20 Best YouTube MCP Servers, Compared (October 2026)
The short answer
Most readers who need YouTube transcripts, search, channels, and playlists inside an agent should reach for YouTube Skills for AI Agents. It is a Community favourite with 964 GitHub stars, 259 stars gained per 30 days, and a commit 6 days ago. If you want a zero-config transcript fetcher with a published npm package, mcp-youtube is the better answer: it exposes getTranscripts, supports a zero-config install for transcript retrieval, and its @kirbah/mcp-youtube package had 427 downloads in a typical week, with 9 tools and an A grade for tool descriptions. If you need uploads from an MCP client instead, Youtube Uploader MCP exposes upload_video with OAuth2 authentication and multi-channel token management.
Whichever you choose, give it the narrowest access that still works (a read-only credential, a replica, a scratch account), and widen it only once you have watched what your agent actually asks for.
Glama operates the MCP registry these numbers are measured from, and sells MCP hosting and a gateway. No position on this page is paid for. How the registry is built.
Quick picks
- 1YouTube Skills for AI Agents : AI agents on OpenClaw, Hermes, Claude Code, or Cursor needing YouTube transcripts, search, channels, and playlists: it ships Agent Skills for those tasks.
- 2YouTube Transcript MCP Server : Pulling YouTube transcripts into Goose CLI or Goose Desktop: it exposes four tools for transcripts, timed transcripts, video info, and available languages.
- 3YouTube MCP Server : Vetting YouTube creators from video mentions: it exposes creator discovery with subscriber-band and recent-upload filters, plus channel lookups.
- 4mcp-youtube : Fetching YouTube transcripts without an API key: it exposes getTranscripts and supports a zero-config install for transcript retrieval.
- 5YouTube MCP Server : Summarizing a YouTube video from its subtitles: it exposes a single download_youtube_url tool that fetches subtitles for Claude to read.
Which one, for your situation
| Your situation | What to use |
|---|---|
| I need YouTube transcripts in Claude Code or Cursor | YouTube Skills for AI Agents ships Agent Skills for those tasks and had 964 GitHub stars with 259 stars gained per 30 days. |
| I want zero-config transcript fetching without an API key | mcp-youtube exposes getTranscripts and supports a zero-config install for transcript retrieval, with 9 tools and tool description grade A. |
| I need creator discovery and channel lookups | YouTube MCP Server (ZubeidHendricks/youtube-mcp-server) exposes creator discovery with subscriber-band and recent-upload filters plus channel lookups, and its npm package had 350 downloads in a typical week. |
| I need to upload videos with OAuth2 and multi-channel support | Youtube Uploader MCP exposes an upload_video tool plus OAuth2 authentication and multi-channel token management, and had a commit 7 days ago. |
| I need to turn long videos into vertical clips | mcp-openshorts exposes process_video, get_job_status, list_clips and publish_clip, with 8 tools, tool description grade A, and 337 commits in the last 12 weeks. |
| I need to automate YouTube channel operations from shell | yutu ships both a CLI and an MCP server for uploads, playlists, comments, and branding, with 85 commits in the last 12 weeks and a commit 2 days ago. |
Top MCP servers for YouTube
| Best for | Profile | ||||||
|---|---|---|---|---|---|---|---|
| 1 | AI agents on OpenClaw, Hermes, Claude Code, or Cursor needing YouTube transcripts, search, channels, and playlists: it ships Agent Skills for those tasks. | Community favourite | 964 | +259 | 6 days ago | 82.4 | |
| 2 | Pulling YouTube transcripts into Goose CLI or Goose Desktop: it exposes four tools for transcripts, timed transcripts, video info, and available languages. | Community favourite | 484 | +13 | 3 days ago | 75.3 | |
| 3 | Vetting YouTube creators from video mentions: it exposes creator discovery with subscriber-band and recent-upload filters, plus channel lookups. | Community favourite | 577 | +9 | 50 days ago | 71.8 | |
| 4 | Fetching YouTube transcripts without an API key: it exposes getTranscripts and supports a zero-config install for transcript retrieval. | Community favourite | 29 | 0 | 16 days ago | 70.7 | |
| 5 | Summarizing a YouTube video from its subtitles: it exposes a single download_youtube_url tool that fetches subtitles for Claude to read. | Community favourite | 546 | +3 | 42 days ago | 69.6 | |
| 6 | Pulling YouTube transcripts and metadata into an AI agent: it exposes ytdlp_ tools for searching videos, listing subtitle languages, and downloading subtitles. | Community favourite | 280 | +4 | 47 days ago | 67.9 | |
| 7 | Pulling captions from YouTube videos or Shorts into an MCP client: it exposes get_transcript with language fallback, optional timestamps, and ad filtering. | Abandoned but popular | 598 | +10 | 69 days ago | 67.4 | |
| 8 | Automating YouTube channel operations from an agent or a shell: it ships both a CLI and an MCP server for uploads, playlists, comments, and branding. | Community favourite | 693 | +85 | 2 days ago | 65.0 | |
| 9 | Turning a YouTube video into a NotebookLM podcast, slide deck, or mind map: it documents automatic subtitle extraction and NotebookLM upload. | Abandoned but popular | 6,147 | +351 | 153 days ago | 63.1 | |
