jkawamoto/mcp-youtube-transcript

MCP server retrieving transcripts of YouTube videos

What it solves

This project provides a way for AI agents to reliably fetch YouTube transcripts and metadata. It addresses the common problem of LLM context window limits when dealing with long videos and the aggressive IP blocking of automated requests by YouTube.

How it works

It is implemented as a Model Context Protocol (MCP) server. It provides a set of tools that LLM clients (like Claude Desktop, Cursor, or LM Studio) can call to retrieve plain-text transcripts, timestamped segments, available languages, and video metadata. To handle long-form content, it automatically chunks transcripts into manageable pieces (default 50,000 characters) using a pagination system with cursor tokens.

Who it’s for

Developers and users of AI agents and MCP-compatible clients who want their LLMs to "see" and analyze the content of YouTube videos.

Highlights

  • Automatic Pagination: Prevents context window overflow by chunking long transcripts.
  • Proxy Support: Built-in support for residential proxies (Webshare, ScrapingAnt) and standard HTTP/HTTPS proxies to avoid IP bans.
  • Multi-language Support: Ability to fetch transcripts in multiple languages.
  • Universal Compatibility: Works with any standard MCP client including Claude Desktop, Cursor, LM Studio, and Goose.

Related

  • Project
    ZubeidHendricks/youtube-mcp-server

    An MCP server that enables AI language models to interact with YouTube by providing tools to search videos, retrieve transcripts, and analyze channel data.

  • Project
    kimtaeyoon83/mcp-server-youtube-transcript

    A Model Context Protocol server that allows AI models to retrieve YouTube transcripts and optionally analyze visual content using TwelveLabs.

  • Project
    anaisbetts/mcp-youtube

    A Model Context Protocol server that enables AI assistants to download and read YouTube subtitles using yt-dlp for video summarization and analysis.

  • Project
    tavily-ai/tavily-mcp

    Tavily MCP is a Model Context Protocol server that exposes four web‑knowledge tools—search, extract, map, and crawl—so LLM‑based agents (Claude Code, Cursor, etc.) can fetch up‑to‑date web data, pull page content, generate site maps, or bulk‑crawl sites. It can be used via Tavily’s hosted endpoint or run locally with a single `npx` command, authenticating with an API key or optional OAuth. Configuration is done through environment variables (`TAVILY_API_KEY`, `DEFAULT_PARAMETERS`, `TAVILY_HUMAN_ID`). The server enables real‑time web access for AI assistants, RAG pipelines, and productivity tools without custom scraping code.

  • Project
    blazickjp/arxiv-mcp-server

    A local MCP server that lets AI assistants search, download, and read arXiv papers (including LaTeX sections), manage citation graphs, set topic watches, and optionally run semantic search, all via a stdio or HTTP JSON‑RPC interface.