MCP Youtube Transcript logo

MCP Youtube Transcript

Retrieve YouTube transcripts, timestamps, language options, and video metadata through MCP tools.

Install MCP Youtube Transcript

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "mcp-youtube-transcript": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/jkawamoto/mcp-youtube-transcript",
        "mcp-youtube-transcript"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Automated check passed— started and listed 4 tools correctly ().

Overview

mcp-youtube-transcript retrieves transcript text and metadata from YouTube videos for AI workflows. It exposes tools for plain and timestamped transcripts, available transcript languages, and video information, with optional language selection. The server communicates over standard stdio and can run through uvx, Docker, or supported MCP clients. Long responses can be split into cursor-based chunks, and proxy settings are available for handling YouTube access restrictions.

Use cases

  • Summarize long YouTube lectures
  • Extract quotes with timestamps from interviews
  • Check which transcript languages a video provides
  • Retrieve video titles and channel information
  • Analyze podcast or conference transcripts in chunks

Key features

  • Plain-text transcript retrieval
  • Timestamped transcript segments
  • Transcript language discovery
  • YouTube video metadata lookup
  • Cursor-based pagination for long transcripts
  • Webshare, ScrapingAnt, and HTTP/HTTPS proxy support

Tools4

What MCP Youtube Transcript lets your agent do. Expand a tool for its parameters.

Verified live~375 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked

Recent health check succeeded.

19/19 checks healthy over the last 63d

What it can do

From the 4 tools this server returned when we ran it.

Read-only tools · 4
Network at startup2 connections
Files written at startup22

Observed 2026-11-10 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 13d ago via OSV.dev · mcp-youtube-transcript (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars497Stargazers on the source repository.
Last commit1d agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed4Callable tools this server registers over MCP.
Directory activity13 viewsConfig copies, upvotes, and views on AllMCPs.

How MCP Youtube Transcript works

What mcp-youtube-transcript does

mcp-youtube-transcript connects MCP-compatible AI applications to YouTube video transcripts and related metadata. Its four tools accept a full YouTube video URL and let an agent retrieve transcript text, timestamped segments, available transcript languages, or video information such as the title and channel.

Transcript requests support a preferred language code, with English used by default. The language listing tool can help an agent choose among manual and automatically generated transcript options before requesting content.

Long-form content is handled through response chunking. Transcripts larger than the default 50,000-character limit are split into responses, and the server returns a cursor that can be supplied to retrieve the next chunk. This is useful for lectures, conferences, interviews, and podcast episodes that may exceed an LLM context window.

How it works

The server uses the Model Context Protocol over standard stdio. An MCP client starts the process and invokes tools with a YouTube URL plus any supported options. For transcript tools, the optional lang parameter selects the requested language and next_cursor requests a later portion of a paginated response.

The default response limit is 50,000 characters. You can change it with --response-limit; a negative value such as -1 disables pagination and requests the complete transcript in one response.

Requests can use residential proxy services or ordinary HTTP and HTTPS proxies. Supported proxy configuration includes Webshare credentials, a ScrapingAnt API token, and custom proxy endpoints. ScrapingAnt access requires a paid subscription, and residential proxy usage consumes its credits.

Setup and configuration

Install Astral uv to use the uvx launcher, then add the server to an MCP client's configuration. A typical command runs the package directly from its Git repository:

config.json
{
  "mcpServers": {
    "youtube-transcript": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/jkawamoto/mcp-youtube-transcript",
        "mcp-youtube-transcript"
      ]
    }
  }
}

The repository also provides a Docker image through Docker Hub. Claude Desktop, Cursor, Goose, and LM Studio have setup paths described for this server; other standard MCP clients can use the stdio configuration when they support command-based servers.

Optional proxy environment variables include WEBSHARE_PROXY_USERNAME, WEBSHARE_PROXY_PASSWORD, SCRAPINGANT_API_TOKEN, HTTP_PROXY, and HTTPS_PROXY. The equivalent command-line flags are available for these settings. Add --response-limit to the command arguments when changing transcript pagination behavior.

Tools and capabilities

  • get_transcript returns plain transcript text. It accepts url, optional lang, and optional next_cursor.
  • get_timed_transcript returns transcript segments with start times and durations. It accepts the same parameters as get_transcript.
  • get_available_languages lists transcript languages for a supplied YouTube URL.
  • get_video_info retrieves video metadata for a supplied YouTube URL.
  • Automatic chunking and cursor-based pagination support transcripts longer than the configured response limit.
  • Proxy configuration supports Webshare, ScrapingAnt, and generic HTTP or HTTPS proxy endpoints.

Limitations and notes

YouTube may block automated requests from data-center or cloud-provider IP addresses. Residential or rotating proxies may be needed to avoid request blocking or IP bans. ScrapingAnt requires a paid web-scraping subscription for YouTube access.

Transcript availability and language choices depend on the target YouTube video. The server needs a full YouTube video URL for every tool call. The default language preference is English unless a different language code is supplied.

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about MCP Youtube Transcript

mcp-youtube-transcript is an MCP server that connects AI workflows to YouTube videos. Its main tools retrieve plain or timestamped transcripts, list available transcript languages, and return video information. It accepts YouTube URLs, supports language selection, and uses cursors to retrieve additional chunks from long transcripts.

Install Astral uv, then configure your MCP client to run the server with uvx and its Git repository source. Use the command `uvx --from git+https://github.com/jkawamoto/mcp-youtube-transcript mcp-youtube-transcript` in the client's MCP server configuration.

Pass the `next_cursor` returned by the previous transcript response to `get_transcript` or `get_timed_transcript`. Responses are split after the configured character limit, which defaults to 50,000 characters; use `--response-limit` to change that behavior.

Yes, it supports Webshare residential proxies, ScrapingAnt, and generic HTTP or HTTPS proxies. Configure Webshare credentials or a ScrapingAnt token through environment variables, or set `HTTP_PROXY` and `HTTPS_PROXY` for custom proxy endpoints.

Yes, Cursor is supported through its MCP Servers settings. Add a new command-based server and use the uvx command with the repository source and `mcp-youtube-transcript` executable.

Related MCP servers

Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewMCP Youtube Transcript AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/mcp-youtube-transcript?style=directory)](https://allmcps.com/mcp/mcp-youtube-transcript)
HTML Embed
<a href="https://allmcps.com/mcp/mcp-youtube-transcript"><img src="https://allmcps.com/api/badge/mcp-youtube-transcript?style=directory" alt="MCP Youtube Transcript on AllMCPs" /></a>