| 10 | Pulling a YouTube transcript locally for analysis: it fetches transcript text, timestamped lines and video metadata through an npx or Docker install. | Abandoned but popular | 37 | +1 | 130 days ago | 58.7 | |
| 11 | Extracting YouTube transcripts and documents without an API key for most sources: it exposes extract_content, plus summarize_content for LLM summaries. | Steady | 174 | +7 | 21 days ago | 56.5 | |
| 12 | Scheduling and publishing YouTube content through an agent: it ships an MCP server and CLI for validating, previewing, applying, and inspecting social publishing schedules. | Steady | 92 | +9 | 34 days ago | 56.1 | |
| 13 | Uploading videos to YouTube from an MCP client: it exposes an upload_video tool plus OAuth2 authentication and multi-channel token management. | Steady | 54 | +4 | 7 days ago | 54.8 | |
| 14 | Turning a long video into vertical clips with captions and posting them: it exposes process_video, get_job_status, list_clips and publish_clip. | Community favourite | 5,679 | +2,597 | today | 51.1 | |
| 15 | Monitoring YouTube channels and pulling structured video reports: an MCP stdio server whose ten tools include channel monitoring, transcript summaries, entity extraction, and report generation. | Steady | 52 | +1 | 19 days ago | 50.4 | |
| 16 | Research workflows that must cite verifiable sources: it exposes citation verification, bibliography auditing, and archive snapshot tools alongside web and academic search. | Emerging | 63 | +11 | 19 days ago | 48.9 | |
| 17 | Educational YouTube channels needing private analytics and metadata write-back: it reads OAuth analytics, updates YouTube titles, descriptions, and tags, and publishes WordPress companion posts. | Dormant | 44 | +9 | 137 days ago | 48.2 | |
| 18 | Turning long YouTube videos into transcripts or clips inside a chat: it exposes search, transcript, download, clip and highlight reel tools with no API key. | Dormant | 52 | +3 | 150 days ago | 45.4 | |
| 19 | Building a persistent YouTube knowledge base with visual frame analysis: it ingests videos into a wiki and answers queries via an FTS5-backed agent. | Abandoned but popular | 158 | +9 | 167 days ago | 44.9 | |
| 20 | When a local LLM needs Google search, YouTube transcription, and OCR without API keys: it exposes 38 tools including google_search, transcribe_video, and ocr_image. | Steady | 128 | +4 | 42 days ago | 44.0 |
The ranking, with the evidence
Each position is a weighted mean of adoption (40%), maintenance (24%), momentum (14%), tool description quality (13%) and trust (9%), multiplied by three attenuators: how directly the server is about YouTube (named for it, declaring it, tagged with it, or merely mentioning it), whether its repository is still moving, and how much independent evidence of adoption it has. Open the score on any entry to see every number, including the ones marked ≈, which were imputed from the median of the other candidates rather than measured. The maintenance grade on each entry is mostly issue responsiveness, release recency and open security alerts rather than commits, so a recent commit beside a low grade is two different measurements rather than a contradiction.
- Abandoned but popular: People use it, but its default branch has stopped moving. Fine to keep running, risky to adopt.
- Community favourite: Widely adopted and still actively maintained.
- Dormant: Neither changing nor widely adopted. Here because it still matches the search.
- Emerging: Small audience, growing quickly, maintained. The bet with the most upside.
- Steady: Maintained, modest audience, no surprises in either direction.
Best for: AI agents on OpenClaw, Hermes, Claude Code, or Cursor needing YouTube transcripts, search, channels, and playlists: it ships Agent Skills for those tasks.
YouTube Skills for AI Agents is an Agent Skills package that documents install commands for OpenClaw, Hermes Agent, Claude Code, Cursor, Antigravity, Cline, and Codex, and provides skills for transcripts, YouTube search, channel browsing, and playlist extraction. It requires a TranscriptAPI API key, and the documented setup registers an email address, verifies an OTP, and saves the key; the free tier includes 100 credits on signup.
GitHub stars964Stars / 30 days+259npm / typical weekShips no npm packagePyPI / typical weekno attributed packageTools exposednever inspectedLast commit6 days agoCommits / 12 weeks15Maintenance gradeCTool descriptionsNot gradedScore 82.4: show every number behind it
- Adoption75 / 100 · weight 40%
- GitHub stars75
- npm downloadsnot measuredno npm package
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance86 / 100 · weight 24%
- Last commit touching this server100
- Repository maintenance grade55
- Commit cadence85
- Momentum99 / 100 · weight 14%
- Stars gained, relative to size100
- Stars gained, absolute97
- npm download trendnot measuredno download history for the selected registry
- Tool quality≈70 / 100 · weight 13%
- Tool description quality≈70tool descriptions not yet scored
- Built and inspected by Glamanot measurednever built and inspected by Glama
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot 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
Best for: Pulling YouTube transcripts into Goose CLI or Goose Desktop: it exposes four tools for transcripts, timed transcripts, video info, and available languages.
