> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agentcdn.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Overview

> AgentTV is the video layer for AI. It makes your videos findable, playable and credited in ChatGPT, Claude, Gemini, the other agents people use, and on your own site.

AgentTV makes your video library usable by AI. A person asks ChatGPT, Claude, Gemini or your own site a question. The answer points to your video at the right second, names you, and links back to your page.

AI apps do not watch video. They read the text that comes with it. AgentTV builds that text for every video you connect, and serves it in the forms search engines and agents read. Your videos keep playing from your own player and your own CDN, under your own rules.

> [!NOTE]
>
> **For AI agents.** These docs have an index at [/llms.txt](https://docs.agentcdn.com/llms.txt), the full text at [/llms-full.txt](https://docs.agentcdn.com/llms-full.txt), and a Markdown copy of every page at its path plus `.md`. See [For AI agents](https://docs.agentcdn.com/guides/ai-agents.md).

## Pick your path

> [card] [You run a video platform](https://docs.agentcdn.com/guides/import-catalog.md)
>
> Brands and media companies with their own player and CDN. Import your catalog by your own ids, put metadata on your pages, and choose how videos play in AI apps.

> [card] [You build agents and apps](https://docs.agentcdn.com/quickstart.md)
>
> Builders. Make one request, get moments with exact times, and connect an AI app over MCP. No key for public libraries.

> [card] [You are a creator](https://docs.agentcdn.com/guides/connect-sources.md)
>
> Connect your YouTube channel or other accounts, choose where your videos appear, and publish your own app in ChatGPT.

> [card] [You run a paid membership](https://docs.agentcdn.com/guides/member-libraries.md)
>
> Make videos members-only, so only your members can search and ask on your member page, and watch in AI apps. Connect Kajabi.

## How it fits together

```mermaid theme={null}
flowchart LR
  A["Your catalog<br/>sitemap and API"] --> B["Import<br/>private copy for analysis"]
  B --> C["Index<br/>transcript, chapters,<br/>moments, rights"]
  C --> D["Page block<br/>JSON-LD on your page"]
  D --> E["Search engines and<br/>AI crawlers"]
  C --> F["ARV record and<br/>MCP tools"]
  E --> G["AI apps"]
  F --> G
  G --> H["Playback<br/>your player or your HLS"]
```

1. **Import.** AgentTV reads your video sitemap and your metadata API, and stores each video under your own id. See [Import a catalog](https://docs.agentcdn.com/guides/import-catalog.md).
2. **Index.** AgentTV builds the transcript, chapters, moments, people, places and rights for each video. See [The ARV record](https://docs.agentcdn.com/concepts/arv-record.md).
3. **Publish at crawl time.** Your page template fetches one block per video and renders it in your page. Search engines and AI crawlers read it. See [Put metadata on your pages](https://docs.agentcdn.com/guides/page-metadata.md).
4. **Answer at inference time.** When an AI app answers a question, it reads the ARV record or calls the MCP tools for the exact moment. See [Crawl time and inference time](https://docs.agentcdn.com/concepts/crawl-and-inference.md).
5. **Play.** The moment plays in your own player, or in the AgentTV player from your own stream. See [Play in your own player](https://docs.agentcdn.com/guides/playback.md).

## What AgentTV builds for each video

* **Transcript.** Timed sentences of what is said, with speakers.
* **Chapters.** Titled sections with a short summary each.
* **Moments.** The start and end time that answers a question, with the words and on-screen text behind it.
* **People, places, products and topics.** Who and what each video covers, so a question about a person finds the right moment.
* **Rights.** Your rules for each video: whether AI apps may search, cite, quote, summarize, play or train on it. Every surface reads the same rules, and every use is logged.

## A typical brand setup

**1. Import your catalog**

Give us your video sitemap and read access to your metadata API. Pick the videos to import. See [Import a catalog](https://docs.agentcdn.com/guides/import-catalog.md).

**2. Put metadata on your pages**

Your page template fetches one block per video page and renders it server side. See [Put metadata on your pages](https://docs.agentcdn.com/guides/page-metadata.md).

**3. Choose how videos play**

Play in your own player, or in the AgentTV player from your own HLS stream. See [Play in your own player](https://docs.agentcdn.com/guides/playback.md).

**4. Connect AI apps and your site**

Connect the MCP server, add Ask to your pages, and build rails from chapters. See [Play a moment in an AI app](https://docs.agentcdn.com/guides/play-in-chat.md), [Add Ask to your site](https://docs.agentcdn.com/guides/embed-ask.md) and [Build a rail from chapters](https://docs.agentcdn.com/guides/moment-rails.md).

**5. Set access and measure**

Allow or block AI use, then track AI answers before and after. See [Control AI access](https://docs.agentcdn.com/guides/access-and-rights.md) and [Track AI visibility](https://docs.agentcdn.com/guides/visibility.md).

No partnership with an AI company is needed. AgentTV works through the open formats search engines and AI apps already read.

## Hosts

| Host | What it serves |
| - | - |
| `https://api.agentcdn.com` | The REST API: public routes and the `/v1` account API. |
| `https://mcp.agentcdn.com` | The MCP servers. |
| `https://app.agentcdn.com` | The console: your account, keys and settings. |
| `https://agenttv.com` | Public pages, watch pages and the Ask script. |

## The open standard

The metadata AgentTV publishes follows the Agent-Ready Video (ARV) standard. ARV is one open record that tells AI what is in a video, who owns it and how it may play. The spec lives at [agentreadyvideo.org](https://agentreadyvideo.org).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.