# Connect JetBrains AI Assistant / Junie to aicharged.io

> JetBrains IDEs (AI Assistant, Junie): paste a JSON server definition in Settings → Tools → AI Assistant → MCP. AI Assistant has no OAuth — use the API key.

## At a glance

| Kind | Sign-in | Platforms | Status | Verified |
|---|---|---|---|---|
| Editors & IDEs | API key (Bearer) | macOS, Linux, Windows | works today | 2026-10-22 |

- MCP: `https://aicharged.io/api/v1/mcp`
- Docs: https://www.jetbrains.com/help/ai-assistant/mcp.html

## Recipe

1. Open Settings → Tools → AI Assistant → Model Context Protocol (MCP) and click Add.
2. Choose HTTP and paste the JSON below.
3. Click OK, then Apply to connect.

JSON to paste into the dialog:

```json
{
  "mcpServers": {
    "aicharged": {
      "url": "https://aicharged.io/api/v1/mcp",
      "headers": {
        "Authorization": "Bearer <API_KEY>"
      }
    }
  }
}
```

Unverified: the JetBrains docs show only url — the headers field comes from the TeamCity docs. AI Assistant cannot sign in with OAuth; Junie can.

[Client documentation](https://www.jetbrains.com/help/ai-assistant/mcp.html)

## Authentication

- Send `Authorization: Bearer <API_KEY>` with every request. Create a key at https://aicharged.io/admin/account/api-keys.
- OAuth 2.1 (PKCE S256) is available for clients that cannot send a static key (ChatGPT).
- Without a key the endpoint answers 401 with a WWW-Authenticate header that points to https://aicharged.io/.well-known/oauth-protected-resource.

All 51 clients: https://aicharged.io/connect.md

HTML version: https://aicharged.io/connect/jetbrains
