Back to Browse

Ytranscript MCP Server

by Nnnoel
Developer ToolsModerate5.6MCP RegistryLocal
Free

Server data from the Official MCP Registry

YouTube transcripts and video details for AI tools. No proxies; transcribes captionless videos.

About

YouTube transcripts and video details for AI tools. No proxies; transcribes captionless videos.

Security Report

5.6
Moderate5.6Moderate Risk

This is a well-structured YouTube transcript and metadata MCP server that requires a yTranscript API key, reads it only from an environment variable, and exposes two read-only tools that call the vendor's API. The only network activity is sending the user-supplied video identifier to the yTranscript API as intended, with no shell execution, filesystem access, or hardcoded secrets found. Minor observations are limited to the API key being passed to a third-party service and a tagged referral URL in the key-link message, which is a marketing rather than security concern. Supply chain analysis found 8 known vulnerabilities in dependencies (0 critical, 4 high severity). Package verification found 1 issue.

10 files analyzed · 13 issues found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

Permissions Required

This plugin requests these system permissions. Most are normal for its category.

HTTP Network Access

Connects to external APIs or services over the internet.

env_vars

Check that this permission is expected for this type of plugin.

What You'll Need

Set these up before or after installing:

API key from https://ytranscript.com/developers (free plan available)Required

Environment variable: YTRANSCRIPT_API_KEY

How to Install

Add this to your MCP configuration file:

{
  "mcpServers": {
    "ytranscript-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "ytranscript-mcp@0.3.0"
      ],
      "env": {
        "YTRANSCRIPT_API_KEY": "your-ytranscript-api-key-here"
      }
    }
  }
}

Some servers take additional arguments. See the repository for details.

Documentation

View on GitHub

From the project's GitHub README.

ytranscript-mcp

npm ytranscript-mcp MCP server

An MCP server that gives Claude, Cursor, VS Code, and other AI tools the transcript of any YouTube video, plus its details: title, channel, duration, views and chapters.

  • Works from anywhere. Runs fine on AWS, Lambda, Vercel, n8n Cloud, and other cloud hosts. There are no proxies to buy and no IP bans to work around. YouTube blocks most cloud IPs for transcript requests; the yTranscript API handles that for you.
  • Handles videos without captions. If a video has no captions, it's transcribed with AI speech-to-text.
  • Returns the language actually spoken by default, including on auto-dubbed videos. Pass lang to pick a specific caption track.
  • Knows what the video is. Get the title, channel, publish date, duration, views, tags and chapters, on their own or together with the transcript.
  • Keeps long videos manageable. Choose plain text or timestamped lines, and cap the length so a two-hour video doesn't flood the model's context.

Setup

  1. Get a free API key at ytranscript.com/developers. The free plan includes 50 units a month, no card required.
  2. Add the server to your client using one of the configs below.

Claude Code

claude mcp add ytranscript -e YTRANSCRIPT_API_KEY=yk_live_your_key -- npx -y ytranscript-mcp

Claude Desktop

Add this to claude_desktop_config.json. Open it from Settings → Developer → Edit Config.

{
  "mcpServers": {
    "ytranscript": {
      "command": "npx",
      "args": ["-y", "ytranscript-mcp"],
      "env": { "YTRANSCRIPT_API_KEY": "yk_live_your_key" }
    }
  }
}

Cursor

Add this to ~/.cursor/mcp.json, or to .cursor/mcp.json in a project:

{
  "mcpServers": {
    "ytranscript": {
      "command": "npx",
      "args": ["-y", "ytranscript-mcp"],
      "env": { "YTRANSCRIPT_API_KEY": "yk_live_your_key" }
    }
  }
}

VS Code

Add this to .vscode/mcp.json:

{
  "servers": {
    "ytranscript": {
      "command": "npx",
      "args": ["-y", "ytranscript-mcp"],
      "env": { "YTRANSCRIPT_API_KEY": "yk_live_your_key" }
    }
  }
}

Any other MCP client that runs stdio servers works the same way: run npx -y ytranscript-mcp with YTRANSCRIPT_API_KEY set.

Tool: get_transcript

ArgumentRequiredDescription
videoyesA YouTube URL (watch, youtu.be, shorts, embed) or an 11-character video ID
langnoLanguage code of the caption track to fetch, such as en or es. Omit it to get the video's original language
formatnotext (default) returns plain text. timestamped returns one line per segment with [m:ss] times
max_charactersnoCut the transcript at about this many characters. The response says how much was left out
include_video_infonotrue adds the title, channel, publish date, duration and view count above the transcript, at no extra cost
max_unitsnoThe most the request may cost. A video without captions that would cost more isn't transcribed or charged, and the response gives the estimate. 1 means captions only

Things to ask your assistant:

  • "Summarize this video: https://youtu.be/..."
  • "What does the speaker say about pricing, and at what timestamps?"
  • "Pull the transcript of this Spanish video and translate it to English."

Tool: get_video_info

Returns a video's details without its transcript: title, description, channel (name, handle, subscribers), publish date, duration, view and like counts, tags, category and chapters.

ArgumentRequiredDescription
videoyesA YouTube URL or an 11-character video ID

Things to ask your assistant:

  • "How long is this video, and who made it?"
  • "List the chapters of https://youtu.be/..."
  • "Is this video worth transcribing? Check the description first."

When YouTube limits what it shows for a video, the duration, tags and category can be missing. The response says so.

Every response ends with the units used and your monthly total, so you can keep an eye on your quota.

Pricing

A transcript from captions costs 1 unit. A video without captions is transcribed with AI for 1 unit per minute of audio, at least 5 (a 9-minute video costs 9). Use max_units to cap what a request may cost. Video info costs 1 unit, and nothing when it comes with a transcript. Failed requests are free.

PlanPriceUnits per month
Free$050
Starter$9/mo1,000
Developer$29/mo10,000
Scale$79/mo50,000

Need more in a given month? Pay-as-you-go packs add 1,000 units for $10, 5,000 for $40 or 20,000 for $120, on top of any plan. See ytranscript.com/developers for details.

Related

License

MIT

Reviews

No reviews yet

Be the first to review this server!