# YouTube Transcripts, Search & Summaries

> YouTube Transcripts, Search & Summaries is a freemium MCP server for design and media. Fetch YouTube transcripts, search, chapters and extractive summaries for agents. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Platforms:** API, CLI, self-hosted
- **Website:** https://apify.com/parallelstudio/youtube-transcripts-mcp
- **Repository:** https://github.com/gunnargray-dev/youtube-transcripts-mcp
- **MCP Registry name:** io.github.gunnargray-dev/youtube-transcripts-mcp
- **Categories:** design and media, web search and scraping, developer tools
- **Listing updated:** 2026-11-15

## About

Every tool here is read-only and works without a YouTube API key or Google account. No language model runs on the server, so summaries are extractive: a TL;DR, de-duplicated key points, keywords, notable quotes and bullets per chapter, each with a timestamp and a link to that moment.

get_transcript returns captions with metadata, available caption languages and whether the track is auto-generated, as plain text, timestamped paragraphs, segments or SRT, with optional machine translation. search_videos queries YouTube with filters for upload date, length and features such as subtitles. get_video_chapters uses the creator's chapters, or derives topic segments from the transcript when there are none.

It can be used hosted on Apify at pay-per-call pricing with an Apify token, or run locally over stdio from the open-source repository. Video inputs accept an 11-character id or URLs of many YouTube forms, including Shorts and live links.

## Features

- **Multi-format transcripts:** Text, timestamped paragraphs, segments or SRT, with optional translation.
- **YouTube search:** Filters by upload date, length, sort order and subtitle availability.
- **Chapters with fallback:** Creator chapters, or topic segments derived from the transcript.
- **Extractive summaries:** Timestamped key points and quotes with no LLM costs.
- **Flexible video input:** Accepts ids, watch links, youtu.be, Shorts, embed and live URLs.

## Good for

- Summarize a two-hour podcast with timestamps
- Quote exact moments from a talk
- Export SRT subtitles
- Search for sources then pull their transcripts
- Draft show notes from a video

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http youtube-transcripts-mcp https://parallelstudio--youtube-transcripts-mcp.apify.actor/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://parallelstudio--youtube-transcripts-mcp.apify.actor/mcp
```

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

```json
{
  "mcpServers": {
    "youtube-transcripts-mcp": {
      "url": "https://parallelstudio--youtube-transcripts-mcp.apify.actor/mcp"
    }
  }
}
```

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

```json
{
  "servers": {
    "youtube-transcripts-mcp": {
      "type": "http",
      "url": "https://parallelstudio--youtube-transcripts-mcp.apify.actor/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "youtube-transcripts-mcp": {
      "serverUrl": "https://parallelstudio--youtube-transcripts-mcp.apify.actor/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "youtube-transcripts-mcp": {
      "type": "http",
      "url": "https://parallelstudio--youtube-transcripts-mcp.apify.actor/mcp"
    }
  }
}
```

## Tools

- `get_transcript`: Returns a video's transcript and metadata as text, segments or SRT, with optional translation.
- `search_videos`: Searches YouTube with date, duration, sort and feature filters.
- `get_video_chapters`: Returns chapters with start and end times, deriving them from the transcript if needed.
- `summarize_transcript`: Builds an extractive summary with key points, keywords and quotes.

## FAQ

### Do I need a YouTube API key?

No, and no Google account either.

### Is an LLM used for summaries?

No. Summaries are extractive and built without a model on the server.

### How is it billed?

The hosted Apify version is pay per call with an Apify token; the code can also be run locally over stdio.

### Can it translate transcripts?

Yes, YouTube's machine translation is available through translate_to.

### Is YouTube Transcripts, Search & Summaries free?

YouTube Transcripts, Search & Summaries has a free plan, with paid plans for more usage or features.

### How do I add YouTube Transcripts, Search & Summaries to Claude Code?

Run this command in your terminal: claude mcp add --transport http youtube-transcripts-mcp https://parallelstudio--youtube-transcripts-mcp.apify.actor/mcp

### What are the best alternatives to YouTube Transcripts, Search & Summaries?

The closest alternatives to YouTube Transcripts, Search & Summaries are REA, Scrapling MCP Server, HyperFrames by HeyGen, Codebase Memory and GitHub.

## Alternatives

- [REA](https://ai-powered.com/mcp/rea): REA is an open-source MCP server for developer tools.
- [Scrapling MCP Server](https://ai-powered.com/mcp/scrapling-mcp-server): Scrapling MCP Server is an open-source MCP server for web search and scraping.
- [HyperFrames by HeyGen](https://ai-powered.com/mcp/hyperframes-by-heygen): HyperFrames by HeyGen is a freemium MCP server for design and media.
- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [GitHub](https://ai-powered.com/mcp/github-2): GitHub is an open-source MCP server for developer tools.
- [Serena MCP: the IDE for your agent](https://ai-powered.com/mcp/serena-mcp-the-ide-for-your-agent): Serena MCP: the IDE for your agent is an open-source MCP server for developer tools.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [Firecrawl MCP Server](https://ai-powered.com/mcp/firecrawl-mcp-server): Firecrawl MCP Server is a freemium MCP server for web search and scraping.

---
Source: https://ai-powered.com/mcp/youtube-transcripts-search-and-summaries
