> AI agents: this is one page from Mammoth Analytics documentation. The index of all pages as Markdown is https://mammoth.io/docs/llms.txt. Append `.md` to any docs URL, or send `Accept: text/markdown`, to get Markdown. # Add a connector with the connector workspace > Add any Mammoth connector: pick a source in the Connectors launcher, connect it, choose tables and columns in the workspace, and save a dataset. This page shows how to bring data from any connector into Mammoth: find the source in the **Connectors** launcher, connect it, pick the tables and columns you want in the connector workspace, and save them as a dataset. Every connector page links here for the shared steps and adds only what is specific to that source. ## Open the Connectors launcher 1. Go to the **Data Library** and click **New dataset**. 2. In **Where do you want to add data from?**, choose **Connectors**. You can also go to **Data → Connections** and click **New Connection**, which opens the same launcher on its own. The launcher has a search box (**Search sources or paste a link**) and a list of sources grouped in a left-hand menu: - **Popular**: your existing connections (**Your connections**) and the most-used sources - **All**: every connector on your plan - One entry per category, such as **Databases**, **Cloud Storage**, **CRM & Marketing**, **Analytics**, **E-commerce**, **Accounting** and **APIs** - **Files & links**: a file at a URL - **Push**: a webhook that other systems send data to (see [Webhooks](https://mammoth.io/docs/learn/data-sources/webhooks/)) If you type a source Mammoth has no connector for, the launcher offers **Build {source} with the agent**, which builds a connector for an API (see [REST API](https://mammoth.io/docs/learn/connectors/rest-api/)). ![Connect a source: search box, the category menu on the left and Popular connectors](https://mammoth.io/docs/images/20261102_connectors-launcher.webp) ## Connect the source What happens when you click a source depends on its type: - **Databases and warehouses** (PostgreSQL, MySQL, SQL Server, Oracle Database, Amazon Redshift, Snowflake, Google BigQuery, Databricks, Apache Hadoop, SAP HANA, MongoDB): the connection form opens first. Fill in the fields listed on the connector's page and click **Connect**. Once Mammoth has connected, the connector workspace opens on your tables. - **Every other source** (cloud apps, drives, file servers): Mammoth opens the connector workspace straight away with the **Chat** open. The chat starts by connecting the source and shows a card that asks for the connection details, or a button to sign in to the service. Fill it in or sign in. - **An existing connection** under **Your connections**: the workspace opens on that connection, with nothing to re-enter. Analysts who can't create connections see **New sources are added by this project's admins.** and can click **Copy a request** to send an admin what they need. ## Work in the connector workspace The connector workspace is a page in the Data Library (**Data → Connections**) with three parts. On a narrow screen they appear as the tabs **Tables**, **Your table** and **Chat**; on a wide screen they sit side by side. ### Tables The list of tables, objects or files the connection can read. Use **Filter tables** to narrow it. - For a **database**, click a table to open its rows with the query that read them above. See [Query and preview database data](https://mammoth.io/docs/learn/connectors/understanding-data-preview-query/) for the SQL view. - For a **cloud app** (CRM, marketing, accounting, analytics), click a table to see its columns and sample rows, then tick the columns you want. Ticked columns gather in **Your table**. - For a **drive or file server**, browse the folders and open a file. A spreadsheet opens to its tabs. If a file can't open in the panel yet, ask the agent in the chat to import it. If a table you expect is missing, click **Refresh list**, or ask the agent in the chat to find it. ### Your table The table you are building, with one column for each column you ticked. Each column header shows which table it comes from. You can rename a column by clicking its name. Click **Preview 100 rows** to see sample rows before saving. ### Chat **This connector's chat**. Ask it what you want in the table, or what a source returns, and it can pick tables and columns for you. Clicks you make in **Tables** show up in the chat. On a database, the chat starts closed: click **Ask AI** to open it. ## Save the data as a dataset 1. Click **Save as dataset**. 2. Enter a **Dataset name** and pick the folder under **Save in**. 3. Choose how the dataset stays current under **Keep it up to date**: - For a cloud app or Google Sheets: **Daily** or **Manual**. - For a database query: **Daily at 06:00** or **Only when I ask**, and what happens **On each refresh** (see [Choose what happens on each refresh](https://mammoth.io/docs/learn/connectors/understanding-data-preview-query/#choose-what-happens-on-each-refresh)). - For a file from a drive or file server, the dataset is saved once: Mammoth shows **Saved once. Scheduled refresh for files is coming.** To bring in new files on a schedule, use a [File Collection](https://mammoth.io/docs/learn/automations/automation-types/) automation. 4. Click **Save** (for a database query, the button in the dialog is **Save as dataset**). Mammoth reads the source in full, which can take a few minutes for a large table. You can leave the page while it saves. When it finishes, click **Open dataset**. For a database query, choosing **Daily at 06:00** creates a [Dataset Refresh](https://mammoth.io/docs/learn/automations/dataset-refresh/) automation named **Daily refresh · {dataset name}**, whose first run is the next morning. You can change its schedule later under **Data → Automation**. ## Pick up a connector you didn't finish A connector you open but don't save stays as a draft. The launcher lists drafts at the top with their state, such as **Not connected yet** or **Connected · pick your columns**. Click **Continue** on a draft to reopen it. Connections that need attention, such as an expired key, appear under **Needs attention** with a **Fix** button that opens the connection on the **Data → Connections** page. ## Related pages - [Connectors](https://mammoth.io/docs/learn/connectors/): every connector and its page - [Query and preview database data](https://mammoth.io/docs/learn/connectors/understanding-data-preview-query/) - [Network requirements & IP whitelisting](https://mammoth.io/docs/learn/connectors/network-requirements/) - [Dataset Refresh](https://mammoth.io/docs/learn/automations/dataset-refresh/) --- Source: https://mammoth.io/docs/learn/connectors/connector-workspace.md · Updated: 2026-11-03