# Connect the MultitaskAI MCP server to Tabnine

The Tabnine Agent reads MCP servers from mcp_servers.json. Add MultitaskAI with its URL and your API key in requestInit headers.

## Endpoint

```text
https://mcp.multitaskai.com
```

## Steps

1. Create an API key in your MultitaskAI account.
2. Open ~/.tabnine/mcp_servers.json for every project, or .tabnine/mcp_servers.json in one project.
3. Add the server below, with your key in place of YOUR_API_KEY, and save the file.
4. Open a project folder in your IDE and check that MultitaskAI appears in Tabnine's MCP list.

```json
{
  "mcpServers": {
    "multitaskai": {
      "url": "https://mcp.multitaskai.com",
      "requestInit": {
        "headers": {
          "Authorization": "Bearer YOUR_API_KEY"
        }
      }
    }
  }
}
```

## Authentication

Tabnine sends your MultitaskAI API key in the Authorization header. Create a key in your account and use it in place of YOUR_API_KEY. Keep the key out of files you share or commit.

```text
Authorization: Bearer YOUR_API_KEY
```

## Good to know

- Headers go inside requestInit.
- Tabnine reads neither file unless a workspace folder is open.
- A url means Streamable HTTP by default, so no transport field is needed.

## Official documentation

The [Tabnine MCP documentation](https://docs.tabnine.com/main/getting-started/tabnine-agent/mcp-intro-and-setup) covers Tabnine's own settings in detail. See the [overview](/docs.md) for the endpoint and authentication, and [pricing](/pricing/) for the daily free requests.
