### Client Configuration

Claude (Web & Desktop)
Availability
A Claude paid subscription is required to use MCP connectors. On Team and Enterprise plans, your workspace administrator must first add the Databox MCP connector in workspace settings before team members can use it.

1. Navigate to claude.ai or open Claude desktop app
2. Go to `Settings > Connectors > Add custom connector`
3. Configure the integration:
  * Name: Databox
  * URL: `https://mcp.databox.com/mcp`
  * Authentication: OAuth 2.0 (follow the on-screen authorization flow)
4. Start asking questions about your Databox data


Claude Code
Availability
A Claude paid subscription is required to use MCP servers in Claude Code.

Add to Claude config:


```
{
  "mcpServers": {
    "databox": {
      "type": "http",
      "url": "https://mcp.databox.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_ACCESS_TOKEN"
      }
    }
  }
}
```

ChatGPT
Availability
MCP apps via ChatGPT developer mode are in **beta** and require an eligible ChatGPT plan — availability and UI may change. On Business and Enterprise plans, how you connect Databox depends on your role:

- **Admins** can enable developer mode and connect Databox directly as a custom connector.
- **Non-admins** need the workspace admin to first add Databox under **Apps** in account settings. Once added, all users can connect without needing developer mode.


First, enable [developer mode](https://developers.openai.com/api/docs/guides/developer-mode/) by following the official OpenAI documentation. Once enabled, click **Create app** and use the following configuration:

* Name: Databox
* URL: `https://mcp.databox.com/mcp`
* Authentication: OAuth 2.0 (complete the authorization flow when prompted)


Gemini
Gemini does not currently support MCP directly. To use Gemini models with Databox MCP, you need to run [Goose](https://block.github.io/goose/docs/category/getting-started/) locally as an MCP client.

1. Create a Gemini API key by clicking **Create API key** in the Gemini console.
2. Name the API key by entering a descriptive name in the text field.
3. Create a new project for the API key by clicking **Create project**.
4. Enter a project name and click **Create project** to finalize it.
5. Copy the API key by clicking the **copy icon**.
6. Open the Goose app and **paste your Gemini API key**, then confirm.
7. Select a Gemini model and click **Select model** to continue.
8. Open **Extensions** in Goose and click **Add custom extension**.
9. Enter the extension details:
  - **Extension name:** Databox
  - **Type:** HTTP
  - **Endpoint:** https://mcp.databox.com/mcp
10. Click **Add Extension** to register Databox MCP with Goose and Gemini.
11. Start a new chat and click the **dumbbell icon**.
12. **Enable Databox**, which opens a browser window for authentication.
13. **Log in to Databox** to authorize the connection.


n8n
Availability
You'll need access to an n8n instance — either cloud or self-hosted — to use Databox MCP for workflow automation.

There are two ways to use Databox MCP with n8n:

**Option 1: Using MCP Client Tool Node (Recommended for AI Agents)**

1. In your n8n workflow, add the **MCP Client Tool** node
2. Configure the node:
  * **SSE Endpoint:** `https://mcp.databox.com/mcp`
  * **Authentication:** Select "Bearer Token"
  * **Access Token:** Enter your Databox OAuth token
3. Connect the MCP Client Tool to your AI Agent node
4. The AI agent can now query and ingest Databox data within workflows


**Option 2: Direct HTTP Integration (Recommended for Data Sync)**

1. In your n8n workflow, add an **HTTP Request** node
2. Configure for Databox MCP operations:
  * **Method:** POST
  * **URL:** `https://mcp.databox.com/mcp`
  * **Authentication:** Bearer Token with your Databox OAuth token
  * **Body:** JSON-RPC formatted requests (see [Databox MCP Tools](/docs/mcp/tools))
3. Use this method for scheduled data ingestion, automated reporting, or multi-step workflows


Known issues
If you get a 404 error while setting up credentials, use `https://mcp.databox.com` instead of `https://mcp.databox.com/mcp` — n8n appends `/mcp` to the URL automatically, which causes a duplicate path.

Cursor
Availability
A Cursor paid subscription is required to use MCP servers.

p

  Use the shortcut button:
  
a
img
Or add it manually:

1. Open Cursor Settings at `Cursor > Settings… > Cursor Settings`
2. Navigate to `Tools & Integrations > New MCP Server`
3. Add this configuration to your `mcp.json`:



```
{
  "mcpServers": {
    "Databox": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.databox.com/mcp",
        "--allow-http"
      ]
    }
  }
}
```

Manus
1. Open Manus and go to `Settings > Integrations > Custom MCP Servers`
2. Click **Add Server**
3. Enter the server details:
  * **Server name:** Databox
  * **URL:** `https://mcp.databox.com/mcp`
  * **Authentication:** OAuth 2.0 (complete the authorization flow when prompted)
4. Click **Add Server** to confirm - Manus will verify the connection and make Databox tools available in your prompts
5. Start a new task and use Databox data directly in your Manus workflows


Antigravity
1. Add this configuration to your Antigravity MCP settings:



```
{
  "mcpServers": {
    "databox": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.databox.com/mcp"
      ],
      "env": {}
    }
  }
}
```

1. A browser window will open for OAuth 2.0 authorization - log in to Databox to complete the connection
2. Start querying your Databox data within Antigravity


Other MCP clients
For MCP-compatible clients:

1. Configure your client to connect to `https://mcp.databox.com/mcp`.
2. Authenticate using OAuth 2.0 through the login screen