yt-transcript
Fetches YouTube transcripts, metadata, descriptions, and comments so an AI agent can read, summarize, and analyze video content — via MCP tools or CLI.
get_transcript_tool(url, languages?)— full video transcript, with optional preferred language codes (e.g."en,es,pt")list_transcripts_tool(url)— available captions, their languages, and whether they're auto-generatedget_video_info_tool(url)— fastest call for header facts only: title, channel, duration, upload dateget_video_details_tool(url, max_comments=50)— full description plus comments (author, text, likes); superset of the info toolAlso runs as a plain CLI (
yt-transcript VIDEO_ID --info --desc --json -l de,fr) for agents that shell outPlugs into opencode, Claude Code, Freebuff, Cursor, or any MCP-compatible client
Resilient by design: 4-layer fallback against YouTube bot checks/429s, disk cache for fast repeat calls, browser-cookie option
Zero config, zero API keys
Caveat: videos with no captions can't be transcribed (no Whisper/ASR)
Provides tools to fetch YouTube video transcripts, list available captions, retrieve video metadata (title, channel, duration, upload date), and get full descriptions plus comments (authors, text, likes) for analysis and summarization.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@yt-transcript summarize this video: https://youtu.be/dQw4w9WgXcQ"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
yt-transcript — YouTube Transcript MCP Server
Give your AI agent eyes for YouTube. A lightweight youtube transcript mcp server + CLI that fetches the transcript, description, and comments of any YouTube video — so your agent can read, summarize, and analyze video content.
Copy-paste in 30s / Copie e rode em 30s
git clone https://github.com/JADRT22/yt-transcript.git
cd yt-transcript
python3 -m venv .venv
.venv/bin/pip install -e .
.venv/bin/yt-transcript "https://www.youtube.com/watch?v=VIDEO_ID"🇧🇷 Em Português: servidor MCP + CLI de transcrição do YouTube (youtube transcript mcp server) — busca transcrição, descrição e comentários de qualquer vídeo para seu agente resumir e analisar, com cache em disco e fallback em 4 camadas contra bloqueio do YouTube.
Works with opencode, Claude Code, Freebuff, Cursor, and any MCP-compatible client — or as a plain CLI any agent can call.
Related MCP server: VidLens
Why this one?
YouTube aggressively blocks scripted access ("confirm you're not a bot", HTTP 429). Most transcript tools break the first time YouTube pushes back. This one ships a 4-layer fallback cascade baked in:
Layer | What it does |
1. | Fast path, no API key needed |
2. yt-dlp web client | Baseline fallback |
3. yt-dlp android client | Bypasses the "not a bot" check on most videos |
4. yt-dlp + browser cookies | Cures hard IP blocks / 429s (uses your Firefox/Chrome cookies) |
Plus:
Disk cache (
~/.cache/yt-transcript/) — second call for the same video is ~10x faster and consumes zero rate limitDescription + comments — likes, authors, replies; great context for richer summaries
Language aware — pick preferred languages; lists everything available per video
Zero config, zero API keys
Install
git clone https://github.com/JADRT22/yt-transcript.git
cd yt-transcript
python3 -m venv .venv
.venv/bin/pip install -e .MCP setup
Point your client at the server binary:
/absolute/path/to/yt-transcript/.venv/bin/yt-transcript-mcpIn ~/.config/opencode/opencode.json (global) or opencode.json (project):
{
"mcp": {
"yt-transcript": {
"type": "local",
"command": ["/absolute/path/to/yt-transcript/.venv/bin/yt-transcript-mcp"],
"enabled": true
}
}
}claude mcp add yt-transcript -- /absolute/path/to/yt-transcript/.venv/bin/yt-transcript-mcpCreate a mcp.json in the project root where the agent runs:
{
"mcpServers": {
"yt-transcript": {
"command": "/absolute/path/to/yt-transcript/.venv/bin/yt-transcript-mcp"
}
}
}Any agent that runs shell commands can read the output directly:
/absolute/path/to/yt-transcript/.venv/bin/yt-transcript "https://www.youtube.com/watch?v=VIDEO_ID"MCP tools
Tool | Description |
| Full transcript of the video |
| Available captions (languages, auto-generated?) |
| Header facts only: title, channel, duration, upload date |
| Full description + comments (author, text, likes) |
get_video_details_tool is a superset of get_video_info_tool — it returns
those same header fields plus the description and comments. Use
get_video_info_tool when you just need the basics and want the fastest call.
Example prompts once connected:
Summarize this video: https://www.youtube.com/watch?v=...
