MCP server connecting Claude Code to LM Studio, delegating token-expensive tasks to a local model while keeping the cloud model in control. It reduces cloud context usage by reading files locally and returning only the processed results.
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find.
Install from
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
process.env. You'll be asked to provide them before it can run.LMSTUDIO_URLLMS_CLI— ~/.lmstudio/bin/lms[.exe] Path to the LM Studio CLILOCAL_ALLOWED_ROOTS— (none) Roots allowed for reading, separated by ;LOCAL_AUTOLOAD— 1 0 disables automatic reloadingLOCAL_CONTEXT— 32768 Context required at startupLOCAL_MODEL_CODE— Adjust to your hardware via / LOCAL_MODEL_LIGHT.LOCAL_MODEL_LIGHT— Adjust to your hardware via LOCAL_MODEL_CODE / .LOCAL_TIMEOUT_MS— 600000 Max call duration (10 min)LOCAL_TTL_SECONDS— 28800 Unload the model after 8 h of inactivity[](https://m8ven.ai/mcp/drangoht-local-llm-mcp-1dcx8i)