List, load, or unload models on a local LLM server to switch active models in LM Studio without opening the GUI.
Apache 2.0
650,596 tools. Updated 2026-10-14 14:58
"How to install LM Studio tool" matching MCP tools:
- List free-seat status and requestable local runtimes such as Ollama, llama.cpp, LM Studio, OpenAI-compatible servers, and vLLM.MIT
- Unload a specified model from the LM Studio server to free memory, requiring explicit user confirmation and reporting the freed bytes.MITDestructive
- Retrieve the current status of LM Studio, including available models, loaded model, and context configuration. Use this tool to diagnose errors or unexpected slowness.MIT
- Copy approved test results between profiles sharing the same LM Studio endpoint, avoiding redundant runs. Different endpoints are refused; later finalize aggregates the copied results without re-running.MIT
- Determine the runtime environment's container, OS, package manager, and sudo availability to decide how to install tools.MIT
Matching MCP Servers
- AlicenseAqualityDmaintenanceEnables AI assistants to manage LM Studio models, including listing, loading, and unloading models through the LM Studio API.626 npm5ISC
- AlicenseAqualityDmaintenanceEnables listing, loading, unloading, and configuring models in LM Studio via MCP tools, with support for TTL and draft model settings.56MIT
Matching MCP Connectors
Connect to the MCP Studio SDK MCP server. This server is connected to two sources: the MCP Studio SDK documentation and the GitHub sample application repos. These resources are great for individuals looking to embed MCP Studio SDK into their web applications, and need an easy way to connect to an MCP server that has access reliable resources for AI-assisted engineering workflows.
LM hash 16-hex shape, value discarded
- Learn how to drive Astral MCP correctly: install command, first calls, full tool list, agent rules for birthplace, timezone, birth_time caveats, and troubleshooting.MIT
- Discover models available from localhost runtimes like Ollama, LM Studio, and LocalAI.MIT
- Lists models available on the active LM Studio endpoint. Returns compact details by default; add verbose for complete model objects.MIT
- Retrieve a list of all downloaded LLM models from LM Studio to see which models are available for use.ISC
- Lists all LLM models currently loaded in LM Studio, showing which models are active and ready for inference.ISC
- Run tasks on a local LLM via Ollama or LM Studio to keep data private and avoid cloud reliance. Use for sensitive information or simple, repeated prompts.MIT
- Load a specified model into the active LM Studio endpoint, accepting optional parameters like context length or flash attention.MIT
- Verify LM Studio server status and response availability to enable function discovery and system diagnostics for Claude Desktop integration.Apache 2.0
- Verify that the LM Studio API is reachable and responding to ensure proper connectivity.ISC
- Lists all available LM Studio models and shows whether each is loaded or not.MIT
- Scan local network ports to detect running AI servers (Ollama, LM Studio, vLLM, etc.), list their active models, and auto-sync them into your provider vault.MIT
- Assess LM Studio health for a profile: verify endpoint reachability with auto-restart recovery, check free disk space for downloads, detect stuck-loaded models, then return overall status.MIT
- Identify which models are currently loaded into GPU or CPU on the active LM Studio profile to confirm available resources before delegating tasks.MIT
- Retrieve detailed information about a loaded model in LM Studio using its instance identifier.ISC
- Return a read-only summary of local LM Studio health, including API status and model counts, to diagnose setup issues.MIT