# YouTube Watch Later

> Use this tool when you need to manage YouTube Watch Later playlists programmatically, solving problems such as content curation and automated playlist management. It integrates with the YouTube API, providing OAuth2 authentication and standardized interfaces for retrieving and managing video content. Ideal for applications involving video recommendation systems, content analysis, and cross-platform video organization, it accepts authentication credentials as input and outputs playlist items and video metadata.

Canonical page: https://skillsregistry.net/skills/rados10-youtube-watch-later  
JSON: https://api.skillsregistry.net/v1/skills/rados10-youtube-watch-later

## Description

This YouTube Watch Later MCP server, developed by Radek, integrates with the YouTube API to manage Watch Later playlists. Built with TypeScript and Express, it provides functionality for OAuth2 authentication, playlist item retrieval, and video management. The server implements a refresh token mechanism for maintaining long-term access and includes a separate script for obtaining initial authentication. By abstracting YouTube API interactions into a standardized MCP interface, it enables AI systems to easily interact with users' Watch Later content. This implementation is particularly useful for applications involving content curation, video recommendation systems, and automated playlist management, facilitating use cases such as personalized viewing schedules, content analysis, and cross-platform video organization.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** social-media
- **Updated:** 2026-04-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/rados10-youtube-watch-later)
- **Repository:** <https://github.com/rados10/youtube-watchlater-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "rados10-youtube-watch-later"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/rados10-youtube-watch-later` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/rados10-youtube-watch-later/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt