Qwen Code Setup
Connect Tempreon to Qwen Code, Alibaba's open-source coding CLI, using the httpUrl MCP config and built-in browser OAuth.
Overview
Qwen Code is Alibaba's open-source coding CLI, built on the Gemini CLI lineage — so if you've configured MCP there, this will feel familiar. It supports remote MCP servers with automatic OAuth discovery and dynamic client registration, which is exactly Tempreon's shape.
Once connected, your AI in Qwen Code loads your Core Imprint, searches your Knowledge Vault, and remembers what it learns — the same intelligence layer that follows you across every tool you connect.
Quick path: add Tempreon to ~/.qwen/settings.json using httpUrl → run /mcp auth tempreon → approve in the browser → done.
Availability note: the old Qwen OAuth free model tier was discontinued on April 15, 2026. The CLI itself remains free and open source, but you now bring your own model access — via the Alibaba Cloud coding plan, ModelScope's free tier, OpenRouter, or any compatible endpoint. Whichever model route you pick, the Tempreon setup below is the same.
Prerequisites
- Qwen Code installed, with a working model route configured (see the availability note above)
- A Tempreon account with at least one available Bridge slot
- A working default browser for the authorization step
Step-by-Step Setup
1. Add Tempreon to settings.json
Edit ~/.qwen/settings.json (or .qwen/settings.json in a project for project-only scope) and add:
{
"mcpServers": {
"tempreon": {
"httpUrl": "https://api.tempreon.com/functions/v1/tempreon-mcp/mcp"
}
}
}
The URL is also shown in your Bridges dashboard.
The key is httpUrl, not url. In Qwen Code, httpUrl means Streamable HTTP — the transport Tempreon uses. A plain url key means the legacy SSE transport and won't connect correctly.
2. Authorize the connection
Start Qwen Code and run:
/mcp auth tempreon
Qwen Code discovers Tempreon's OAuth endpoint and registers itself automatically (dynamic client registration is the default) — a browser tab opens with the Tempreon consent screen. Sign in if prompted and approve. Tokens are stored in ~/.qwen/mcp-oauth-tokens.json and refreshed automatically.
3. Verify the connection
Run /mcp inside Qwen Code to see the server status, or just ask:
"What Tempreon tools do you have access to?"
If it answers with a list of tools, the Bridge is live.
Troubleshooting
Connection fails immediately. Check the URL ends in /mcp — no trailing slash. The full URL is https://api.tempreon.com/functions/v1/tempreon-mcp/mcp.
Server connects but behaves oddly or times out. The most common cause is using url instead of httpUrl — url selects legacy SSE. Switch the key to httpUrl and restart.
Browser doesn't open for authorization. Some terminal environments print the authorization link instead — look for an https:// URL in the output and open it manually. Also check pop-up blockers and your default browser setting.
"Unauthorized" or stale-token errors. Delete the Tempreon entry from ~/.qwen/mcp-oauth-tokens.json and run /mcp auth tempreon again for fresh tokens.
Model errors that mention quotas or endpoints. That's your model route, not the Tempreon Bridge — the two are independent. Check your coding plan, ModelScope, or OpenRouter configuration separately.
Also connect: OpenCode · Kimi · Claude Code
Try saying...
- "Start my session." — triggers
session_startto load your Core Imprint - "Remember: the data pipeline runs UTC, never local time." — stores knowledge your AI will carry into future sessions
- "What do you know about me from Tempreon?" — a quick end-to-end test