# yt-transcript-mcp

> Use this tool when you need to extract and refine transcripts from YouTube videos, solving issues with incomplete or inaccurate subtitles. It takes YouTube video URLs as input and outputs cleaned transcripts, handling manual and auto-generated subtitles with deduplication. Ideal for use cases requiring accurate video content analysis or text extraction, such as media monitoring or content research.

Canonical page: https://skillsregistry.net/skills/warshanks-yt-transcript-mcp  
JSON: https://api.skillsregistry.net/v1/skills/warshanks-yt-transcript-mcp

## Description

Fetches and cleans YouTube video transcripts using yt-dlp, with fallback from manual to auto-generated subtitles and deduplication.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** social-media
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/z3wx8zql2s)
- **Repository:** <https://github.com/warshanks/yt-transcript-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": "warshanks-yt-transcript-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/warshanks-yt-transcript-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/warshanks-yt-transcript-mcp/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