The server retrieves transcripts for YouTube video URLs, exposing get_transcript, get_timed_transcript, get_video_info, and get_available_languages. Before choosing it, note that using the uvx installation path requires uv to be installed on the system.
GitHub stars484Stars / 30 days+13npm / typical weekShips no npm packagePyPI / typical weekno attributed packageTools exposed4Last commit3 days agoCommits / 12 weeks39Maintenance gradeBTool descriptionsAScore 75.3: show every number behind it
- Adoption67 / 100 · weight 40%
- GitHub stars67
- npm downloadsnot measuredno npm package
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance95 / 100 · weight 24%
- Last commit touching this server100
- Repository maintenance grade80
- Commit cadence100
- Momentum53 / 100 · weight 14%
- Stars gained, relative to size58
- Stars gained, absolute46
- npm download trendnot measuredno 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 measurednot published by the vendor it integrates
- Weighted mean of the five
- 75.3
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 75.3
Best for: Vetting YouTube creators from video mentions: it exposes creator discovery with subscriber-band and recent-upload filters, plus channel lookups.
The server exposes 10 MCP tools for YouTube video details and search, transcript retrieval, channel lookup and creator discovery, and playlist retrieval. The main caveat is that it ships as an npm package, with no PyPI package attributed, and transcript language falls back to YOUTUBE_TRANSCRIPT_LANG or en.
GitHub stars577Stars / 30 days+9npm / typical week350PyPI / typical weekno attributed packageTools exposed10Last commit50 days agoCommits / 12 weeks11Maintenance gradeBTool descriptionsCScore 71.8: show every number behind it
- Adoption73 / 100 · weight 40%
- GitHub stars69
- npm downloads27downloads show none of the weekday rhythm human traffic has; halved
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance85 / 100 · weight 24%
- Last commit touching this server88
- Repository maintenance grade80
- Commit cadence85
- Momentum49 / 100 · weight 14%
- Stars gained, relative to size45
- Stars gained, absolute40
- npm download trend67
- Tool quality48 / 100 · weight 13%
- Tool description quality40
- Built and inspected by Glama100
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot published by the vendor it integrates
- Weighted mean of the five
- 71.8
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 71.8
Best for: Fetching YouTube transcripts without an API key: it exposes getTranscripts and supports a zero-config install for transcript retrieval.
The server exposes 9 tools for YouTube Data API v3 data: getVideoDetails, searchVideos, getTranscripts, getVideoComments, getChannelStatistics, getChannelTopVideos, getTrendingVideos, getVideoCategories, and findConsistentOutlierChannels. One thing worth knowing before choosing it: search and analytics need a YouTube Data API v3 key, while transcript retrieval can work without one and MongoDB caching needs a connection string.
GitHub stars29Stars / 30 days0npm / typical week427PyPI / typical weekno attributed packageTools exposed9Last commit16 days agoCommits / 12 weeks59Maintenance gradeBTool descriptionsAScore 70.7: show every number behind it
- Adoption62 / 100 · weight 40%
- GitHub stars37
- npm downloads56
- Used through Glama29
- Maintenance95 / 100 · weight 24%
- Last commit touching this server100
- Repository maintenance grade80
- Commit cadence100
- Momentum23 / 100 · weight 14%
- Stars gained, relative to size0
- Stars gained, absolute0
- npm download trend92
- Tool quality85 / 100 · weight 13%
- Tool description quality77
- Built and inspected by Glama100
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot published by the vendor it integrates
- Weighted mean of the five
- 70.7
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 70.7
Best for: Summarizing a YouTube video from its subtitles: it exposes a single download_youtube_url tool that fetches subtitles for Claude to read.
The server exposes one tool, download_youtube_url, which downloads subtitles from a YouTube URL so Claude can read them. It assumes yt-dlp is installed locally, for example via Homebrew or WinGet, and is added through mcp-installer under the name @anaisbetts/mcp-youtube.
GitHub stars546Stars / 30 days+3npm / typical weekdownloads not countedPyPI / typical weekno attributed packageTools exposed1Last commit42 days agoCommits / 12 weeks13Maintenance gradeCTool descriptionsAScore 69.6: show every number behind it
- Adoption68 / 100 · weight 40%
- GitHub stars68
- npm downloadsnot measurednpm names no repository for @anaisbetts/mcp-youtube, so its downloads cannot be attributed
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance86 / 100 · weight 24%
- Last commit touching this server100
- Repository maintenance grade55
- Commit cadence85
- Momentum25 / 100 · weight 14%
- Stars gained, relative to size26
- Stars gained, absolute24
- npm download trendnot measuredno 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 measurednot published by the vendor it integrates
- Weighted mean of the five
- 69.6
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 69.6
Best for: Pulling YouTube transcripts and metadata into an AI agent: it exposes ytdlp_ tools for searching videos, listing subtitle languages, and downloading subtitles.
