Server profile

YouTube MCP Server

YouTube MCP Server gives assistants video search, transcripts, channel research, and playlist access. Creator discovery supports subscriber and activity filters, while multiple API keys can provide fallback when a key exhausts its quota.

Server facts

YouTube MCP Server

Tech

Runtime / language
node
Transports
stdio
Remote available
No
Authentication
Not specified

Activity

GitHub stars
585
Last commit
Data as of

Tags

  • Creator Discovery
  • Playlists
  • Transcripts
  • Video Search
  • Youtube

Overview

YouTube MCP Server exposes ten tools for researching videos, channels, transcripts, and playlists. Video search accepts publication-date constraints and channel filters, while detailed video lookup can request selected resource parts. Channel research includes individual and bulk lookups, searches by handle or query, and a discovery workflow that finds creators through videos mentioning a topic. Subscriber bands, latest-upload activity, and creator-oriented heuristics help narrow those searches. Channel responses can also include normalized metadata and the latest video publication time. Playlist tools retrieve playlist information and its constituent videos.

Transcript retrieval accepts an optional language and otherwise uses a configured default or English. At least one YouTube Data API key is required. The README allows three configured keys and retries a quota-exhausted request with the next available key. Local MCP configuration uses either a globally installed command or npx with the zubeid-youtube-mcp-server package. The README also documents a Docker image that defaults to stateless HTTP, with separate MCP and readiness endpoints. Its build process copies a local environment file into the runtime image, meaning credentials present during the build can be included there. Source development uses npm dependency installation and build commands. The project states an MIT license. The documented tools are oriented toward retrieving and discovering content rather than uploading videos or managing a publishing workflow.

Install & configure

Requirements

  • Node.js and npx
  • At least one YouTube Data API key
  • An MCP-compatible client
Documented launch / install command
npx -y zubeid-youtube-mcp-server

Uses the README's npx configuration, not the different package in the structured config hint. YOUTUBE_API_KEY2 and YOUTUBE_API_KEY3 are optional fallback keys. YOUTUBE_TRANSCRIPT_LANG optionally changes the default transcript language. Docker defaults to HTTP at http://localhost:8088/mcp.

Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Desktop configuration
{
  "mcpServers": {
    "youtube-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "zubeid-youtube-mcp-server"
      ],
      "env": {
        "YOUTUBE_API_KEY": "<YouTube Data API key>"
      }
    }
  }
}

Read the Claude Desktop setup guide

Config file · Project: .cursor/mcp.json

User: ~/.cursor/mcp.json

The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.

Cursor configuration
{
  "mcpServers": {
    "youtube-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "zubeid-youtube-mcp-server"
      ],
      "env": {
        "YOUTUBE_API_KEY": "<YouTube Data API key>"
      }
    }
  }
}

Read the Cursor setup guide

Config file · Workspace: .vscode/mcp.json

For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.

VS Code configuration
{
  "servers": {
    "youtube-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "zubeid-youtube-mcp-server"
      ],
      "env": {
        "YOUTUBE_API_KEY": "<YouTube Data API key>"
      }
    }
  }
}

Read the VS Code setup guide

Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json

Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json

Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.

Windsurf configuration
{
  "mcpServers": {
    "youtube-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "zubeid-youtube-mcp-server"
      ],
      "env": {
        "YOUTUBE_API_KEY": "<YouTube Data API key>"
      }
    }
  }
}

Read the Windsurf setup guide

Config file · Project scope: .mcp.json at the repository root

The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Code configuration
{
  "mcpServers": {
    "youtube-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "zubeid-youtube-mcp-server"
      ],
      "env": {
        "YOUTUBE_API_KEY": "<YouTube Data API key>"
      }
    }
  }
}

Read the Claude Code setup guide

Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.

Tools

Source: repository README. Tool descriptions are a documented snapshot, not a live capability check.

ToolWhat it does
videos_getVideoRetrieve video details, optionally selecting resource parts.
videos_searchVideosSearch videos using date, channel, subscriber, activity, and ordering filters.
transcripts_getTranscriptRetrieve a video's transcript in a requested or configured language.
channels_getChannelInspect a channel with latest-upload and normalized metadata fields.
channels_getChannelsRetrieve several channels, optionally including their latest upload dates.
channels_searchChannelsFind channels by handle, name, or query with subscriber and activity filters.
channels_findCreatorsDiscover creator channels from topic-matching videos using size and activity constraints.
channels_listVideosList videos belonging to a specified channel.
playlists_getPlaylistInspect details for a selected playlist.
playlists_getPlaylistItemsRetrieve videos contained in a playlist.

Names, permissions, and defaults can change. Check the current upstream documentation before granting access.

Use cases

  • Search videos within publication dates and channel constraints.
  • Retrieve transcripts for assistant-led content review.
  • Discover creator channels by topic, subscriber size, and recent activity.
  • Inspect channel uploads and playlist contents.

Strengths

  • Combines video, transcript, channel, and playlist research.
  • Creator discovery includes size and activity filters.
  • Supports multiple API keys with quota-triggered fallback.
  • Offers both local stdio and Docker HTTP operation.

Limitations

  • At least one YouTube Data API key is required.
  • Creator-only filtering uses heuristics rather than a guaranteed classification.
  • The Docker build can include credentials from its copied environment file.

Frequently asked questions

No. One configured key is sufficient; the second and third key variables provide optional fallbacks.

The README says the server retries that request using the next configured key.

Yes. Channel search and creator discovery support subscriber bands and latest-upload activity filters, with heuristic creator classification.

Yes. The tool accepts a language, otherwise using YOUTUBE_TRANSCRIPT_LANG or English.

Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.

Related MCP servers

Firecrawl MCP Server

Search & Web Data

Firecrawl MCP connects AI agents to web search, scraping, crawling, and live browser interaction. It offers hosted access or a local server for collecting structured web context and running research tasks.

Tavily MCP Server

Search & Web Data

Tavily MCP Server connects AI clients to web search, page extraction, site mapping, and crawling. Run it locally with an API key or connect to the hosted service using API-key or OAuth authentication.

AgentQL MCP Server

Search & Web Data

AgentQL MCP Server extracts structured JSON from a web page using a natural-language description of the desired fields. It provides one focused extraction tool for MCP assistants.

Exa MCP Server

Search & Web Data

Exa MCP Server gives AI assistants web search and readable page retrieval, with optional advanced search and agent research tools. It supports hosted connections and a local npm package for research and coding context.

Perplexity API Platform MCP Server

Search & Web Data

The Perplexity API Platform MCP Server gives assistants web search, conversational answers, research, and reasoning tools. It connects to Perplexity’s Search API and Sonar models through local stdio or an HTTP deployment.

ArXiv MCP Server

Search & Web Data

Search arXiv, download papers, and read their contents through an AI assistant. Local storage and research prompts support repeatable literature review and paper analysis.

Bright Data Web MCP

Search & Web Data

Give AI assistants live web search, page extraction, and optional browser automation through Bright Data. Tool groups also provide structured datasets, package information, and AI brand-visibility queries.

DuckDuckGo Search MCP Server

Search & Web Data

Give MCP assistants DuckDuckGo search and webpage text retrieval. It suits research workflows that need regional results, readable page content, and configurable filtering.