YouTube Summarizer MCP Server
Provides tools for fetching and searching YouTube video transcripts, including full text, timestamped segments, and stats. Allows AI agents to summarize videos via a prompt template.
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., "@YouTube Summarizer MCP Server summarize 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.
YouTube Summarizer MCP Server
An MCP (Model Context Protocol) server that fetches YouTube video transcripts and exposes them to AI agents as tools, resources, and prompts.
Works with any MCP client — OpenWork, Claude Desktop, or any custom MCP host.
Features
Tools (callable by agents)
Tool | Description |
| Full plain-text transcript |
| Case-insensitive search, returns matching lines with timestamps |
| Every line prefixed with |
Resources (readable by agents)
URI | Description |
| Full plain text |
| Timestamped segments |
| Word count, duration, estimated reading time |
Prompt
summarize_video(video_url, format_style)— generates a prompt template that asks the LLM to summarize a video. The LLM can read the transcript resource and return a summary in the requested format (default: bullet points).
Related MCP server: YouTube for AI Agents
Usage
Run directly
uv run --directory /path/to/yt-summarizer python3 summarizer.pyOr with the fastmcp CLI:
uv run --directory /path/to/yt-summarizer fastmcp run summarizer.pyConnect from Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"yt-summarizer": {
"command": "/path/to/uv",
"args": [
"run",
"--directory",
"/path/to/yt-summarizer",
"python3",
"summarizer.py"
]
}
}
}Connect from OpenWork
Add to opencode.jsonc:
{
"mcp": {
"youtube-summarizer": {
"type": "local",
"command": ["uv", "run", "--directory", "/path/to/yt-summarizer", "python3", "summarizer.py"],
"enabled": true
}
}
}Example
An agent can fetch and summarize a video in one interaction:
Agent reads
youtube://transcript/dQw4w9WgXcQ/stats— sees "1250 words, 5 min duration"Agent calls
get_youtube_transcript("https://youtube.com/watch?v=dQw4w9WgXcQ")— gets the full textAgent calls
search_transcript("https://youtube.com/watch?v=dQw4w9WgXcQ", "important topic")— finds relevant parts with timestampsAgent uses the
summarize_videoprompt template to format the final summary
Supported URL formats
https://youtube.com/watch?v=VIDEO_IDhttps://youtu.be/VIDEO_IDhttps://youtube.com/shorts/VIDEO_IDhttps://youtube.com/embed/VIDEO_IDhttps://youtube.com/v/VIDEO_ID
Requirements
Python 3.10+
fastmcp— MCP server frameworkyoutube-transcript-api— fetches YouTube transcripts
Project structure
yt-summarizer/
├── summarizer.py # Main MCP server
├── yt-summarizer.py # Original minimal version
├── yt-summarizer1.py # Older version with logging
├── pyproject.toml # Dependencies
├── plan.txt # Dev notes
└── README.mdAvailable Tools
3 toolsget_timestamped_transcriptB
Return the full transcript with [MM:SS] timestamps on each line. Useful when an agent needs to cite specific moments in the video.
Inputs: video_url (required). Returns: result
get_youtube_transcriptB
Fetch the full plain-text transcript of a YouTube video. Best for agents that want all text at once.
Inputs: video_url (required). Returns: result
search_transcriptA
Search inside a video transcript and return matching lines with timestamps. Case-insensitive. Helpful when an agent needs to find a specific topic.
Inputs: keyword (required), video_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 3 tools
Each tool has a clearly distinct purpose: one returns the full transcript with timestamps, one returns plain text, and one searches for specific terms. No ambiguity between them.
All tool names follow a consistent verb_noun pattern in snake_case (get_timestamped_transcript, get_youtube_transcript, search_transcript), making them predictable and easy to understand.
Three tools is well-scoped for a YouTube transcript server, covering the core needs without being too few or too many.
The set covers the main transcript retrieval and search functionality. A minor gap is the lack of a tool to get video metadata or list available transcripts, but it is still complete for typical summarization tasks.
Maintenance
Related MCP Connectors
YouTube transcripts, search, channel/playlist listings and upload tracking for AI agents.
YouTube transcripts, search, channels, playlists and bulk transcript jobs for AI agents. 14 tools.
YouTube transcripts for AI agents: 150+ languages, AI transcription fallback, search, summaries.
Transcripts, summaries, chapters and timestamped search for video links, for AI agents.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables AI tools to access YouTube content, including transcript extraction, video/channel info, and search.423 npmMIT
- AlicenseAqualityDmaintenanceEnables AI agents to search, watch, summarize, clip, and extract transcripts from YouTube videos, all without needing an API key or leaving the chat.914 npm67Apache 2.0
- FlicenseNot gradedqualityDmaintenanceEnables LLMs to interact with YouTube videos by fetching transcripts, summarizing content, and answering questions based on video context.-
- AlicenseAqualityBmaintenanceAllows AI agents to fetch, search, and summarize YouTube video transcripts without an API key, including chapter summaries.4MIT