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

# Quickstart

> Sign up, get an API key, and make your first request to Synthesize Bio.

This guide takes you from zero to a working API call in about five minutes. Pick the SDK or integration that matches your environment at the end.

<Steps>
  <Step title="Create an account">
    Sign up at [app.synthesize.bio](https://app.synthesize.bio) and verify your email.
  </Step>

  <Step title="Generate an API key">
    In the platform, open **Settings → API keys** and click **Create key**. Copy the key somewhere safe — you won't be able to view it again.

    <Note>
      Treat the key like a password. Set it as an environment variable rather than checking it into source control:

      ```bash theme={null}
      export SYNTHBIO_API_KEY="sk-..."
      ```
    </Note>
  </Step>

  <Step title="Pick how you want to call the platform">
    <Tabs>
      <Tab title="Python (`pysynthbio`)">
        ```bash theme={null}
        pip install pysynthbio
        ```

        ```python theme={null}
        from pysynthbio import SynthbioClient

        client = SynthbioClient()  # picks up SYNTHBIO_API_KEY
        models = client.list_models()
        print(models[0])
        ```

        See the [Python SDK docs](/pysynthbio) for the full reference.
      </Tab>

      <Tab title="R (`rsynthbio`)">
        ```r theme={null}
        install.packages("rsynthbio")

        library(rsynthbio)
        models <- list_models()
        head(models)
        ```

        See the [R SDK docs](/rsynthbio) for the full reference.
      </Tab>

      <Tab title="MCP (Claude / Cursor)">
        Configure Synthesize Bio as an MCP server in your client of choice — the [MCP setup guide](/platform) walks through Claude Desktop, Cursor, and other compatible tools.
      </Tab>
    </Tabs>
  </Step>

  <Step title="Make your first prediction">
    Once `list_models()` returns results, you have a working connection. Pick a `model_id` and use `get_example_query(model_id=...)` to generate a starter request you can adapt to your data.

    Need to know which metadata fields a model accepts? See [Available metadata](/get-started/available-metadata). Want to understand public dataset inputs? See [Public dataset preprocessing](/get-started/data-preprocessing).
  </Step>
</Steps>

## Next article

<Card title="Available metadata" icon="database" href="/get-started/available-metadata">
  Browse the metadata vocabularies that each model accepts.
</Card>

## What's next?

<CardGroup cols={2}>
  <Card title="Python SDK reference" icon="python" iconType="brands" href="/pysynthbio">
    Full `pysynthbio` reference and recipes.
  </Card>

  <Card title="R SDK reference" icon="r-project" iconType="brands" href="/rsynthbio">
    Full `rsynthbio` reference and recipes.
  </Card>

  <Card title="MCP setup" icon="plug" href="/platform">
    Connect Synthesize Bio to Claude, Cursor, and other MCP clients.
  </Card>
</CardGroup>