YouTube Transcript MCP Server

@jkawamoto

About YouTube Transcript MCP Server

MCP server retrieving transcripts of YouTube videos

Config

Add this server to your MCP-compatible client using the configuration below.

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

Tools

No tools detected

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is YouTube Transcript MCP Server?

YouTube Transcript MCP Server is a Model Context Protocol server that retrieves transcripts and metadata for YouTube videos. It provides tools for fetching plain or timestamped transcripts, video info, and available languages. It is intended for use with MCP-compatible clients like Claude Desktop, goose, and LM Studio.

How to use YouTube Transcript MCP Server?

Install via uvx with the command uvx --from git+https://github.com/jkawamoto/mcp-youtube-transcript mcp-youtube-transcript. Configure it in your MCP client (e.g., Claude Desktop, goose, LM Studio). Optionally set a response size limit with --response-limit <chars> or configure proxy servers via environment variables or command‑line arguments.

Key features of YouTube Transcript MCP Server

Fetch plain or timestamped YouTube video transcripts.
Retrieve video metadata (title, description, etc.).
List available transcript languages for a video.
Automatic pagination for long transcripts (default 50,000 characters per page).
Supports proxy servers for restricted environments.
Works with Claude, goose, and LM Studio.

Use cases of YouTube Transcript MCP Server

Extract transcript text for content analysis or summarization.
Obtain timed transcript segments for subtitling or translation.
Retrieve video metadata for archival or research purposes.
Query available language tracks to select the best transcript.
Automate transcript fetching in AI‑powered workflows.

FAQ from YouTube Transcript MCP Server

What tools does the server provide?

It offers get_transcript, get_timed_transcript, get_video_info, and get_available_languages.

How does response pagination work?

Transcripts exceeding 50,000 characters are split; a next_cursor is returned to retrieve the next part. You can adjust the limit with --response-limit.

Can I use a proxy with this server?

Yes. For WebShare proxies set WEBSHARE_PROXY_USERNAME and WEBSHARE_PROXY_PASSWORD. For other proxies use HTTP_PROXY/HTTPS_PROXY or the --http-proxy/--https-proxy arguments.

What languages are supported for transcripts?

You can request a specific language via the optional lang parameter (defaults to English). Use get_available_languages to see all options for a video.

What are the runtime requirements?

You need uv installed to use the uvx command. A Docker image is also available on Docker Hub.

Frequently asked questions

What tools does the server provide?

It offers `get_transcript`, `get_timed_transcript`, `get_video_info`, and `get_available_languages`.

How does response pagination work?

Transcripts exceeding 50,000 characters are split; a `next_cursor` is returned to retrieve the next part. You can adjust the limit with `--response-limit`.

Can I use a proxy with this server?

Yes. For WebShare proxies set `WEBSHARE_PROXY_USERNAME` and `WEBSHARE_PROXY_PASSWORD`. For other proxies use `HTTP_PROXY`/`HTTPS_PROXY` or the `--http-proxy`/`--https-proxy` arguments.

What languages are supported for transcripts?

You can request a specific language via the optional `lang` parameter (defaults to English). Use `get_available_languages` to see all options for a video.

What are the runtime requirements?

You need `uv` installed to use the `uvx` command. A Docker image is also available on Docker Hub.

Comments

Basic information

More Media & Design MCP servers

Framelink Figma MCP Server

GLips

MCP server to provide Figma layout information to AI coding agents like Cursor

15.3K

diggercamp

Tommaso Savorana (ti es)

diggercamp finds independent music by how it sounds. Paste any Bandcamp, YouTube or SoundCloud link and get the closest sonic matches from 4M+ independent tracks — matched by rhythm, timbre, key and energy, not genre tag

Notch

Create finished video ads from chat. Give Notch a brief or product URL — it loads your brand context, writes the script, and produces the finished ad: avatar, scenes, voiceover, captions. Built for performance marketers,

SVGator

Drive your SVGator account from any AI assistant. Prompt an animation, get an editable project back, and export it as SVG, Lottie, GIF, MP4, and more, then open it in the editor to finish by hand.

百度地图 MCP Server

baidu-maps

Baidu Map MCP Server

436