It wraps yt-dlp behind MCP, exposing tools prefixed ytdlp_ for searching YouTube, reading video metadata, listing subtitle languages, downloading subtitles in VTT, and saving trimmed video or audio files, with setup documented for Claude Code, Claude Desktop, Cursor, VS Code, Windsurf, Cline, Warp, JetBrains, and Dive. The requirement worth knowing is that yt-dlp must be installed on the machine first (winget, brew, or pip) before the npx server definition will work, since the README lists it as a prerequisite rather than something the npm package provides.
GitHub stars280Stars / 30 days+4npm / typical week252PyPI / typical weekno attributed packageTools exposednever inspectedLast commit47 days agoCommits / 12 weeks1Maintenance gradeATool descriptionsNot gradedScore 67.9: show every number behind it
- Adoption65 / 100 · weight 40%
- GitHub stars61
- npm downloads26downloads show none of the weekday rhythm human traffic has; halved
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance81 / 100 · weight 24%
- Last commit touching this server88
- Repository maintenance grade100
- Commit cadence40
- Momentum31 / 100 · weight 14%
- Stars gained, relative to size41
- Stars gained, absolute29
- npm download trend14
- Tool quality≈70 / 100 · weight 13%
- Tool description quality≈70tool descriptions not yet scored
- Built and inspected by Glamanot measurednever built and inspected by Glama
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot published by the vendor it integrates
- Weighted mean of the five
- 67.9
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 67.9
Best for: Pulling captions from YouTube videos or Shorts into an MCP client: it exposes get_transcript with language fallback, optional timestamps, and ad filtering.
mcp-server-youtube-transcript exposes get_transcript, which accepts a YouTube URL, Shorts URL, or video ID and returns captions or subtitles, with options for language, timestamps, and filtering sponsorships and ads. Before choosing it, note that it requires Node.js 18 or higher and transcript retrieval depends on captions or subtitles being available for the video.
GitHub stars598Stars / 30 days+10npm / typical weekdownloads not countedPyPI / typical weekno attributed packageTools exposed1Last commit69 days agoCommits / 12 weeks1Maintenance gradeFTool descriptionsAScore 67.4: show every number behind it
- Adoption69 / 100 · weight 40%
- GitHub stars69
- npm downloadsnot measurednpm names no repository for @kimtaeyoon83/mcp-server-youtube-transcript, so its downloads cannot be attributed
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance58 / 100 · weight 24%
- Last commit touching this server88
- Repository maintenance grade5
- Commit cadence40
- Momentum45 / 100 · weight 14%
- Stars gained, relative to size47
- Stars gained, absolute42
- npm download trendnot measuredno 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 measurednot 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: widely adopted
- 1.00
- Composite score
- 67.4
Best for: Automating YouTube channel operations from an agent or a shell: it ships both a CLI and an MCP server for uploads, playlists, comments, and branding.
yutu is a Go CLI that also runs as an MCP server, covering the workflows its README documents: uploading and optimizing videos, and managing comments, playlists, and channel branding. Before choosing it, note the prerequisite chain it assumes: a Google Cloud project with the YouTube Data API v3 enabled, OAuth desktop-app credentials saved as client_secret.json, and an interactive auth step that writes a token file before other subcommands run.
GitHub stars693Stars / 30 days+85npm / typical weekShips no npm packagePyPI / typical weekno attributed packageTools exposednever inspectedLast commit2 days agoCommits / 12 weeks85Maintenance gradeATool descriptionsNot gradedScore 65.0: show every number behind it
- Adoption71 / 100 · weight 40%
- GitHub stars71
- npm downloadsnot measuredno npm package
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance100 / 100 · weight 24%
- Last commit touching this server100
- Repository maintenance grade100
- Commit cadence100
- Momentum91 / 100 · weight 14%
- Stars gained, relative to size100
- Stars gained, absolute78
- npm download trendnot measuredno download history for the selected registry
- Tool quality≈70 / 100 · weight 13%
- Tool description quality≈70tool descriptions not yet scored
- Built and inspected by Glamanot measurednever built and inspected by Glama
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot published by the vendor it integrates
- Weighted mean of the five
- 83.3
- × relevance: the keyword is declared here
- 0.78
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 65.0
Best for: Turning a YouTube video into a NotebookLM podcast, slide deck, or mind map: it documents automatic subtitle extraction and NotebookLM upload.
The README documents a natural-language workflow that accepts WeChat articles, YouTube videos, podcast pages, web pages, documents, images, audio, and archives, extracts or transcribes their content, uploads it to Google NotebookLM, and requests outputs such as podcasts, slide decks, mind maps, quizzes, reports, infographics, or flashcards. One caveat is that setup assumes Python 3.9+, cloning into the Claude skills directory, a one-time NotebookLM login, and optional Get笔记 API credentials for Xiaoyuzhou, Ximalaya, or Bilibili transcription.
