PyPI package, and it assumes a Google OAuth client_secret.json from the Google Developer Console, with subtitle uploads requiring the youtube.force-ssl scope and therefore a re-authentication over any older saved token.

  Score 56.4: 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
  • Maintenance88 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade80
    • Commit cadence65
  • Momentum64 / 100 · weight 14%
    • Stars gained, relative to size80
    • Stars gained, absolute39
    • 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

  66.4

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  56.4

• 13

  content-core

  Steady▼ 2

  lfnovo/content-core ↗

  Best for: Extracting YouTube transcripts and other URL or file content: extract_content handles web pages, PDFs, documents, and YouTube transcripts without an API key for most sources.

  The server exposes two MCP tools: extract_content for URLs and files including YouTube transcripts, PDFs, and documents, and summarize_content for LLM summaries. Summarization requires an LLM provider key such as OPENAI_API_KEY, while extraction does not require an API key for most sources.

  Score 56.3: show every number behind it

  • Adoption57 / 100 · weight 40%
    • GitHub stars57
    • npm downloadsnot measured
      no npm package
    • 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
  • Momentum64 / 100 · weight 14%
    • Stars gained, relative to size77
    • Stars gained, absolute44
    • 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

  72.2

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  56.3

• 14

  YouTube for AI Agents

  Dormant▼ 1

  JCodesMore/youtube-for-ai-agents ↗

  Best for: For searching, transcribing, and clipping YouTube videos in chat: it exposes 9 tools covering search, transcripts, metadata, downloads, and clips without an API key.

  YouTube for AI Agents exposes 9 MCP tools for YouTube search, transcript retrieval, video and channel metadata, playlist listing, downloads, clip extraction, and highlight-reel assembly. It requires Node.js 18 or later and relies on an unofficial YouTube client that is not affiliated with YouTube or Google.

  Score 50.0: show every number behind it

  • Adoption47 / 100 · weight 40%
    • GitHub stars45
    • 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
  • Momentum65 / 100 · weight 14%
    • Stars gained, relative to size92
    • Stars gained, absolute43
    • npm download trend44
  • 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

  58.8

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  50.0

• 15

  Web Researcher MCP

  Emerging▼ 1

  zoharbabin/web-researcher-mcp ↗

  Best for: YouTube research where transcripts feed a citation workflow: scrape_page extracts YouTube transcripts, and verify_citation checks whether cited sources resolve.

  Web Researcher MCP exposes 25 tools for web search, scraping pages and YouTube transcripts, extracting PDF/DOCX content, academic and patent search, citation verification, bibliography formatting, and multi-step research session tracking. Before choosing it, note that the one-click Cursor, VS Code, and LM Studio installs assume uv is installed.

  Score 49.0: show every number behind it

  • Adoption47 / 100 · weight 40%
    • GitHub stars47
    • 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
  • Momentum73 / 100 · weight 14%
    • Stars gained, relative to size93
    • Stars gained, absolute44
    • 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

  73.9

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  49.0

• 16

  mcp-video-analyzer

  EmergingNew

  guimatheus92/mcp-video-analyzer ↗

  Best for: Reading a YouTube video inside an agent instead of watching it: eight tools return transcript, key frames, OCR text, metadata and comments.

  It runs as an MCP server (and as a one-shot CLI) exposing eight tools including analyze_video, get_transcript, get_frames, get_frame_burst and analyze_moment, which return timestamped transcripts, key frames, OCR text and annotated timelines from video URLs. Platform links such as YouTube require yt-dlp to be installed separately and Node.js 22.12+ to run via npx, while direct video URLs and local files fall back to bundled ffmpeg-static.

  Score 48.1: show every number behind it

  • Adoption57 / 100 · weight 40%
    • GitHub stars52
    • npm downloads30
      downloads show none of the weekday rhythm human traffic has; halved
    • Used through Glama33
  • Maintenance100 / 100 · weight 24%
    • Last commit touching this server100
    • Repository maintenance grade100
    • Commit cadence100
  • Momentum88 / 100 · weight 14%
    • Stars gained, relative to size100
    • Stars gained, absolute60
    • npm download trend100
  • Tool quality93 / 100 · weight 13%
    • Tool description quality85
    • 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

  80.2

  × relevance: the keyword is tagged here

  0.60

  × continuity: actively changing

  1.00

  × evidence: widely adopted

  1.00

  Composite score

  48.1

• 17

  MCP YouTube Intelligence

  Steady▼ 1

  JangHyuckYun/mcp-youtube-intelligence ↗

  Best for: YouTube video and channel analysis when context is limited: it summarizes transcripts on the server and returns structured entities, topics, and comment sentiment.

  It exposes 10 MCP tools for video metadata and transcript summaries, comments, RSS channel monitoring, transcript and YouTube search, entity extraction, topic segmentation, playlists, and report generation. Transcript extraction depends on yt-dlp, and report summaries require an LLM provider such as Ollama or a configured cloud API key.

