# Connect the MultitaskAI MCP server to Gumloop

Gumloop agents can use custom MCP servers as connectors. Add MultitaskAI with its URL and your API key as the access token.

## Endpoint

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

## Steps

1. Create an API key in your MultitaskAI account.
2. Select Customize in the left sidebar, open the Connectors tab and click the + button, labeled Add Custom MCP on wider screens.
3. Enter the endpoint URL in MCP Server URL and click Connect.
4. Open the Authentication dropdown, select API Key / Credentials and paste your key as the Access Token / API Key.
5. Open your agent, click + Add in the Connectors section, add MultitaskAI, click Save and ask the agent to list its available tools.

```text
MCP Server URL: https://mcp.multitaskai.com
Authentication: API Key / Credentials
Access Token / API Key: YOUR_API_KEY
```

## Authentication

Gumloop 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

- Gumloop sends the access token as an Authorization Bearer header, so paste the key without the Bearer prefix.
- Do not put the key in the Additional Header field: Anthropic models in Gumloop do not forward custom headers, while the token works with every model.
- Credentials can be stored at the personal or team level.
- Gumloop does not ask for approval before tool calls.

## Official documentation

The [Gumloop MCP documentation](https://docs.gumloop.com/nodes/mcp/custom_mcp_servers) covers Gumloop's own settings in detail. See the [overview](/docs.md) for the endpoint and authentication, and [pricing](/pricing/) for the daily free requests.