GitHub stars6,147Stars / 30 days+351npm / typical weekShips no npm packagePyPI / typical weekno attributed packageTools exposednever inspectedLast commit153 days agoCommits / 12 weeks0Maintenance gradeDTool descriptionsNot gradedScore 63.1: show every number behind it
- Adoption95 / 100 · weight 40%
- GitHub stars95
- npm downloadsnot measuredno npm package
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance46 / 100 · weight 24%
- Last commit touching this server68
- Repository maintenance grade30
- Commit cadence5
- Momentum99 / 100 · weight 14%
- Stars gained, relative to size98
- Stars gained, absolute100
- npm download trendnot measuredno download history for the selected registry
- Tool quality≈70 / 100 · weight 13%
- Tool description quality≈70tool descriptions not yet scored
- Built and inspected by Glamanot measurednever built and inspected by Glama
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot published by the vendor it integrates
- Weighted mean of the five
- 80.9
- × relevance: the keyword is declared here
- 0.78
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 63.1
Best for: Pulling a YouTube transcript locally for analysis: it fetches transcript text, timestamped lines and video metadata through an npx or Docker install.
The README documents get_transcripts for pulling transcript text, with get_transcript as a compatibility alias, get_timed_transcript for one timestamped line per caption segment, and get_video_info for video metadata, configured as a local npx or Docker process for Claude Desktop, Cursor, Cline, and other MCP clients. Worth knowing before choosing it: it assumes Node.js 18 or higher on the machine, because transcript requests are made from the local install rather than a remote proxy.
GitHub stars37Stars / 30 days+1npm / typical week403PyPI / typical weekno attributed packageTools exposed1Last commit130 days agoCommits / 12 weeks0Maintenance gradeDTool descriptionsAScore 58.7: show every number behind it
- Adoption61 / 100 · weight 40%
- GitHub stars39
- npm downloads55
- Used through Glamanot measurednot 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 size35
- Stars gained, absolute15
- npm download trend42
- Tool quality76 / 100 · weight 13%
- Tool description quality68
- Built and inspected by Glama100
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot 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
Best for: Extracting YouTube transcripts and documents without an API key for most sources: it exposes extract_content, plus summarize_content for LLM summaries.
content-core provides an MCP server that exposes two tools: extract_content for pulling content from URLs, documents, videos, and audio, and summarize_content for LLM-based summaries. Before choosing it, note that summarize_content requires an LLM provider key such as OPENAI_API_KEY, while extract_content does not require an API key for most sources.
GitHub stars174Stars / 30 days+7npm / typical weekShips no npm packagePyPI / typical weekno attributed packageTools exposed2Last commit21 days agoCommits / 12 weeks30Maintenance gradeATool descriptionsAScore 56.5: show every number behind it
- Adoption56 / 100 · weight 40%
- GitHub stars56
- npm downloadsnot measuredno npm package
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance100 / 100 · weight 24%
- Last commit touching this server100
- Repository maintenance grade100
- Commit cadence100
- Momentum51 / 100 · weight 14%
- Stars gained, relative to size61
- Stars gained, absolute37
- npm download trendnot measuredno download history for the selected registry
- Tool quality76 / 100 · weight 13%
- Tool description quality68
- Built and inspected by Glama100
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot published by the vendor it integrates
- Weighted mean of the five
- 72.4
- × relevance: the keyword is declared here
- 0.78
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 56.5
Best for: Scheduling and publishing YouTube content through an agent: it ships an MCP server and CLI for validating, previewing, applying, and inspecting social publishing schedules.
SocialClaw documents a CLI and an MCP server that connect workspace accounts and handle scheduling, validation, preview, application, and inspection of posts across social platforms including YouTube. One requirement before choosing it: the CLI works against a deployed SocialClaw workspace via API key auth, and an API key alone is not enough because the workspace must also have an active trial or paid plan for agent execution.
GitHub stars92Stars / 30 days+9npm / typical week126PyPI / typical weekno attributed packageTools exposednever inspectedLast commit34 days agoCommits / 12 weeks15Maintenance gradeATool descriptionsNot gradedScore 56.1: show every number behind it
- Adoption56 / 100 · weight 40%
- GitHub stars49
- npm downloads45
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance97 / 100 · weight 24%
- Last commit touching this server100
- Repository maintenance grade100
- Commit cadence85
- Momentum59 / 100 · weight 14%
- Stars gained, relative to size78
- Stars gained, absolute40
- npm download trend48
- Tool quality≈70 / 100 · weight 13%
- Tool description quality≈70tool descriptions not yet scored
- Built and inspected by Glamanot measurednever built and inspected by Glama
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot published by the vendor it integrates
- Weighted mean of the five
- 71.9
- × relevance: the keyword is declared here
- 0.78
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 56.1
Best for: Uploading videos to YouTube from an MCP client: it exposes an upload_video tool plus OAuth2 authentication and multi-channel token management.