  Score 47.7: 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
  • Maintenance70 / 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 4 days ago, which counts every ref; the stored date would have published 4 days ago
    • Repository maintenance grade55
    • Commit cadence40
  • Momentum25 / 100 · weight 14%
    • Stars gained, relative to size32
    • Stars gained, absolute14
    • 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

  56.1

  × relevance: the keyword is dedicated here

  1.00

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  47.7

• 18

  Arcmira: YouTube Transcript Search

  EmergingNew

  arcmira/mcp ↗

  Best for: Researching what was said on YouTube or podcasts: it searches transcripts for exact quotes with speakers and timestamped links.

  Arcmira is a hosted remote MCP server at https://mcp.arcmira.com/mcp that documents an arcmira_describe call for loading a client reference plus arcmira_execute_read and arcmira_execute_write tools covering transcript search, transcript reading, mentions, momentum, sponsors and monitor setup. It requires an Arcmira account reached either through host OAuth sign-in or an arc_sk_ bearer key, and its README notes that speaker identification and commercial classifications can be incomplete.

  Score 47.3: show every number behind it

  • Adoption39 / 100 · weight 40%
    • GitHub stars39
    • 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
  • Momentum78 / 100 · weight 14%
    • Stars gained, relative to size100
    • Stars gained, absolute45
    • 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

• 19

  Smartest-TV

  Emerging▼ 2

  Hybirdss/smartest-tv ↗

  Best for: Playing YouTube videos on a smart TV by name or URL: it exposes tv_play and tv_cast to resolve content and deep-link into the TV app.

  Smartest-TV exposes 23 tools for playing streaming content by name or URL on LG, Samsung, Android TV, and Roku televisions, along with power, volume, app, queue, scene, and multi-TV controls. It installs from the stv PyPI package rather than npm, and its README lists Python 3.11 or later.

  Score 46.6: show every number behind it

  • Adoption47 / 100 · weight 40%
    • GitHub stars44
    • PyPI downloads18
      PyPI downloads show no weekday rhythm; halved
    • 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
  • Momentum75 / 100 · weight 14%
    • Stars gained, relative to size84
    • Stars gained, absolute40
    • PyPI download trend100
  • 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

  70.3

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  46.6

• 20

  socialclaw

  EmergingNew

  ndesv21/socialclaw ↗

  Best for: Publishing scheduled YouTube content from an AI agent via MCP: it ships an MCP server for schedule validation, preview, apply, and post inspection.

  The repository documents a CLI and an MCP server for connecting a SocialClaw workspace, listing accounts and capabilities, uploading assets, validating and previewing schedules, applying them with idempotency keys, and inspecting posts, runs, analytics, usage, and health. Before choosing it, note that access requires a workspace API key and an active trial or paid plan, with the MCP server launched through npx.

  Score 45.3: show every number behind it

  • Adoption54 / 100 · weight 40%
    • GitHub stars51
    • npm downloads22
      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
      dated from the last commit on the default branch, re-read from GitHub at publication; github.com shows a push 27 days ago, which counts every ref; the stored date would have published 27 days ago
    • Repository maintenance grade55
    • Commit cadence40
  • Momentum84 / 100 · weight 14%
    • Stars gained, relative to size98
    • Stars gained, absolute48
    • npm download trend100
  • 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

  68.3

  × relevance: the keyword is declared here

  0.78

  × continuity: actively changing

  1.00

  × evidence: modest but real audience

  0.85

  Composite score

  45.3

Questions people ask

Other comparisons

• Best Figma MCP servers
• Best Obsidian MCP servers
• Best Jira MCP servers
• Best PostgreSQL MCP servers
• Best MySQL MCP servers
• Best GitHub MCP servers
• Best Slack MCP servers
• Best Notion MCP servers
• Best Linear MCP servers
• Best Discord MCP servers
• Best MongoDB MCP servers
• Best CRM MCP servers
• Best Payments MCP servers
• Best Ecommerce MCP servers
• Best Social Media MCP servers
• Best Browser Automation MCP servers
• Best CMS MCP servers
• Best Email MCP servers
• Best PDF MCP servers
• Best Kubernetes MCP servers
• Best Docker MCP servers
• Best AWS MCP servers
• Best Spreadsheets MCP servers
• Best SEO MCP servers
• Best Web Search MCP servers
• Best Web Scraping MCP servers
• Best Vector Database MCP servers
• Best Code Execution MCP servers
• Best Calendar MCP servers
• Best Observability MCP servers
• Best Image Generation MCP servers
• Best Speech & Transcription MCP servers
• Best Maps MCP servers
• Best Travel MCP servers
• Best Stock Market MCP servers
• Best Web Analytics MCP servers
• Best Memory MCP servers
• Best Documentation MCP servers
• Best Security MCP servers