How do I add an MCP server to LM Studio?

Edit ~/.lmstudio/mcp.json (Program tab → Install → Edit mcp.json in the app) and add your server under mcpServers: { "mcpServers": { "local-mcp": { "command": "npx", "args": ["-y","local-mcp@latest"] } } }. LM Studio loads it automatically when you save.

Does using MCP tools in LM Studio send data to the cloud?

No. LM Studio runs the model locally and LMCP runs the tools locally on your Mac. The model, the tools, and your data all stay on-device. LMCP is free and needs no API keys.

What can LM Studio do with LMCP?

LMCP gives LM Studio 230+ local Mac tools: read and send Mail, manage Calendar, read iMessages, search Notes and Reminders, browse Files, read Microsoft Teams, OneDrive and more — all on your Mac.

How to Add MCP Tools to LM Studio on Mac (Local, Free)

A fully local AI stack

LM Studio runs open LLMs locally on your Mac. LMCP is a local MCP server that gives an AI access to your real Mac apps. Together, both the model and the tools run on your machine — no cloud, no API keys, nothing uploaded. Ask LM Studio to read your email, check your calendar, or search your Messages, and it acts on the real apps.

Step 1: Install LMCP

Download and open the free installer (macOS 12+, Apple Silicon & Intel):

curl -fsSL 'https://local-mcp.com/install?ref=guide-lm-studio-mac' | bash

Or download the app. LMCP starts in your menu bar.

Step 2: Add LMCP to LM Studio

LM Studio loads MCP servers from ~/.lmstudio/mcp.json. Open it inside the app: in the right sidebar switch to the Program tab, click Install → Edit mcp.json, and add LMCP under mcpServers:

{
  "mcpServers": {
    "local-mcp": {
      "command": "npx",
      "args": ["-y", "local-mcp@latest"]
    }
  }
}

Save the file — LM Studio loads the server automatically. (LM Studio uses npx to launch it, so you need Node.js installed.)

Step 3: Enable and try it

Make sure the local-mcp server is toggled on, load a tool-capable model, start a chat, and ask:

List my email accounts

LM Studio calls the tool on your Mac and returns the result — a fully local AI with access to your real apps.

Troubleshooting

The server won’t start — make sure the Local MCP app is running (menu-bar icon) and that npx is on your PATH (install Node.js).

The model doesn’t call tools — pick a model that supports tool/function calling; not every local model does.