JetBrains IDEs Setup

Overview

JetBrains IDEs — IntelliJ IDEA, PyCharm, WebStorm, GoLand, and the rest of the family — support MCP through AI Assistant (2025.2 and later). Connect Tempreon once and AI Assistant loads your Core Imprint, searches your Knowledge Vault, and remembers what it learns, across every tool you use. The same server also works with Junie, JetBrains' autonomous coding agent.

Quick path: Settings | Tools | AI Assistant | Model Context Protocol (MCP) → Add → paste the JSON config → approve in the browser.

Prerequisites

• A JetBrains IDE on 2025.2 or later with the AI Assistant plugin enabled
• A JetBrains AI tier — as of July 2026 there's an AI Free tier with a small cloud quota, paid AI Pro and Ultimate tiers, and AI Pro comes bundled with the All Products Pack
• A Tempreon account with at least one available Bridge slot
• The Tempreon server URL (also shown in your Bridges dashboard)

Step-by-Step Setup

1. Open the MCP settings

1. Open Settings (Cmd+, / Ctrl+Alt+S)
2. Go to Tools | AI Assistant | Model Context Protocol (MCP)
3. Click Add

You can add the server at the global level (all projects) or project level. If you already use Tempreon in Claude Desktop, the Import from Claude button can pull that config in directly.

2. Paste the configuration

Choose the JSON option and paste:

{
  "mcpServers": {
    "tempreon": {
      "url": "https://api.tempreon.com/functions/v1/tempreon-mcp/mcp"
    }
  }
}

3. Authorize the connection

Current 2026 builds run the OAuth flow automatically (it's labeled beta): a browser tab opens to Tempreon's consent screen — sign in to your Tempreon account and approve. If the IDE shows a dialog asking for manual client registration details, choose the automatic option first; Tempreon supports dynamic client registration, so no client ID or secret is needed.

On older 2025.x builds without the OAuth flow, use the proxy fallback instead:

{
  "mcpServers": {
    "tempreon": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://api.tempreon.com/functions/v1/tempreon-mcp/mcp"]
    }
  }
}

4. Confirm the tools are active

The server should show a connected status in the MCP settings list. In an AI Assistant chat, ask "What Tempreon tools do you have access to?" If it answers with a list, the Bridge is live.

Junie

Junie reads its own config file — .junie/mcp/mcp.json in the project root, or ~/.junie/mcp/mcp.json for user-level:

{
  "mcpServers": {
    "tempreon": {
      "type": "streamable-http",
      "url": "https://api.tempreon.com/functions/v1/tempreon-mcp/mcp"
    }
  }
}

The "type": "streamable-http" field is required in Junie's config.

Troubleshooting

Connection fails immediately. The URL must end in /mcp with no trailing slash: https://api.tempreon.com/functions/v1/tempreon-mcp/mcp.

Don't see the MCP settings page? Confirm the IDE is on 2025.2+ and the AI Assistant plugin is installed and enabled. AI Assistant also requires an active JetBrains AI tier — AI Free is enough to get started.

A dialog asks for a client ID and secret. Pick the automatic registration option — Tempreon registers the client for you. Manual registration is only a fallback for servers that don't support it.

OAuth flow never appears on an older build. 2025.x builds may lack the browser OAuth flow entirely. Use the mcp-remote fallback config from step 3, which handles the OAuth handshake in your terminal's browser session.

Also connect: VS Code · Zed · Windsurf

Try saying...

• "Start my session." — triggers session_start to load your Core Imprint
• "Search my knowledge base for our testing conventions." — exercises knowledge retrieval end-to-end
• "Remember that we target Java 21 across all services." — stores a decision for every future session