Youtube Uploader MCP documents tools for OAuth2 authentication, channel listing, token refresh, video upload, post-upload updates, and video listing for MCP clients such as Claude, Cursor, and VS Code. Before choosing it, note that it requires a Google OAuth client_secret.json file and local authentication, and subtitle uploads need the youtube.force-ssl scope.
GitHub stars54Stars / 30 days+4npm / typical weekShips no npm packagePyPI / typical weekno attributed packageTools exposednever inspectedLast commit7 days agoCommits / 12 weeks5Maintenance gradeATool descriptionsNot gradedScore 54.8: show every number behind it
- Adoption44 / 100 · weight 40%
- GitHub stars44
- npm downloadsnot measuredno npm package
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance93 / 100 · weight 24%
- Last commit touching this server100
- Repository maintenance grade100
- Commit cadence65
- Momentum47 / 100 · weight 14%
- Stars gained, relative to size60
- Stars gained, absolute29
- npm download trendnot measuredno download history for the selected registry
- Tool quality≈70 / 100 · weight 13%
- Tool description quality≈70tool descriptions not yet scored
- Built and inspected by Glamanot measurednever built and inspected by Glama
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot published by the vendor it integrates
- Weighted mean of the five
- 64.5
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: modest but real audience
- 0.85
- Composite score
- 54.8
Best for: Turning a long video into vertical clips with captions and posting them: it exposes process_video, get_job_status, list_clips and publish_clip.
mcp-openshorts exposes eight tools that carry a video URL or an uploaded file through transcription, AI moment selection, vertical rendering, caption restyling, recutting and posting to connected TikTok, Instagram and YouTube accounts. Before choosing it, note that process_video consumes the authenticated user's plan minutes and fails with quota_exceeded when the balance is insufficient, and publish_clip needs a connected social profile.
GitHub stars5,679Stars / 30 days+2,597npm / typical weekShips no npm packagePyPI / typical weekno attributed packageTools exposed8Last committodayCommits / 12 weeks337Maintenance gradeBTool descriptionsAScore 51.1: show every number behind it
- Adoption94 / 100 · weight 40%
- GitHub stars94
- npm downloadsnot measuredno npm package
- Used through Glamanot measurednot 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 measuredno download history for the selected registry
- Tool quality83 / 100 · weight 13%
- Tool description quality75
- Built and inspected by Glama100
- Trust0 / 100 · weight 9%
- License0
- Published by the vendor it integratesnot measurednot published by the vendor it integrates
- Weighted mean of the five
- 85.2
- × relevance: the keyword is tagged here
- 0.60
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 51.1
- 15
Best for: Monitoring YouTube channels and pulling structured video reports: an MCP stdio server whose ten tools include channel monitoring, transcript summaries, entity extraction, and report generation.
MCP YouTube Intelligence exposes ten tools over stdio, covering video metadata and summaries, transcripts, comments, RSS channel monitoring, stored-transcript search, entity extraction, topic segmentation, YouTube search, playlists, and structured markdown reports, with a parallel mcp-yt CLI documented in the README. Before installing, note that transcript extraction assumes yt-dlp is present and that the report's summary section requires an LLM provider such as Ollama or a cloud API key, while basic extractive summaries work without one.
GitHub stars52Stars / 30 days+1npm / typical weekShips no npm packagePyPI / typical weekdownloads not countedmcp-youtube-intelligenceTools exposed10Last commit19 days agoCommits / 12 weeks1Maintenance gradeBTool descriptionsAScore 50.4: show every number behind it
- Adoption43 / 100 · weight 40%
- GitHub stars43
- npm downloadsnot measuredno npm package
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance83 / 100 · weight 24%
- Last commit touching this server100
- Repository maintenance grade80
- Commit cadence40
- Momentum26 / 100 · weight 14%
- Stars gained, relative to size34
- Stars gained, absolute15
- npm download trendnot measuredno 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 measurednot published by the vendor it integrates
- Weighted mean of the five
- 59.3
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: modest but real audience
- 0.85
- Composite score
- 50.4
- 16
Best for: Research workflows that must cite verifiable sources: it exposes citation verification, bibliography auditing, and archive snapshot tools alongside web and academic search.
The server exposes 25 tools covering web search and scraping, PDF, DOCX and YouTube transcript extraction, academic, patent, legal, clinical and economic search, plus citation verification, bibliography formatting and auditing, and Internet Archive snapshots. Its search tools route through third-party providers (Google, Brave, Serper, SearXNG) rather than an index of its own, and it ships as a single Go binary installed via uvx, Homebrew, an install script, or Docker.
