# mcp-youtube-transcript

MCP server that retrieves YouTube video transcripts, timed segments, and metadata for AI agents. It splits long transcripts into chunks to protect the LLM context window.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed · ★ 492
- Author: jkawamoto
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/jkawamoto/mcp-youtube-transcript
- Updated: 2026-10-21
- HTML: https://affpapa.org/en/nevibecode/mcp/mcp-youtube-transcript

## What it does

The server exposes four tools for client workflows: `get_transcript`, `get_timed_transcript`, `get_available_languages`, and `get_video_info`. Models can read complete video transcripts, fetch timestamped intervals, or inspect channel details and video titles. The optional `lang` parameter specifies preferred subtitle languages.

To prevent context window overflow, responses exceeding 50,000 characters are broken into chunks. The tool returns a `next_cursor` token so the agent can request subsequent sections on demand. Passing `--response-limit` adjusts this character boundary, and setting it to `-1` disables chunking entirely. The server also supports residential proxies like Webshare or ScrapingAnt to bypass YouTube IP restrictions.

Running the server through `uvx` requires having `uv` installed on the host system.

## Requirements
- Needs: Python and uv (commands run via uvx)

## Install

### Claude Code (native platform)

**Install**
- The MCP registry has no launch command for it: see the repository README

## When to use it
- Fetch raw text transcripts from YouTube video links
- Extract subtitle segments with start timestamps and duration values
- Check manual and generated subtitle languages for a video
- Handle long transcripts in chunks using cursor pagination
- Route requests through residential proxies to prevent IP rate limits

## Example prompts
- Extract the full text transcript for `<url>`.
- Get the timed transcript with timestamps for `<url>` in English.
- Show all available subtitle languages for `<url>`.

## Similar
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89433
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [AIHawk](https://affpapa.org/en/nevibecode/mcp/aihawk.md) — MCP server · ★ 32221
- [Skyvern](https://affpapa.org/en/nevibecode/mcp/skyvern.md) — MCP server · ★ 23263
- [SeleniumBase MCP](https://affpapa.org/en/nevibecode/mcp/seleniumbase-mcp.md) — MCP server · ★ 13169
- [apify-mcp-server](https://affpapa.org/en/nevibecode/mcp/apify-mcp-server.md) — MCP server · ★ 12927

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md