# Connect the MultitaskAI MCP server to LM Studio

LM Studio reads MCP servers from mcp.json, opened from the Program tab. Add MultitaskAI with its URL and your API key in the headers.

## Endpoint

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

## Steps

1. Create an API key in your MultitaskAI account.
2. Open the Program tab in the right-hand sidebar.
3. Click Install, then Edit mcp.json.
4. Add the server below inside mcpServers, with your key in place of YOUR_API_KEY, and save the file.
5. Start a new chat with a model that supports tool use and check that the MultitaskAI tools are available.

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

## Authentication

LM Studio 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

- Remote MCP servers need LM Studio 0.3.17 or later.
- If mcp.json already has servers, paste only the multitaskai entry inside the existing mcpServers block.
- Use a model that supports tool use.

## Official documentation

The [Element Labs MCP documentation](https://lmstudio.ai/docs/app/mcp) covers LM Studio's own settings in detail. See the [overview](/docs.md) for the endpoint and authentication, and [pricing](/pricing/) for the daily free requests.
