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

# Cursor

> Connect GooseWorks to Cursor with one click, the CLI, or a manual MCP config

Connect GooseWorks to **Cursor** so its agent can use your GooseWorks tools — files, chat history, automations, and the full [Ad Remixer](/ad-remixer/mcp) — right inside the editor, in your own account and billed to your own credits.

<Note>
  This is the **same** `gooseworks` MCP server documented in [MCP Servers](/concepts/mcp-servers) and [Ad Remixer MCP](/ad-remixer/mcp). Cursor supports both **OAuth** (sign in with GooseWorks — used by the one-click install) and a **`Bearer` token** (used by the CLI install). Either way it's the same server and the same account.
</Note>

## One-click install (recommended)

Click the button below on a machine with Cursor installed:

<a href="cursor://anysphere.cursor-deeplink/mcp/install?name=gooseworks&config=eyJ1cmwiOiJodHRwczovL21jcC5nb29zZXdvcmtzLmFpL21jcCJ9">
  <img src="https://cursor.com/deeplink/mcp-install-dark.svg" alt="Add gooseworks MCP server to Cursor" height="32" />
</a>

<Steps>
  <Step title="Confirm the install">
    Cursor opens with an **Install MCP server** dialog pre-filled with the `gooseworks` server. Click **Install**.
  </Step>

  <Step title="Sign in with GooseWorks">
    In **Cursor Settings → MCP**, the `gooseworks` server shows **Needs authentication**. Click it to start the OAuth flow — sign in with the **same account** you use for GooseWorks and click **Allow**.
  </Step>

  <Step title="Confirm it's connected">
    Back in **Cursor Settings → MCP**, the server shows a green dot with its tool list. Ask the agent something like *"list my GooseWorks brands"* to test it.
  </Step>
</Steps>

## Install from a prompt

Paste one prompt into Cursor's agent. It runs the CLI, which writes the MCP config (with a `Bearer` token) into Cursor for you, then verifies the connection by listing the tools your token can see:

Paste this into your agent — Claude Code, Cursor, Codex, or a chat app like Claude or ChatGPT:

```text theme={null}
Install gooseworks: https://gooseworks.ai/install.md
```

Your agent reads that page and follows it. It **asks you before it installs anything**, then runs the GooseWorks CLI with `--all` (it sets up every coding agent on your machine at once), opens a browser for Google sign-in, checks the install, and carries on in the same chat: it sets up your brand there (it asks for your website and a couple of quick questions), then gets back to what you asked for. You don't need to reopen your agent; the GooseWorks tools also show up in its next session. If your agent is a chat app like claude.ai, the Claude desktop app's chat or ChatGPT, it gives you the MCP connector address instead.

The page only ever runs `npx gooseworks@latest …`. It writes your agent's skills folder, your agent's MCP config (for Cursor that is the global Cursor MCP config, plus the project's `.cursor/mcp.json` if the folder has one), and `~/.gooseworks/credentials.json`. The MCP config entries contain your sign-in token. It writes no other files. Installing is free; some skills spend credits when they run. The check at the end also reports whether ffmpeg and a browser are present; those only matter for rendering video ads on your machine and do not block the install.

The agent keeps going in the same chat and sets up your brand there, calling GooseWorks through the CLI until Cursor loads the new MCP config in its next session. The raw command, if you prefer the terminal, is in the [CLI reference](/concepts/cli#run-it-yourself).

## Manual configuration

Add the server to `~/.cursor/mcp.json` (global) or `<project>/.cursor/mcp.json` (per-project):

```json ~/.cursor/mcp.json theme={null}
{
  "mcpServers": {
    "gooseworks": {
      "url": "https://mcp.gooseworks.ai/mcp"
    }
  }
}
```

With no `headers`, Cursor prompts you to sign in over OAuth. To use a token instead, add a token created in [Settings → CLI & MCP](https://make.gooseworks.ai/settings/api-keys):

```json With a Bearer token theme={null}
{
  "mcpServers": {
    "gooseworks": {
      "url": "https://mcp.gooseworks.ai/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}
```

## What you can do

Once connected, Cursor's agent can, on your behalf and in your account:

* **Make, edit & analyze ads** — research a brand, remix templates into branded creatives, re-roll and edit them, and diagnose campaign performance. Generation runs through the same cloud workflow as the [web app](/ad-remixer/overview) — billed to your credits.
* **Work with your files, chat history & automations** — the standard [MCP Servers](/concepts/mcp-servers) tools.
* **Discover & load skills** — ask the agent to find and use any GooseWorks skill.

## Managing the connection

* **Tool approval** — by default Cursor asks before each MCP tool call and shows the arguments; you can allowlist tools you trust.
* **Disable / remove** — toggle or delete the server in **Cursor Settings → MCP** at any time.
* **Refresh tools** — after we ship new tools, use the refresh icon next to the server in **Cursor Settings → MCP**.

## Troubleshooting

* **Button does nothing** — your browser may be blocking the `cursor://` link; copy the manual config above instead.
* **Server shows red / no tools** — fully quit and reopen Cursor; then check the URL is exactly `https://mcp.gooseworks.ai/mcp`.
* **Sign-in loops** — make sure you're signing in with the account tied to your GooseWorks workspace, and that pop-ups aren't blocked.

## Other clients

* **Claude** (claude.ai and Cowork) — sign-in (OAuth); see [Claude](/connections/claude).
* **ChatGPT** — see [ChatGPT (web)](/connections/chatgpt-web) and [ChatGPT work](/connections/chatgpt-work).
* **Claude Code / Codex** — see [MCP Servers](/concepts/mcp-servers).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.