# MCP Server YouTube Transcript (MCP server)

> MCP Server YouTube Transcript is an MCP server that enables retrieval of transcripts from YouTube videos. This server provides direct access to video captions and subtitles through a simple interface. It has 602 GitHub stars, is released under the MIT license and runs locally with npx -y @kimtaeyoon83/mcp-server-youtube-transcript.

A Model Context Protocol server that enables retrieval of transcripts from YouTube videos. This server provides direct access to video captions and subtitles through a simple interface.

## Key facts

| Fact | Value |
|---|---|
| Repository | https://github.com/kimtaeyoon83/mcp-server-youtube-transcript |
| GitHub stars | 602 |
| License | MIT |
| Language | TypeScript |
| Transport | stdio |
| Packages | npm: @kimtaeyoon83/mcp-server-youtube-transcript |
| Remote URL | none |
| Needs API key | yes |
| Official | no |
| Works with | Claude Desktop, Claude Code, Cursor, VS Code |
| Category | AI & search |
| Latest release | none |
| Last commit | Jul 21, 2026 |

## Install

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "mcp-server-youtube-transcript": {
      "command": "npx",
      "args": [
        "-y",
        "@kimtaeyoon83/mcp-server-youtube-transcript"
      ],
      "env": {
        "TWELVELABS_API_KEY": "your-value"
      }
    }
  }
}
```

Settings > Developer > Edit Config. macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\. Restart Claude Desktop afterwards.

### Claude Code

```sh
claude mcp add --env TWELVELABS_API_KEY=your-value --transport stdio mcp-server-youtube-transcript -- npx -y @kimtaeyoon83/mcp-server-youtube-transcript
```

### Cursor (.cursor/mcp.json)

```json
{
  "mcpServers": {
    "mcp-server-youtube-transcript": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@kimtaeyoon83/mcp-server-youtube-transcript"
      ],
      "env": {
        "TWELVELABS_API_KEY": "your-value"
      }
    }
  }
}
```

Project file; use ~/.cursor/mcp.json to enable it in every project.

### VS Code (.vscode/mcp.json)

```json
{
  "inputs": [
    {
      "type": "promptString",
      "id": "twelvelabs_api_key",
      "description": "TWELVELABS_API_KEY",
      "password": true
    }
  ],
  "servers": {
    "mcp-server-youtube-transcript": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@kimtaeyoon83/mcp-server-youtube-transcript"
      ],
      "env": {
        "TWELVELABS_API_KEY": "${input:twelvelabs_api_key}"
      }
    }
  }
}
```

Config formats checked against the official docs on 2026-10-07.

## Environment variables

- `TWELVELABS_API_KEY` (secret): Shown in the README's example configuration.

## Tools

- `get_transcript`
- `lang`: Language code for transcript (e.g., 'ko', 'en'). Automatically falls back to available languages if requested language…
- `include_timestamps`: Include timestamps in output (e.g., '[0:05] text')
- `strip_ads`: Filter out sponsorships, ads, and promotional content from transcript based on chapter markers
- `analyze_video`
- `prompt`: Instruction or question for the model (e.g. "Summarize this video in 3 sentences" or "What products are shown?").
- `model`: Pegasus model to use ("pegasus1.2" or "pegasus1.5").
- `max_tokens`: Maximum response length in tokens.

## Similar MCP servers

- [haiku.rag](https://appsgit.com/mcp-servers/haiku-rag): Local-first agentic RAG with citations - hybrid search, reranking, multimodal document retrieval. (636 stars, MIT)
- [Octocode](https://appsgit.com/mcp-servers/octocode): AI-powered code indexer with semantic search and knowledge graphs. (517 stars, Apache-2.0, official)
- [ThoughtDAG](https://appsgit.com/mcp-servers/thoughtdag): Search local AI conversations by file or phrase and recall source turns. (699 stars, MIT)
- [Telemem](https://appsgit.com/mcp-servers/telemem): Long-term and multimodal memory for AI agents - character-aware, mem0-compatible, fully-local option. (494 stars, Apache-2.0, needs API key)
- [MegaMemory](https://appsgit.com/mcp-servers/megamemory): Persistent project knowledge graph for coding agents. (727 stars, MIT)
- [Context](https://appsgit.com/mcp-servers/context): Local-first documentation for AI agents. Offline, instant, private doc retrieval. (429 stars, Apache-2.0, official)

---

Canonical page: https://appsgit.com/mcp-servers/mcp-server-youtube-transcript
Source: appsgit (https://appsgit.com), the app store for github. Data from the GitHub API, refreshed daily.
Machine access: JSON API https://appsgit.com/api/v1/apps (OpenAPI: https://appsgit.com/openapi.json), MCP server https://mcp.appsgit.com/mcp, full index https://appsgit.com/llms-full.txt.