GitHub stars63Stars / 30 days+11npm / typical weekShips no npm packagePyPI / typical weekno attributed packageTools exposed25Last commit19 days agoCommits / 12 weeks294Maintenance gradeATool descriptionsAScore 48.9: show every number behind it
- Adoption45 / 100 · weight 40%
- GitHub stars45
- npm downloadsnot measuredno npm package
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance100 / 100 · weight 24%
- Last commit touching this server100
- Repository maintenance grade100
- Commit cadence100
- Momentum75 / 100 · weight 14%
- Stars gained, relative to size96
- Stars gained, absolute44
- npm download trendnot measuredno download history for the selected registry
- Tool quality93 / 100 · weight 13%
- Tool description quality85
- Built and inspected by Glama100
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot published by the vendor it integrates
- Weighted mean of the five
- 73.8
- × relevance: the keyword is declared here
- 0.78
- × continuity: actively changing
- 1.00
- × evidence: modest but real audience
- 0.85
- Composite score
- 48.9
Best for: Educational YouTube channels needing private analytics and metadata write-back: it reads OAuth analytics, updates YouTube titles, descriptions, and tags, and publishes WordPress companion posts.
The README documents a skill suite plus MCP server that authenticates to a YouTube channel with OAuth, reads private analytics, writes titles, descriptions, and tags back to YouTube, and publishes companion WordPress posts from agent commands. The server requires Node.js 18+, a Google Cloud project with YouTube Data API v3 and YouTube Analytics API enabled, and OAuth 2.0 Desktop credentials.
GitHub stars44Stars / 30 days+9npm / typical weekShips no npm packagePyPI / typical weekno attributed packageTools exposednever inspectedLast commit137 days agoCommits / 12 weeks0Maintenance gradeCTool descriptionsNot gradedScore 48.2: show every number behind it
- Adoption41 / 100 · weight 40%
- GitHub stars41
- npm downloadsnot measuredno npm package
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance52 / 100 · weight 24%
- Last commit touching this server68
- Repository maintenance grade55
- Commit cadence5
- Momentum68 / 100 · weight 14%
- Stars gained, relative to size87
- Stars gained, absolute40
- npm download trendnot measuredno download history for the selected registry
- Tool quality≈70 / 100 · weight 13%
- Tool description quality≈70tool descriptions not yet scored
- Built and inspected by Glamanot measurednever built and inspected by Glama
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot published by the vendor it integrates
- Weighted mean of the five
- 56.7
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: modest but real audience
- 0.85
- Composite score
- 48.2
Best for: Turning long YouTube videos into transcripts or clips inside a chat: it exposes search, transcript, download, clip and highlight reel tools with no API key.
The server exposes nine tools for searching YouTube, fetching transcripts, video and channel metadata, playlists, downloads, clip extraction, and highlight reels, and its README documents installing it as a Claude Code plugin or wiring the published npm package into other MCP clients. Before choosing it, note that it requires Node.js 18 or later and that its README states it is built on an unofficial YouTube client and is not affiliated with, endorsed by, or associated with YouTube or Google.
GitHub stars52Stars / 30 days+3npm / typical week14PyPI / typical weekno attributed packageTools exposed9Last commit150 days agoCommits / 12 weeks0Maintenance gradeDTool descriptionsAScore 45.4: show every number behind it
- Adoption45 / 100 · weight 40%
- GitHub stars43
- npm downloads13downloads show none of the weekday rhythm human traffic has; halved
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance46 / 100 · weight 24%
- Last commit touching this server68
- Repository maintenance grade30
- Commit cadence5
- Momentum33 / 100 · weight 14%
- Stars gained, relative to size49
- Stars gained, absolute24
- npm download trend17
- Tool quality83 / 100 · weight 13%
- Tool description quality75
- Built and inspected by Glama100
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot published by the vendor it integrates
- Weighted mean of the five
- 53.4
- × relevance: the keyword is dedicated here
- 1.00
- × continuity: actively changing
- 1.00
- × evidence: modest but real audience
- 0.85
- Composite score
- 45.4
Best for: Building a persistent YouTube knowledge base with visual frame analysis: it ingests videos into a wiki and answers queries via an FTS5-backed agent.
The README documents a CLI and an MCP server that ingest YouTube videos, extract transcripts and scene-change frames, describe those frames with a vision model, and write a persistent JSON wiki indexed by SQLite FTS5 for agent querying. It assumes ffmpeg and an LLM vision model for ingestion, since scene-change detection and frame description are part of its documented pipeline.
