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

# Introduction

> Connect an AI assistant to your NeetoRecord workspace over the Model Context Protocol.

NeetoRecord runs a hosted MCP server. Point a compatible AI assistant at it and
the assistant can work with your recordings directly: no local install, no
glue code.

Once connected, an assistant can search recordings by title or by what was said
in them, read transcripts and chapters, pull a still frame out of a video,
produce share links and embed codes, organize recordings into folders and tags,
and report view analytics. The full list is on the [Tools](/mcp/tools) page.

## What you need

* An AI assistant that supports MCP. Setup steps for Claude, ChatGPT, Claude
  Code, Codex, Cursor, Gemini CLI, VS Code with GitHub Copilot, and Windsurf are
  on [Connect your assistant](/mcp/connect).
* A NeetoRecord API key, but only for workspace scoped access. Every client can
  sign you in over OAuth instead, which needs nothing beyond the server URL. See
  [Authentication](/mcp/authentication).

The choice decides what the assistant can reach: an OAuth connection acts as you
and sees what you see, while an API key acts as the workspace and sees everything
in it.

## Next steps

<CardGroup cols={2}>
  <Card title="Authentication" icon="key" href="/mcp/authentication">
    Generate an API key and understand how the server uses it.
  </Card>

  <Card title="Connect your assistant" icon="plug" href="/mcp/connect">
    Server details and per client configuration.
  </Card>

  <Card title="Examples" icon="comments" href="/mcp/examples">
    Prompts that show what the connection is good for.
  </Card>

  <Card title="Tools" icon="screwdriver-wrench" href="/mcp/tools">
    Every tool the server exposes, grouped by resource.
  </Card>
</CardGroup>