youtube-mcp

youtube-mcp

A local-first MCP server for inspecting and managing a creator-owned YouTube channel, using Google's official YouTube Data API v3 and Analytics API.

Category
Visit Server

README

YouTube MCP

A safe, local-first Model Context Protocol server for inspecting and managing a creator-owned YouTube channel.

@fullstackcraftllc/youtube-mcp uses Google's official YouTube Data API v3 and YouTube Analytics API. It does not scrape YouTube, download videos, send telemetry, or provide a hosted intermediary.

Features

  • Inspect your channel and page through its uploads.
  • Read owned-video metadata and public statistics.
  • Analyze channel/video performance, traffic sources, YouTube search terms, and audience retention.
  • Preview exact title, description, tag, and category changes.
  • Apply only an unexpired reviewed preview after rechecking ownership and remote state.
  • Maintain separate readonly and manage OAuth authorizations in named local profiles.

Version 0.1 intentionally excludes uploads, deletes, thumbnails, visibility, comments, playlists, monetization, public-channel research, transcripts, and HTTP hosting.

Requirements

  • Node.js 22 or newer.
  • A creator-owned YouTube channel.
  • Your own Google Cloud project and Desktop OAuth client.

Follow Google Cloud setup before logging in. Never commit the downloaded OAuth client JSON.

Authorize a profile

Readonly analytics:

npx -y @fullstackcraftllc/youtube-mcp@0.1.0 auth login \
  --profile vannacharm \
  --mode readonly \
  --client-secrets /absolute/path/to/client_secret.json

Metadata management uses a separate token and explicit extra permission:

npx -y @fullstackcraftllc/youtube-mcp@0.1.0 auth login \
  --profile vannacharm \
  --mode manage \
  --client-secrets /absolute/path/to/client_secret.json

If Google exposes multiple channels, repeat the command with --channel-id <id> after the CLI prints the valid choices.

Check configuration without exposing credentials:

npx -y @fullstackcraftllc/youtube-mcp@0.1.0 auth status --profile vannacharm --mode readonly
npx -y @fullstackcraftllc/youtube-mcp@0.1.0 doctor --profile vannacharm --mode readonly

MCP client configuration

Codex, readonly:

codex mcp add youtube \
  -- npx -y @fullstackcraftllc/youtube-mcp@0.1.0 serve --profile vannacharm --mode readonly

Codex, manage mode as a separately named server:

codex mcp add youtube-manage \
  -- npx -y @fullstackcraftllc/youtube-mcp@0.1.0 serve --profile vannacharm --mode manage

Claude Desktop:

{
  "mcpServers": {
    "youtube": {
      "command": "npx",
      "args": [
        "-y",
        "@fullstackcraftllc/youtube-mcp@0.1.0",
        "serve",
        "--profile",
        "vannacharm",
        "--mode",
        "readonly"
      ]
    }
  }
}

The server starts even if authorization is missing so the client can call youtube_get_auth_status. Other tools return AUTH_REQUIRED until the selected profile and mode are authorized.

Safe metadata updates

There is no direct update tool. The workflow is:

  1. Call youtube_preview_video_update with one or more proposed fields.
  2. Review the complete before/after diff, video ID, channel ID, expiry, and hash.
  3. Call youtube_apply_video_update with the preview ID, hash, and exact video ID.

Apply re-fetches current metadata and fails if anything changed since preview. YouTube receives a complete writable snippet so omitted fields are preserved. A preview expires after ten minutes and is consumed after one apply attempt.

See the complete tool reference, privacy and deletion behavior, and threat model.

Other CLI commands

youtube-mcp profiles list
youtube-mcp auth revoke --profile vannacharm --mode readonly
youtube-mcp auth revoke --profile vannacharm --mode manage
youtube-mcp --help
youtube-mcp --version

Local development

git clone https://github.com/FullStackCraft/youtube-mcp.git
cd youtube-mcp
npm install
npm run release:check

Run locally from an MCP client with:

node /absolute/path/to/youtube-mcp/dist/index.js serve --profile vannacharm --mode readonly

Compliance and affiliation

Use of this software is subject to the YouTube Terms of Service, YouTube API Services Terms of Service, and Google Privacy Policy.

YouTube and Google are trademarks of Google LLC. This independent project is not affiliated with, sponsored by, or endorsed by YouTube or Google.

License

MIT © Full Stack Craft LLC.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured