# AI Agent Setup & Tooling



The **YouTube Transcript & Data API** is designed AI-native from the ground up. Autonomous agents, LLMs, and IDE assistants can read clean markdown schemas, query machine-readable indexes, and execute tools via the Model Context Protocol (MCP).

***

Machine-Readable Endpoints [#machine-readable-endpoints]

For LLMs and agents that need to fetch documentation into context windows without parsing heavy HTML:

| Resource           | URL                                    | Description                                                                         |
| :----------------- | :------------------------------------- | :---------------------------------------------------------------------------------- |
| **LLMs Index**     | `https://docs.ytapi.dev/llms.txt`      | Spec-compliant manifest of all documentation pages with short descriptions.         |
| **Full LLMs Dump** | `https://docs.ytapi.dev/llms-full.txt` | Single concatenated Markdown document containing the entire platform documentation. |
| **Raw Page MDX**   | `https://docs.ytapi.dev/{slug}.mdx`    | Append `.mdx` to any documentation URL to retrieve raw, clean Markdown.             |

<Callout type="idea" title="Agent Quick Fetch">
  In bash-based agents (e.g. Claude Code, Codex, Aider), fetch the entire API reference with:

  ```bash
  curl -s https://docs.ytapi.dev/llms-full.txt
  ```
</Callout>

***

Model Context Protocol (MCP) [#model-context-protocol-mcp]

<div id="mcp" />

Connect your AI assistants directly to the YouTube Transcript API using the Model Context Protocol (MCP).

Claude Desktop & Cursor Configuration [#claude-desktop--cursor-configuration]

Add the following to your MCP client configuration (`claude_desktop_config.json` or `.cursor/mcp.json`):

```json
{
  "mcpServers": {
    "youtube-transcript": {
      "command": "npx",
      "args": ["-y", "@ytapi/mcp-server"],
      "env": {
        "YT_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}
```

Available MCP Tools [#available-mcp-tools]

| Tool Name        | Parameters                           | Description                                                              |
| :--------------- | :----------------------------------- | :----------------------------------------------------------------------- |
| `get_transcript` | `video_id`, `format`, `languages`    | Fetch transcript in `markdown`, `srt`, `vtt`, or `word_timestamps`.      |
| `get_video_info` | `video_id`, `mode` (`fast` / `full`) | Fetch metadata, author, view counts, and chapter boundaries.             |
| `search_youtube` | `query`, `type`, `limit`             | Full-text video and channel search without consuming Google Cloud quota. |
| `get_comments`   | `video_id`, `sort_by`, `limit`       | Retrieve top or recent comment threads with engagement metrics.          |

***

Code Mode & Function Calling [#code-mode--function-calling]

<div id="code-mode" />

When orchestrating extraction pipelines via OpenAI, Anthropic, or Gemini tool calling, provide the JSON Schema directly:

```json
{
  "name": "fetch_youtube_transcript",
  "description": "Extract subtitles or transcripts from any YouTube video in structured Markdown or SRT.",
  "parameters": {
    "type": "object",
    "properties": {
      "video_id": {
        "type": "string",
        "description": "11-character YouTube video ID or full URL"
      },
      "format": {
        "type": "string",
        "enum": ["markdown", "text", "srt", "vtt", "word_timestamps"],
        "default": "markdown"
      }
    },
    "required": ["video_id"]
  }
}
```

***

Platform Skills & System Prompts [#platform-skills--system-prompts]

<div id="skills" />

Cursor Rules (.cursorrules) [#cursor-rules-cursorrules]

Add this prompt rule to your project to instruct Cursor on how to query YouTube transcripts:

```markdown
# YouTube Transcript API Guidelines

When writing code that extracts YouTube subtitles or transcripts:
1. Always use `https://api.ytapi.dev/v1/transcripts` with `Authorization: Bearer $YT_API_KEY`.
2. For LLM summaries or context injection, specify `"format": "markdown"`.
3. For video subtitle synchronizing, specify `"format": "word_timestamps"` with `"word_level": true`.
4. Check `X-Cache` response headers (`HIT` or `MISS`) to measure latency.
5. Refer to complete documentation at `https://docs.ytapi.dev/llms.txt`.
```