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

# Quickstart

> Install the Nodal plugin, connect a read-only warehouse, run setup, and build your first domain — in about ten minutes of setup.

Four steps. Everything runs inside your own agent, on your own machine.

<Note>
  **Nothing reaches Nodal.** The open-source package is instructions and local scripts that run inside
  your agent — no data, no credentials, no queries, no results, no telemetry. Warehouse access goes
  through an MCP server *you* configure with a read-only identity. The only external data flow is the
  one you already have with your agent's model provider. The [hosted MCP](/mcp/overview) is a
  separate, paid product that activates only when you opt in.
</Note>

<Steps>
  <Step title="Install the plugin">
    Pick **one** installation method per host — installing both a native plugin and skills.sh copies
    makes every skill appear twice.

    <Tabs>
      <Tab title="Claude Code">
        ```bash theme={null}
        claude plugin marketplace add nodal-data/nodal-context
        claude plugin install nodal-analytics@nodal
        ```

        To update an existing installation:

        ```bash theme={null}
        claude plugin marketplace update nodal
        claude plugin update --scope user nodal-analytics@nodal
        ```
      </Tab>

      <Tab title="Codex">
        ```bash theme={null}
        codex plugin marketplace add nodal-data/nodal-context
        codex plugin add nodal-analytics@nodal
        ```
      </Tab>

      <Tab title="Cursor & other skill-compatible agents">
        ```bash theme={null}
        npx skills@latest add nodal-data/nodal-context
        ```

        This copies editable skills into your project. Select `setup-nodal` along with the workflows you
        want to use.
      </Tab>
    </Tabs>

    <Accordion title="Or let your agent install it for you">
      If you already use an AI coding agent, paste this into a project where you want to evaluate Nodal.
      The [agent guide](https://github.com/nodal-data/nodal-context/blob/main/docs/agent-guide.md) it
      reads teaches the agent to pick one installation path, ask before changing anything, and stop at
      the new-session boundary.

      ```text theme={null}
      Help me understand and set up Nodal Analytics for this project. Read
      https://github.com/nodal-data/nodal-context/blob/main/docs/agent-guide.md
      first. Explain what will change, choose only one supported installation method,
      and ask before installing anything or editing configuration. Then walk me
      through it one step at a time.
      ```
    </Accordion>
  </Step>

  <Step title="Connect a read-only warehouse over MCP">
    Wire your warehouse's MCP server into your agent with a **read-only** role — Nodal only ever
    `SELECT`s. The [Connect your database](/open-source/connect-your-database) page lists the
    vendor-maintained MCP servers for Snowflake, BigQuery, Redshift, and Databricks, plus the optional
    query-history grant that makes the interview's best input available.

    Start your agent from the folder that holds your data lineage, so the context repo Nodal creates
    sits next to it:

    ```text theme={null}
    code/                        <-- start Claude Code / Codex here
    ├── dbt-repo/                # your existing dbt project (optional, recommended)
    └── analytics-context/       # created by Nodal, a sister repo to the dbt project
    ```
  </Step>

  <Step title="Start a new session and run setup">
    Plugins are discovered at the session boundary, so **start a fresh agent session** after
    installing — a skill that "isn't showing up" is almost always this. Then run setup once:

    ```text theme={null}
    # Claude Code
    /nodal-analytics:setup-nodal

    # Codex
    $setup-nodal
    ```

    Setup probes your warehouse connection (read-query, metadata, query-history), discovers nearby dbt
    and context sources, and writes only sanitized paths and capability classifications to a
    gitignored `.nodal.local.json` — never credentials.
  </Step>

  <Step title="Ask">
    Either take the short path or the full one:

    ```text theme={null}
    # ~30 minutes — one domain, five high-leverage questions, a live check:
    Take Nodal for a test drive on one analytics domain.

    # The complete interview:
    Build my analytics context.
    ```

    Both write a reviewable `../analytics-context/` git repo and offer to push it to your own private
    remote. Every confirmed definition also becomes an eval seed, and each domain closes by verifying
    its answers against a dashboard you trust.
  </Step>
</Steps>

## Next

<CardGroup cols={3}>
  <Card title="Build your context" icon="comments" href="/open-source/build-your-context">
    What the interview asks, what it needs, and what it writes.
  </Card>

  <Card title="Evaluation as you build it" icon="chart-line" href="/open-source/evaluation">
    Watch a live dashboard verification and see the accuracy delta.
  </Card>

  <Card title="Share with your team" icon="users" href="/mcp/share-with-your-team">
    Put the context in front of everyone's agent with one `.mcp.json` file.
  </Card>
</CardGroup>