MCP server
YouTube Transcript MCP server
A community MCP server that fetches public YouTube transcripts, timed transcripts, video details and available languages.
- Community server
- Search and web
At a glance
- Maintained by
- Junpei Kawamoto (community)
- Tools exposed
- 4 listed below
- Reviewed
- September 24, 2026
Why it matters
What it does and why it matters
A lot of useful knowledge sits in videos: product demos, conference talks, training sessions and webinars. This community MCP server lets an assistant fetch the public transcript of a YouTube video, with or without timestamps, along with video details and the available transcript languages.
Once the transcript is available, the assistant can summarize the video, pull out key points, answer questions about it or find the moment a topic is discussed.
We did not find an official YouTube or Google server for transcripts, so this is a community server by Junpei Kawamoto. It needs no credentials for normal use, with optional proxy settings for heavy use. Review the code before installing, and use it only for videos where you have the right to use the content.
Automatic captions can contain errors, especially with names and technical terms. For anything important, check the quoted passage against the video itself.
Use cases
Best business use cases
Video summaries
Find the moment
Competitor demos
Transcript languages
Tools
Available tools
Tool names as published by the maintainer at review time. Versions change, so check the repository for the current list.
Read and write: Read-only; fetches public transcripts and metadata.
-
get_transcriptGets a video's transcript, with language and paging options.
-
get_timed_transcriptGets a video's transcript with timestamps.
-
get_video_infoGets a video's metadata.
-
get_available_languagesLists transcript languages for a video.
Workflows
Example workflows
Webinar to blog outline
-
1
Share the webinar link.
-
2
The assistant fetches the transcript.
-
3
It lists the main points in order.
-
4
It drafts an outline for a written article.
-
5
A writer turns it into a post.
Find a topic in a long talk
-
1
Share the video link and the topic.
-
2
The assistant fetches the timed transcript.
-
3
It finds the passages about the topic.
-
4
It returns timestamps and quotes.
-
5
You jump straight to that part.
Prompts
Example prompts
“Summarize this video in ten bullet points.”
“At what timestamp does the speaker discuss pricing?”
“Which transcript languages are available for this video?”
Setup
Installation and configuration
Examples for Claude Desktop and Claude Code. Replace the placeholder values with your own keys, and store secrets outside version control.
Claude Desktop: claude_desktop_config.json
{
"mcpServers": {
"youtube-transcript": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/jkawamoto/mcp-youtube-transcript",
"mcp-youtube-transcript"
]
}
}
}Claude Code: terminal
claude mcp add youtube-transcript -- uvx --from git+https://github.com/jkawamoto/mcp-youtube-transcript mcp-youtube-transcript- Local server: stdio. Python package mcp-youtube-transcript, run with uvx from the git repo; .mcpb bundle in Releases.
- Needs: None required; Optional proxy settings: SCRAPINGANT_API_TOKEN, WEBSHARE_PROXY_USERNAME, WEBSHARE_PROXY_PASSWORD, HTTP_PROXY, HTTPS_PROXY.
Security
Security considerations
-
Community code
Review the code and pin the version before installing.
-
Content rights
Use transcripts only where you have the right to use the content.
-
Untrusted text
Transcripts are untrusted content. Do not follow instructions found in them.
-
Caption errors
Check important quotes against the video.
Related servers
Servers that pair well with it
Fetch
The MCP project's reference Fetch server lets AI download a web page and read it as clean text or markdown.
Perplexity
Perplexity's official MCP server lets AI search the web, ask questions with cited answers, run deeper research and reason over results.
Notion
Notion's official hosted MCP server lets AI search and read pages, create and update pages and databases, query data and add comments.
Keep exploring
Solutions and services that use it
Related services
View all related servicesSolutions
View all solutions- AI sales research agent Short, sourced briefings on each prospect before a call, drafted by an AI agent from public information and your CRM.
- Price monitoring Collect competitor prices automatically, match them to your products and alert you when something changes.
- Compliance tracking Track filing deadlines, licenses and obligations in one place, with reminders and AI summaries of relevant rule changes.
- Knowledge assistant (RAG) Ask a question in plain words and get an answer from your own documents, with links to the sources.
- Internal help desk assistant An assistant in Slack or Teams that answers policy and how-to questions from your handbooks and opens tickets when needed.
- Meeting notes automation Transcribe meetings and calls, summarize decisions and push action items into your CRM or project tool.
Industries
View all industriesGuides and articles
View all guides and articles- What are AI agents and how do businesses use them? What AI agents are, real business uses, the controls they need and how to start with one safely.
- What is the Model Context Protocol? A business guide to MCP: what it is, how MCP servers work, who supports it and how to start using it.
- How to build an AI workflow with MCP servers Plan, connect and test an AI workflow that uses MCP servers, from a single task to a reliable process.
- AI chatbot vs AI agent What separates a chatbot that answers from an agent that acts, and when you need each.
AI models
View all ai models- Reasoning Models that think through multi-step problems before answering: analysis, planning, math, complex documents and agent work.
- Claude Fable 5.1 The top tier of the Claude family, for the most demanding reasoning and long-horizon agent work, priced above Opus.
- Claude Opus 5.5 Anthropic's recommended starting point for most serious work: long-running agentic coding and knowledge work, with a 1M token context window.
- GPT-6 Astra OpenAI's most capable model, built for the hardest end-to-end work: complex reasoning, coding, computer use and research.
- DeepSeek V4 Pro DeepSeek's model for demanding reasoning and agent work, with thinking effort levels, tool calling, JSON output and a 1 million token window.
- Grok 4.7 xAI's current flagship for coding, agent tasks and knowledge work, with image input, tool calling, structured outputs, reasoning effort levels and a 500K window.
Glossary terms
View all glossary terms- Natural language processing Natural language processing is the field of AI that deals with understanding and generating human language, in text or speech.
- RAG RAG, or retrieval-augmented generation, is a method where an AI system first finds relevant passages in your documents, then answers using only those passages.
- AI agent An AI agent is software that uses a language model to plan steps, call tools and act toward a goal, instead of only answering one question.
- MCP server An MCP server is a program or hosted service that exposes a system's data and actions as tools that AI assistants can use through the Model Context Protocol.
- Model Context Protocol The Model Context Protocol, or MCP, is an open standard for connecting AI assistants to external tools and data in a consistent way.
- Tool calling Tool calling is when an AI model asks the application to run a tool, such as a search or database lookup, and then uses the result in its answer.
FAQ
Questions people ask us
Have a question that is not here? Ask us directly.
We did not find one at review time. This is a community server.
No, for normal use. Optional proxy settings exist for heavy use.
It fetches public transcripts. Private videos are not supported.