You can configure server settings, such as the port number, whether to allow other API clients to access the server and MCP features.

Configure LM Studio API Server settings

Server Port : Integer

Port number on which the LM Studio API server listens for incoming connections.

Serve on Local Network : Switch

Allow other devices on the same local network to access the API server. Learn more in the Serve on Local Network section.

Allow Per Request Remote MCPs : Switch

Enable sending requests to remote MCP (Model Control Protocol) servers on a per-request basis.

Enable CORS : Switch

Enable Cross-Origin Resource Sharing (CORS) to allow applications from different origins to access the API.

Just in Time Model Loading : Switch

Load models dynamically at request time to save memory.

Auto Unload Unused JIT Models : Switch

Automatically unload JIT-loaded models from memory when they are no longer in use.

Only Keep Last JIT Loaded Model : Switch

Keep only the most recently used JIT-loaded model in memory to minimize RAM usag

Server Settings