youtube-data

MCP server from icraft2170/youtube-data-mcp-server

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

Command

claude mcp add --transport stdio icraft2170-youtube-data-mcp-server npx -y youtube-data-mcp-server \
  --env YOUTUBE_API_KEY="YOUR_API_KEY_HERE" \
  --env YOUTUBE_TRANSCRIPT_LANG="ko"

How to use

This MCP server exposes a set of YouTube-focused tools that let AI models fetch and analyze YouTube content through a standardized interface. The available operations include retrieving detailed video information, searching for videos by keywords, obtaining transcripts in multiple languages, pulling related videos, and analyzing channel statistics and engagement. It also provides trend analysis capabilities such as finding trending videos by region or category and comparing statistics across multiple videos. To use these tools, connect to the MCP server from your client (e.g., Claude Desktop) and invoke the desired tool by name with the required parameters (for example, video IDs, query strings, or channel IDs). The server returns structured data that your model can consume for downstream reasoning, summarization, or decision making.

How to install

Prerequisites:

Node.js 18.x or higher
npm (comes with Node.js)

Automatic installation (via Smithery):

npx -y @smithery/cli install @icraft2170/youtube-data-mcp-server --client claude

Manual installation:

# Install from npm
npm install youtube-data-mcp-server

# Or clone repository and install locally
git clone https://github.com/icraft2170/youtube-data-mcp-server.git
cd youtube-data-mcp-server
npm install

Environment setup:

Obtain a YouTube Data API key and set it in your environment (see Environment Configuration below).

Run in development:

npm run dev

Build for production:

npm run build

Additional notes

Environment variables: YOUTUBE_API_KEY is required for API access. YOUTUBE_TRANSCRIPT_LANG is optional and defaults to 'ko' if not set. Do not commit API keys to version control. The server exposes HTTP on port 3000 and gRPC on port 3001; ensure firewall rules allow these ports if needed. When using with Claude Desktop, configure the mcpServers entry with the node-based npx invocation as shown in the README example. If you hit rate limits, consider restricting requests or applying for higher quota through Google Cloud Console. Regularly rotate API keys and monitor usage via the YouTube Data API Console.

Related MCP Servers

zen

1.1k

Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage

MCP -Deepseek_R1

A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)

mcp-fhir

A Model Context Protocol implementation for FHIR

mcp

Inkdrop Model Context Protocol Server

mcp-appium-gestures

This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..

dubco -npm

The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.