Advertise
MCP.so
Sign In

Yt Dlp MCP Server

@kevinwatt

Repository

Basic information

Category

Media & Design

License

MIT

Transports

stdio

Author

kevinwatt

About Yt Dlp MCP Server

A Model Context Protocol (MCP) server that bridges Video & Audio content with Large Language Models using yt-dlp.

Yt Dlp MCP Server config

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

{
  "mcpServers": {
    "yt-dlp": {
      "command": "npx",
      "args": [
        "-y",
        "@kevinwatt/yt-dlp-mcp@latest"
      ]
    }
  }
}

Yt Dlp MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

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

Overview

What is yt-dlp-mcp?

yt-dlp-mcp is a Model Context Protocol server that integrates yt-dlp with MCP-compatible AI systems like Claude and Dive. It lets you search videos, download content, extract metadata, get transcripts, and more — all through natural language commands.

How to use yt-dlp-mcp?

Install yt‑dlp on your system first, then add the npx configuration to your MCP client. Tools are prefixed with ytdlp_ and are invoked by the AI agent based on natural language prompts. Environment variables let you customize downloads directory, default resolution, subtitle language, and character limits.

Key features of yt-dlp-mcp

  • Search YouTube with pagination and date filtering
  • Extract comprehensive video metadata (views, likes, upload date, tags)
  • Download subtitles in VTT format and generate clean text transcripts
  • Download videos at resolutions from 480p to 1080p with trimming support
  • Extract audio in best quality M4A/MP3
  • Retrieve YouTube comments in flat or threaded JSON or Markdown

Use cases of yt-dlp-mcp

  • Search for tutorials or videos on any topic and get structured results
  • Download a video or audio file from YouTube, Facebook, or other platforms
  • Get a clean transcript or subtitles for a video in multiple languages
  • Analyze video metadata and comments for research or content curation

Frequently asked questions

1

Does yt-dlp-mCP require yt-dlp to be installed separately?

Yes. You must install yt‑dlp using `winget` (Windows), `brew` (macOS), or `pip` (Linux) before using the server.

2

How do I access private or age-restricted videos?

Configure cookies by setting the `YTDLP_COOKIES_FROM_BROWSER` environment variable (e.g., `chrome`) or providing a cookie file path. This requires a JavaScript runtime (deno) to be installed.

3

Where are downloaded files saved?

Downloads are saved to `~/Downloads` by default. You can change the directory via the `YTDLP_DOWNLOADS_DIR` environment variable.

4

Are there any character limits enforced?

Yes. The server enforces a default character limit of 25,000 for outputs and a maximum transcript length of 50,000 characters, both adjustable via environment variables.

5

What data does yt-dlp-mCP collect from my usage?

The server does not perform any tracking or analytics. All downloads happen directly via yt‑dlp, and inputs are validated with Zod schemas for LLM safety.

Comments

More Media & Design MCP servers

Katto

Katto

AI video clipping MCP server for scored, captioned vertical shorts, with 29 documented tools and dubbing in 19 languages. Hosted OAuth connection with a local installation option.

Uwear.ai

Uwear.ai

Run complete AI fashion photoshoots from ChatGPT, Claude, or Codex. Turn flat-lay, packshot, and mannequin product images into catalog-ready on-model photos and video with saved art direction, automatic QA, and catalog-s

getimg

getimg.ai

Create and edit images, videos, music, speech, and sound effects with your getimg account. Use ready-made workflows for professional headshots, photo restoration, stickers, lighting changes, background cleanup, product v

North Noir

North Noir

Make AI-drawn video from chat. Claude, Cursor or Claude Code plans the film, the model draws every frame in code at 30 fps, and you edit it on a timeline with narration, music and sound effects.

GPT Image 2.5 MCP

you.bot

Generate and edit images with GPT Image 2.5 for $0.029 each. A free you.bot key (not an OpenAI key) comes with 50 credits — about 17 images — and needs no credit card.

Advertise