fetchtranscript-mcp
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FETCHTRANSCRIPT_API_KEY | Yes | Your FetchTranscript API key (starts with yt_). | |
| FETCHTRANSCRIPT_BASE_URL | No | Override API base URL (default: https://api.fetchtranscript.com). |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Access YouTube transcripts, video metadata, chapters, comments, channels, and search via the FetchTranscript API.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_transcriptA | Get the transcript of a YouTube video. Args: video_id: YouTube video ID (11 characters, e.g. 'dQw4w9WgXcQ') lang: Language code (e.g. 'en', 'it'). Auto-detected if omitted. format: Output format — 'text' (default), 'json' (segments with timestamps), or 'srt'. |
| list_languagesB | List available transcript languages for a YouTube video. Args: video_id: YouTube video ID (11 characters) |
| get_video_metadataB | Get metadata for a YouTube video (title, description, views, likes, etc.). Args: video_id: YouTube video ID (11 characters) |
| get_chaptersB | Get chapter list for a YouTube video. Args: video_id: YouTube video ID (11 characters) |
| get_commentsA | Get top comments on a YouTube video. Args: video_id: YouTube video ID (11 characters) limit: Number of comments to fetch (default 20, max 500) |
| get_channel_infoB | Get information about a YouTube channel. Args: channel_id: YouTube channel ID (UCxxxxxx format) or handle (@username) |
| list_channel_videosB | List videos from a YouTube channel. Args: channel_id: YouTube channel ID (UCxxxxxx format) or handle (@username) limit: Number of videos to return (default 10, max 100) offset: Number of videos to skip for pagination (default 0) include_shorts: Whether to include YouTube Shorts (default false) |
| search_videosC | Search YouTube videos. Args: query: Search query string limit: Number of results (default 5, max 50) |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| summarize_video | Summarize a YouTube video from its transcript. Args: video_id: YouTube video ID (e.g. 'dQw4w9WgXcQ') lang: Transcript language code (optional, auto-detected if omitted) |
| compare_videos | Compare multiple YouTube videos on similar topics. Args: video_ids: Comma-separated list of video IDs (e.g. 'abc123,def456,ghi789') |
| extract_quotes | Extract notable quotes from a YouTube video. Args: video_id: YouTube video ID topic: Optional topic to focus on (e.g. 'machine learning', 'productivity') |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| api_reference | Complete FetchTranscript API reference. |
| quickstart | Getting started with FetchTranscript MCP server. |
| pricing | FetchTranscript pricing and credit system. |
| examples | Common workflow examples. |
TDQS
Scored across 8 tools
Each tool targets a clearly distinct resource or action: transcript, comments, metadata, chapters, languages, channel info, channel video listing, and search. There is no meaningful overlap between any pair, and argument shapes reinforce the distinctions.
All tool names use a consistent snake_case verb_noun pattern (get_, list_, search_) with predictable resource suffixes. The use of get_ vs list_ vs search_ is semantically coherent and easy to follow.
Eight tools is well-scoped for a YouTube transcript and metadata server, with each tool earning its place. Nothing feels redundant or conspicuously absent from the count perspective.
The surface covers the core lifecycle well: transcript retrieval, language discovery, comments, metadata, chapters, channel info, channel videos, and search. Minor gaps exist—e.g., no comment-reply retrieval or in-transcript search—but agents can work around these for most transcript-focused workflows.