# YouTube Transcript (MCP Server)

> Fetch YouTube video transcripts for summarization and Q&A

- Type: MCP server
- Publisher: kimtaeyoon83
- Categories: Media & Entertainment, Research
- Website: https://github.com/kimtaeyoon83/mcp-server-youtube-transcript
- Source: https://github.com/kimtaeyoon83/mcp-server-youtube-transcript
- Transport: stdio
- Launch command: npx -y @kimtaeyoon83/mcp-server-youtube-transcript
- Sign-in: none
- GitHub stars: 598
- Listed: 2024-11-29

## About

Community MCP server that downloads transcripts and subtitles from YouTube videos by URL or ID, with language selection. Optionally analyzes video content with TwelveLabs when an API key is provided.

## Install

1. **Add the server to Codex**

   Codex CLI:

   ```bash
   codex mcp add youtube-transcript -- npx -y @kimtaeyoon83/mcp-server-youtube-transcript
   ```

   config.toml:

   ```toml
   [mcp_servers.youtube-transcript]
   command = "npx"
   args = ["-y", "@kimtaeyoon83/mcp-server-youtube-transcript"]
   ```

   Agents SDK:

   ```python
   from agents import Agent, Runner
   from agents.mcp import MCPServerStdio
   
   async with MCPServerStdio(
       name="YouTube Transcript",
       params={"command": "npx", "args": ["-y", "@kimtaeyoon83/mcp-server-youtube-transcript"]},
   ) as server:
       agent = Agent(name="Assistant", mcp_servers=[server])
       result = await Runner.run(agent, "Summarize this YouTube video: <url>")
       print(result.final_output)
   ```

## Tools

- `get_transcript`
- `analyze_video`

## Example prompts

- "Summarize this YouTube video: <url>"
- "Get the Spanish transcript of this talk"
- "List the key points from this lecture"

## Related

- [Fetch](https://chatgptplugins.directory/mcp/fetch.md): Fetch web pages and convert them to markdown for LLMs
- [DeepWiki](https://chatgptplugins.directory/mcp/deepwiki.md): Ask questions about any public GitHub repo using DeepWiki's generated docs
- [Apify](https://chatgptplugins.directory/mcp/apify.md): Run thousands of Apify Actors for scraping and automation from your agent
- [Firecrawl](https://chatgptplugins.directory/mcp/firecrawl.md): Scrape, search, crawl and interact with live web pages for LLMs
- [AWS Knowledge](https://chatgptplugins.directory/mcp/aws-knowledge.md): Search current AWS docs, API references and regional availability
- [ElevenLabs](https://chatgptplugins.directory/mcp/elevenlabs.md): Build and manage ElevenLabs voice agents and generate speech

---
Source: https://chatgptplugins.directory/mcp/youtube-transcript · Index: https://chatgptplugins.directory/llms.txt · Independent and community-run. Not affiliated with or endorsed by OpenAI. ChatGPT is a trademark of OpenAI.