$ loading_
Manage LM Studio models via MCP for loading, unloading, and configuration.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "LM Studio MCP Server" yet — see the docs or source repo.
Use the LM Studio MCP Server to list all available models, including model name, loaded status, and key configuration details.
A list of available models with each model’s status and basic configuration summary.
Use the LM Studio MCP Server to load a specified model, set TTL to 30 minutes, and enable draft model settings.
A result confirming the model was loaded and the TTL and draft model settings were applied.
Use the LM Studio MCP Server to unload the currently idle model that is no longer needed, and tell me whether the operation succeeded.
A result indicating whether the target model was successfully unloaded and released.
Let AI assistants list, load, and unload local LM Studio models.
Offload non-critical LLM tasks to your own model and save premium quota.
Offload non-critical LLM tasks to your own model to save premium quota.
Manage local model runtimes with unified discovery, checks, lifecycle control, and inference.
Build, debug, and manage software tasks with natural language across LLMs.
Delegate low-risk tasks to a cheaper model with main-agent review.