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

# AI tools

> Wire any MCP-capable AI tool to your xysq memory. One connection per tool, one context lake behind all of them.

Connect a tool once and it shares memory with every other tool you've connected. Claude learns something on Monday, Cursor knows it on Tuesday. Each connection takes one to three minutes.

## What a connection gives your tool

Every connected tool talks to the same **context lake**: one per user or team, holding your **context graphs** (Personal, Teams, Agents). Agents read from one or many graphs and write to their own.

The connection exposes four MCP tools. That's the whole surface; your AI tool does no orchestration.

| Tool            | What it does                                                                                                                                                                                                                   |
| --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| `userinfo`      | Confirms the connection is authenticated and shows the state of your memory (items captured, items pending processing).                                                                                                        |
| `push_context`  | Ships session content in, verbatim. The xysq Memory Engine does all processing server-side: extraction, deduplication, distillation into your context graph. Re-pushing identical content is safe; the server dedupes by hash. |
| `pull_context`  | Semantic recall. One call, assembled context back. New content is retrievable in seconds; the distilled graph catches up within minutes.                                                                                       |
| `share_context` | Proposes sharing a page or source with someone by email. Nothing is sent until you approve it in the xysq app (Vault → Sharing). Shares are live, view-only, and revocable.                                                    |

## Two ways to authenticate

* **OAuth** (Claude, Claude Code, ChatGPT): sign in through your browser once. No key to copy.
* **API key** (Cursor, Windsurf, Antigravity, generic clients): a bearer token you generate in the app's connect guide. Each tool gets its own key so you can revoke them independently. The full value is shown exactly once.

Server endpoints, if your client asks:

```text theme={"dark"}
https://api.xysq.ai/mcp   # streamable HTTP (recommended)
https://api.xysq.ai/sse   # legacy SSE
```

## Pick your tool

<CardGroup cols={2}>
  <Card title="Claude Code" icon="terminal" href="/connect/claude-code">
    Install the plugin, sign in via /mcp. \~1 min, OAuth.
  </Card>

  <Card title="Claude" icon="message" href="/connect/claude">
    Add a custom integration in Settings. \~3 min, OAuth.
  </Card>

  <Card title="Cursor" icon="code" href="/connect/cursor">
    One-click install or paste the config. \~2 min, API key.
  </Card>

  <Card title="ChatGPT" icon="comments" href="/connect/chatgpt">
    Create an app in ChatGPT settings. \~2 min, OAuth.
  </Card>

  <Card title="Windsurf" icon="wind" href="/connect/windsurf">
    Paste the config and restart. \~2 min, API key.
  </Card>

  <Card title="Antigravity" icon="rocket" href="/connect/antigravity">
    Direct SSE connection with header support. \~2 min, API key.
  </Card>

  <Card title="Any MCP client" icon="plug" href="/connect/generic">
    Streamable HTTP or legacy SSE. \~2 min, API key.
  </Card>
</CardGroup>

<Tip>
  The in-app guides at [app.xysq.ai](https://app.xysq.ai) walk the same steps with your key and config pre-filled, and watch for your tool's first call to confirm the connection is live. These pages mirror them for reference.
</Tip>