yt-playlist-organizer-mcp
An MCP server for organizing YouTube playlists via the YouTube Data API v3, enabling playlist and playlist item creation, listing, updating, and deletion through natural language.
README
yt-playlist-organizer-mcp
An MCP server for organizing YouTube playlists via the YouTube Data API v3.
It does exactly one thing and nothing more: create, list, update, and delete playlists and their playlist items. It does not touch videos, channels, captions, comments, subscriptions, or any other YouTube Data API resource.
Built with the official @modelcontextprotocol/sdk
and the YouTube Data API v3 REST endpoints (no heavy googleapis dependency).
Tools
Everything this server does. There are no other tools.
Playlists (/playlists)
| Tool | HTTP | Quota | Description |
|---|---|---|---|
playlists_list |
GET | 1 | List playlists by id, channelId, or mine=true. |
playlists_insert |
POST | 50 | Create a playlist (requires title). |
playlists_update |
PUT | 50 | Modify a playlist (requires id + title). |
playlists_delete |
DELETE | 50 | Delete a playlist (requires id). |
PlaylistItems (/playlistItems)
| Tool | HTTP | Quota | Description |
|---|---|---|---|
playlistItems_list |
GET | 1 | List items by playlistId or id. |
playlistItems_insert |
POST | 50 | Add a videoId to a playlistId. |
playlistItems_update |
PUT | 50 | Modify a playlist item (e.g. its position). |
playlistItems_delete |
DELETE | 50 | Remove a playlist item (requires id). |
Plus auth_status to check which credentials are configured.
Configuration
This server only ever calls the /playlists and /playlistItems endpoints.
The rest of the YouTube Data API is out of scope.
The server reads two environment variables:
| Variable | Purpose |
|---|---|
YOUTUBE_API_KEY |
Google API key. Enables public reads (playlists_list, playlistItems_list). |
YOUTUBE_ACCESS_TOKEN |
OAuth2 access token. Required for write tools and mine=true. |
See .env.example.
- Reads (
..._list) work with just an API key (or an access token). - Writes (
insert/update/delete) andmine=truerequire an OAuth2 access token with the scopesyoutube,youtube.force-ssl, oryoutubepartner.
Getting OAuth2 credentials
- Create a project in Google Cloud Console.
- Enable the YouTube Data API v3.
- Create an OAuth2 client ID (Desktop app) and download the JSON.
- Exchange credentials for an access token (e.g. via
google-auth-oauthlibon Python, or a local OAuth flow service). SetYOUTUBE_ACCESS_TOKEN=<token>. - (Optional) Create an API key for simpler read-only use.
Nix
This is NixOS-friendly. Both a flake and a shell.nix are provided.
# Enter the dev shell (node + typescript toolchain)
nix develop
# or, non-flake:
nix-shell
Build
npm install # install node deps (zod + MCP SDK)
npm run build # emits dist/
npm run typecheck # tsc --noEmit
Run locally
# Reads only (API key):
YOUTUBE_API_KEY=... node dist/index.js
# Reads + writes/mine (OAuth access token):
YOUTUBE_ACCESS_TOKEN=... node dist/index.js
Wiring into opencode
Add the following to ~/.config/opencode/opencode.jsonc under mcp:
"mcp": {
"yt-playlist-organizer-mcp": {
"type": "local",
"command": ["node", "<path-to-repo>/dist/index.js"],
"enabled": true,
"environment": {
"YOUTUBE_API_KEY": "{file:~/.secrets/yt-api-key}",
"YOUTUBE_ACCESS_TOKEN": "{file:~/.secrets/yt-access-token}"
}
}
}
Replace <path-to-repo> with the absolute path where you cloned it, or install
it via npm to run it by name:
npm install -g .
# then use: "command": ["yt-playlist-organizer-mcp"]
To run it through the Nix shell instead, use the same key but change command:
"command": ["nix", "develop", "<path-to-repo>", "--command", "node", "dist/index.js"],
Notes
- Quota costs are per the official API docs and documented per tool.
partvalues are validated against the valid sets for each resource.playlists_list/playlistItems_listrequire exactly one filter parameter; otherwise input validation rejects the call.- Update tools (
playlists_update,playlistItems_update) read the existing resource first and preserve any omitted fields (e.g.description,privacyStatus,position,contentDetails), rather than clearing them. Each update therefore costs an extra read against your quota. startAt/endAtare provided in seconds and converted to ISO 8601 durations (PT1M30S) before being sent to the API.
Development
npm install
npm test # vitest unit tests
npm run typecheck
npm run build
License
MIT
Recommended Servers
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.