portertech/lm-studio-mcp-server repository overview

⁠LM Studio MCP Server

An MCP (Model Context Protocol) server that provides AI assistants with control over LM Studio models. Enables remote model management including listing, loading, and unloading models through the LM Studio API.

⁠Features

• Health Check - Verify connectivity to LM Studio
• List Models - View downloaded and loaded models
• Load/Unload Models - Manage models in memory with configurable parameters
• Get Model Info - Retrieve detailed information about loaded models

⁠Quick Start

# Pull the image
docker pull portertech/lm-studio-mcp-server:latest

# Run (connects to LM Studio on host machine)
docker run -i --rm portertech/lm-studio-mcp-server:latest

# Run with custom LM Studio host
docker run -i --rm \
  -e LMSTUDIO_HOST=192.168.1.100 \
  -e LMSTUDIO_PORT=1234 \
  portertech/lm-studio-mcp-server:latest

⁠Environment Variables

⁠Claude Desktop Configuration

{
  "mcpServers": {
    "lmstudio": {
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "LMSTUDIO_HOST=host.docker.internal",
        "-e", "LMSTUDIO_PORT=1234",
        "portertech/lm-studio-mcp-server:latest"
      ]
    }
  }
}

⁠Available Tools

⁠Prerequisites

• LM Studio running with the local server enabled

⁠Links

• Source Code: GitHub⁠
• npm Package: @portertech/lm-studio-mcp-server⁠

⁠License

ISC