GitHub stars158Stars / 30 days+9npm / typical weekShips no npm packagePyPI / typical weekno attributed packageTools exposednever inspectedLast commit167 days agoCommits / 12 weeks0Maintenance gradeFTool descriptionsNot gradedScore 44.9: show every number behind it
- Adoption55 / 100 · weight 40%
- GitHub stars55
- npm downloadsnot measuredno npm package
- Used through Glamanot measurednot used through Glama in the last 30 days
- Maintenance40 / 100 · weight 24%
- Last commit touching this server68
- Repository maintenance grade5
- Commit cadence5
- Momentum57 / 100 · weight 14%
- Stars gained, relative to size69
- Stars gained, absolute40
- npm download trendnot measuredno download history for the selected registry
- Tool quality≈70 / 100 · weight 13%
- Tool description quality≈70tool descriptions not yet scored
- Built and inspected by Glamanot measurednever built and inspected by Glama
- Trust100 / 100 · weight 9%
- License100
- Published by the vendor it integratesnot measurednot published by the vendor it integrates
- Weighted mean of the five
- 57.6
- × relevance: the keyword is declared here
- 0.78
- × continuity: actively changing
- 1.00
- × evidence: widely adopted
- 1.00
- Composite score
- 44.9
Best for: When a local LLM needs Google search, YouTube transcription, and OCR without API keys: it exposes 38 tools including google_search, transcribe_video, and ocr_image.
noapi-google-search-mcp exposes 38 tools for Google search, news, images, maps, finance, weather, shopping, books, translation, flights, hotels, Lens, OCR, document reading, media conversion, email fetching, URL shortening, QR generation, webpage archiving, Wikipedia, S3 uploads, and feed subscriptions with transcript search. Before choosing it, note that it runs through headless Chromium and local open-source models, and its no-API-key Google access can encounter CAPTCHAs or rate limits.
GitHub stars128Stars / 30 days+4npm / typical weekShips no npm packagePyPI / typical weekno attributed packageTools exposed38Last commit42 days agoCommits / 12 weeks4Maintenance gradeBTool descriptionsAScore 44.0: show every number behind it
- Adoption55 / 100 · weight 40%
- GitHub stars53
- npm downloadsnot measuredno npm package
- Used through Glama14
- Maintenance83 / 100 · weight 24%
- Last commit touching this server100
- Repository maintenance grade80
- Commit cadence40
- Momentum42 / 100 · weight 14%
- Stars gained, relative to size51
- Stars gained, absolute29
- npm download trendnot measuredno 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 measurednot published by the vendor it integrates
- Weighted mean of the five
- 66.4
- × relevance: the keyword is declared here
- 0.78
- × continuity: actively changing
- 1.00
- × evidence: modest but real audience
- 0.85
- Composite score
- 44.0
Questions people ask
Which YouTube MCP server should I use for transcripts without an API key?
mcp-youtube is the direct fit: it exposes getTranscripts and supports a zero-config install for transcript retrieval. Its @kirbah/mcp-youtube package had 427 downloads in a typical week, and it exposes 9 tools with tool description grade A. It also had 59 commits on its default branch in the last 12 weeks and a commit 16 days ago.
How do I choose between mcp-youtube and YouTube Transcript MCP Server (jkawamoto/mcp-youtube-transcript)?
YouTube Transcript MCP Server (jkawamoto/mcp-youtube-transcript) is built for Goose CLI or Goose Desktop and exposes 4 tools for transcripts, timed transcripts, video info, and available languages. It has tool description grade A and 39 commits on its default branch in the last 12 weeks. mcp-youtube exposes 9 tools and has a published npm package with 427 downloads in a typical week, so pick it if you want npm install and zero-config transcript retrieval; pick YouTube Transcript MCP Server (jkawamoto/mcp-youtube-transcript) if you are working inside Goose.
What does Youtube Uploader MCP require before it will run?
Youtube Uploader MCP uses an OAuth2 authentication flow and manages access tokens and refresh tokens. It supports multi-channel token management and exposes an upload_video tool. It had a commit 7 days ago and 5 commits on its default branch in the last 12 weeks.
Which servers have not been committed to recently?
Anything-to-NotebookLM had a commit 153 days ago and no commits on its default branch in the last 12 weeks, while its profile is Abandoned but popular. youtube-marketing-skills had a commit 137 days ago and no commits in the last 12 weeks, and mcptube-vision had a commit 167 days ago and no commits in the last 12 weeks. If you need active development, mcp-openshorts had 337 commits in the last 12 weeks, and yutu had 85 commits in the last 12 weeks with a commit 2 days ago.
Can these servers upload or schedule YouTube content?
Youtube Uploader MCP exposes an upload_video tool plus OAuth2 authentication and multi-channel token management. yutu ships both a CLI and an MCP server for uploads, playlists, comments, and branding. socialclaw ships an MCP server and CLI for validating, previewing, applying, and inspecting social publishing schedules, including YouTube. For a narrow upload tool, Youtube Uploader MCP; for channel operations, yutu; for broader social scheduling, socialclaw.
What should I check before pointing an agent at a YouTube MCP server?
Check whether the server exposes the tools you need and whether its tool descriptions are graded. For example, mcp-openshorts exposes 8 tools with tool description grade A, while YouTube MCP Server (ZubeidHendricks/youtube-mcp-server) exposes 10 tools with tool description grade C. Also check activity: mcp-openshorts had 337 commits in the last 12 weeks, while Anything-to-NotebookLM had no commits in the last 12 weeks and a commit 153 days ago. Check whether the repository was archived by its owner.