Agent Lore

Why server mode matters

Server mode turns LM Studio into a drop-in replacement for the OpenAI API. Any tool that accepts a custom base URL can talk to your local model.

Start the server

1. Go to the Developer tab
2. Click Start Server
3. Note the URL, usually

http://localhost:1234/v1

Test with curl

curl http://localhost:1234/v1/chat/completions   -H "Content-Type: application/json"   -d '{
    "model": "local-model",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Connect Claude Code

claude --api-url http://localhost:1234/v1

Connect Cursor

Open Settings → Models → OpenAI API. Set the base URL to:

http://localhost:1234/v1

Use any non-empty string for the API key.

Keep the server running

Server mode only works while LM Studio is open. For headless automation, prefer Ollama.