# Connect the MultitaskAI MCP server to Copilot for JetBrains

GitHub Copilot for JetBrains reads MCP servers from mcp.json in Agent mode. 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. Click the GitHub Copilot icon in the lower right corner, select Open Chat and make sure you are in Agent mode.
3. Click the tools icon (Configure your MCP server) at the bottom of the chat, then Add MCP Tools to open mcp.json.
4. Add the server below, with your key in place of YOUR_API_KEY, and save the file.
5. Click the tools icon again and check that the MultitaskAI tools are listed.

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

## Authentication

Copilot for JetBrains 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

- Works in IntelliJ IDEA, PyCharm, WebStorm, PhpStorm, GoLand, Rider and the other supported JetBrains IDEs.
- The format uses a top-level servers key and puts headers inside requestInit, unlike VS Code.
- Copilot Business and Enterprise users need the MCP servers in Copilot policy enabled by their organisation.

## Official documentation

The [GitHub MCP documentation](https://docs.github.com/en/copilot/how-tos/provide-context/use-mcp/extend-copilot-chat-with-mcp?tool=jetbrains) covers Copilot for JetBrains's own settings in detail. See the [overview](/docs.md) for the endpoint and authentication, and [pricing](/pricing/) for the daily free requests.
