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

# Quickstart

> From sign-up to a connected tool in a few minutes.

This guide gets you a working OneLamp setup: an account, your personal MCP
endpoint, and a tool that loads and saves your context automatically.

## 1. Create your account

Go to [app.onelamp.ai](https://app.onelamp.ai) and sign in with GitHub, Google,
or a one-time email code. This is the only account you'll need — OneLamp is its
own identity provider, so your AI clients authorize against it directly.

## 2. Copy your MCP endpoint

After signing in, the **Connect** home shows your personal MCP endpoint:

```
https://api.onelamp.ai/mcp
```

<Note>
  The endpoint URL is the same for everyone, but it's **personal and
  authenticated** — every request is scoped to the signed-in user. There are no
  API keys to copy or rotate; clients sign in with OneLamp via OAuth.
</Note>

## 3. Connect a client

It's one endpoint, so connecting is the same everywhere: add
`https://api.onelamp.ai/mcp` to your client as a remote MCP server. The first time
it connects, it opens OneLamp in your browser to sign in and authorize — no API
keys. After that, the token is cached and refreshed automatically.

A few clients add more on top (Claude Code, Codex, and Cursor ship lifecycle
hooks that auto-load and auto-save context). The [Connect your tool](/integrations)
page has the copy-paste setup for each.

<Card title="Connect your tool" icon="plug" href="/integrations">
  Universal setup plus the client-specific bits for Claude Code, Codex, Cursor,
  VS Code, and ChatGPT — each has its own tab.
</Card>

## 4. Seed your context (one-time)

Connecting captures what your tools learn **going forward**. To also pull in what
a tool *already* knows about you, run a one-time seed:

<Steps>
  <Step title="Claude Code">
    Run `/ol` (alias of `/onelamp`). It scans this repo's `CLAUDE.md`,
    `.cursorrules`, or `AGENTS.md` and saves them with `save_context`.
  </Step>

  <Step title="Any other tool">
    Tell it: *"Fetch [https://app.onelamp.ai/setup.md](https://app.onelamp.ai/setup.md) and follow it."* It seeds your
    context from what the tool already knows **and** adds OneLamp to the
    tool's system prompt so it keeps loading and saving context — which is how
    hookless browser tools (Gemini, Perplexity, ChatGPT web) stay in sync.
  </Step>
</Steps>

## 5. Verify the connection

Once connected, your tool has the context tools available. Ask it to run a
quick check:

<Steps>
  <Step title="Save something durable">
    Tell your tool: *"Remember that I deploy on Fridays."* It should call
    `save_context` and confirm with an id.
  </Step>

  <Step title="Read it back">
    In a fresh session, ask: *"When do I deploy?"* The tool calls `get_context`
    and retrieves the fact you saved — even from a different tool.
  </Step>

  <Step title="Export your data (anytime)">
    Your data is always yours to take. From your **Account** in the
    [OneLamp app](https://app.onelamp.ai), export your full store as portable JSON
    on demand — no queue, no lock-in.
  </Step>
</Steps>

<Check>
  If the tool saved a fact in one tool and retrieved it in another, OneLamp is
  working — every tool you connect now uses what the others have learned, with
  no re-explaining.
</Check>

## What's next

<CardGroup cols={2}>
  <Card title="Understand context memory" icon="brain" href="/concepts/context-memory">
    How saving, deduping, and ranked retrieval work under the hood.
  </Card>

  <Card title="Build your Library" icon="book" href="/concepts/library">
    Ingest documents and URLs into an interlinked Library your tools can query.
  </Card>

  <Card title="Connect your tools" icon="link" href="/concepts/data-sources">
    Pull in documents from Notion, Drive, Slack, and other MCP servers.
  </Card>

  <Card title="Browse the tools" icon="wrench" href="/tools/context">
    The full reference for every tool your AI tool can call.
  </Card>
</CardGroup>