> 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.

# Find a connector, draft or saved connection in Mammoth

> Search Mammoth's Connectors launcher by name, sentence or link, browse categories, see plan limits, and reopen draft connectors and saved connections.
>
> Applies to: The launcher shows the connectors your plan includes. Roles: Project Admins see Needs attention and can discard drafts. Where: Data Library › New dataset › Connectors

The Connectors launcher lists every source you can connect, your saved connections and the connectors you started but didn't save. Open it from the **Data Library**: click **New dataset** and choose **Connectors**, or go to **Data → Connections** and click **New Connection**. To connect the source you find, see [Connect a database or app](https://mammoth.io/docs/learn/get-data-in/connect-a-source/).

## Browse the launcher menu

| Menu entry | What it lists |
| --- | --- |
| **Popular** | Your existing connections (**Your connections**) and the most-used sources |
| **All** | Every connector on your plan, then the API sources Mammoth already knows |
| A category | Such as **Databases**, **Cloud Storage**, **CRM & Marketing**, **Analytics**, **E-commerce**, **Accounting**, **APIs** and **Education** |
| **Files & links** | A file at a URL (see [Import from a URL](https://mammoth.io/docs/learn/get-data-in/import-from-a-url/)) |
| **Push** | A webhook that other systems send data to (see [Receive data by webhook](https://mammoth.io/docs/learn/get-data-in/webhooks/)) |

Besides its built-in connectors, the launcher lists several hundred API sources Mammoth already knows (for example payment, payroll, school or marketing systems), under the matching category or under **APIs**. Clicking one opens the connector workspace, where the agent reads the vendor's API documentation and builds the connector with your key. See [REST API](https://mammoth.io/docs/learn/get-data-in/connectors/rest-api/).

## Search the launcher by name, sentence or link

The search box (**Search sources or paste a link**) reads what you type in one of three ways. The first result is what **Enter** does.

| You type | The launcher offers |
| --- | --- |
| A name of one or two words, such as `hubspot` | Matching drafts, connections and sources, then **Build hubspot with the agent** |
| A sentence, such as `hubspot deals with owner and amount` | **Start: hubspot deals with owner and amount**, which opens a draft on the source the sentence names and hands the rest to the chat (if it names no source, the chat asks which one), then your drafts and connections for that source |
| A link starting with `http://` or `https://` | **Fetch this file**, which reads a CSV, Excel or JSON file at that address, or **It's an API: build it with the agent** |

## Connectors not on your plan

A connector your plan doesn't include still turns up in search, greyed out, with **Not on your plan · See plans**. Clicking it opens the plan picker. A connector your plan has retired stays available only while your project still has connections to it.

## Pick up a connector you didn't finish

A connector you open but don't save stays as a draft, listed in the launcher under **In progress** with its state: **Not connected yet**, **Pick a table**, **5 columns picked · not saved yet** or **2 columns still to find**. Click one to reopen it.

Up to two drafts show; the rest, and drafts older than 14 days, sit behind a "more drafts" line. Drafts also appear on the [Connections page](https://mammoth.io/docs/learn/get-data-in/connections/#continue-or-discard-a-draft), where a Project Admin can **Discard** one. That removes the draft and its chat; your data doesn't change.

Project Admins also see **Needs attention**: connections with a reason such as **key expired** or **unreachable**. Click one to open it on the **Data → Connections** page.

## Start another dataset from a saved connection

Click the connection under **Your connections** in the launcher, or go to **Data → Connections**, click the connection, and click **Create dataset**. A new draft opens with nothing to re-enter. If a draft can't be started, Mammoth opens the connection's own page, listing its **Tables and endpoints**; click **New dataset from this**.

## Related

- [Connect a database or app](https://mammoth.io/docs/learn/get-data-in/connect-a-source/): connect the source and save a dataset.
- [Mammoth connectors](https://mammoth.io/docs/learn/get-data-in/connectors/): every connector with its sign-in and firewall needs.
- [Manage saved connections](https://mammoth.io/docs/learn/get-data-in/connections/): edit, reuse and delete connections and drafts.
- [REST API](https://mammoth.io/docs/learn/get-data-in/connectors/rest-api/): build a connector for a service Mammoth doesn't list.

---
Source: https://mammoth.io/docs/learn/get-data-in/find-a-connector.md · Updated: 2026-11-08