What are people saying in the comments of this video? [URL]
Compare what the video claims with what the description promises: [URL]CLI usage
# Full transcript (default languages: en, es, pt)
.venv/bin/yt-transcript "https://www.youtube.com/watch?v=VIDEO_ID"
# Metadata only
.venv/bin/yt-transcript VIDEO_ID --info
# Description + comments (JSON)
.venv/bin/yt-transcript VIDEO_ID --desc --max-comments 50
# Available captions
.venv/bin/yt-transcript VIDEO_ID --list
# JSON output / other languages
.venv/bin/yt-transcript VIDEO_ID --json
.venv/bin/yt-transcript VIDEO_ID -l de,frAccepts youtube.com/watch?v=..., youtu.be/..., youtube.com/shorts/..., or the bare 11-character ID.
Configuration
Environment variable | Default | Purpose |
|
| Browser for the cookie fallback ( |
|
| Cache directory ( |
To force a fresh fetch for one video, delete its file (SHA-256-named) from the cache directory.
How it works
extract_video_idnormalizes any YouTube URL format into a video ID.Transcripts: captions API first; on any failure, yt-dlp downloads the
.vttthrough the client cascade and converts it to plain text (each attempt only counts if the caption file is actually written — yt-dlp's simulation mode silently skips it, and--no-simulateguards that).Metadata/details:
yt-dlp --print/--dump-json --write-commentsthrough the same cascade.Everything is cached on disk; agents can retry cheaply.
Limitations
Videos with no captions at all can't be transcripted (no Whisper/ASR — this tool stays lightweight on purpose).
Browser-cookie access requires the target browser installed locally; in logged-in sessions YouTube sometimes serves empty format lists to yt-dlp, which is exactly why cookies are the last layer (and always paired with
--ignore-no-formats-error).Cache is content-blind: if a video's description/comments change, clear the cache entry.
License
MIT © 2026 JADRT22
Available Tools
4 toolsget_transcript_toolB
Returns the full transcript of a YouTube video.
Args: url: Video URL (youtube.com/watch?v=..., youtu.be/..., shorts/...) or ID. languages: Preferred language codes, comma-separated (e.g. "en,es,pt"). Defaults to the server default.
Returns: Transcript text with a metadata header, or an error message.
Inputs: url (required), languages. Returns: result
get_video_details_toolA
Returns title, channel, duration, FULL description and comments of a video.
Useful for understanding context, mentioned links and audience reception.
Args: url: Video URL or ID. max_comments: maximum number of comments (default 50).
Returns: JSON with description and a comments list (author, text, likes).
Inputs: url (required), max_comments. Returns: result
get_video_info_toolC
Returns video metadata: title, channel, duration and upload date.
Inputs: url (required). Returns: result
list_transcripts_toolA
Lists the captions/transcripts available for a video (languages and type).
Inputs: url (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
get_video_details_tool and get_video_info_tool overlap heavily, both returning title, channel and duration; the distinction (details adds description/comments, info adds upload date) is only implicit. get_transcript_tool and list_transcripts_tool are clearly separable, but the two metadata tools risk misselection.
All four tools follow a consistent verb_noun_tool pattern (get_video_details_tool, get_transcript_tool, list_transcripts_tool, get_video_info_tool) with uniform snake_case. Naming is highly predictable.
Four tools are well-scoped for a YouTube transcript/metadata server, each targeting a distinct operation. Slightly thin, and the count is partly inflated by two near-duplicate metadata tools that could be merged.
The surface covers listing available transcripts, fetching a transcript, retrieving metadata, and gathering description/comments, which spans the core domain lifecycle. No update/delete is needed for a read-only extractor, so coverage is solid with only minor gaps (e.g. no bulk or search operation).
Maintenance
Related MCP Connectors
YouTube for AI agents: transcripts, comments, video stats, channel monitor, Shorts captions.
YouTube transcripts, search, channel/playlist listings and upload tracking for AI agents.
YouTube transcripts for AI agents: 150+ languages, AI transcription fallback, search, summaries.
YouTube transcripts for AI agents: text, JSON, SRT, or VTT in 150+ languages, with AI fallback.
Related MCP Servers
- AlicenseBqualityNot gradedmaintenanceYouTube intelligence layer for AI agents. 41 tools across 10 modules ; search, explore, transcripts, comments, visual search, analytics, and more. Zero config.41179 npm-
- AlicenseCqualityCmaintenanceEnables AI agents to search, analyze, and extract insights from YouTube videos including transcripts, visual frames, and benchmarks without requiring API keys. Supports semantic search across playlists, sentiment analysis, and visual content indexing with automatic fallback chains for reliable access.41179 npm36MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to fetch transcripts, metadata, and download videos/audio from YouTube without API keys.33MIT
- AlicenseAqualityBmaintenanceAllows AI agents to fetch, search, and summarize YouTube video transcripts without an API key, including chapter summaries.4MIT