Jervi
Back to all articles
Lm studioantigravityMCP

Connect LM Studio to Antigravity IDE Using MCP

I wanted to use my local LM Studio models inside Antigravity IDE, so I connected them through MCP.

Requirements

  • Antigravity IDE
  • LM Studio
  • A loaded model (Gemma, Qwen, Llama, etc.)
  • uv installed, if not then do install it with following brew install uv

Start the LM Studio server:

text
Developer → Local Server

Default endpoint:

text
http://127.0.0.1:1234/v1

Add this to your Antigravity MCP config:

json
{
  "mcpServers": {
    "lmstudio-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "git+https://github.com/infinitimeless/LMStudio-MCP"
      ],
      "env": {
        "LMSTUDIO_HOST": "127.0.0.1",
        "LMSTUDIO_PORT": "1234"
      }
    }
  }
}

Important: Use git+https://, otherwise you'll get:

text
Direct URL references a Git repository,
but is missing the git+ prefix

Reload Antigravity.

Method 2: Clone Locally

bash
git clone https://github.com/infinitimeless/LMStudio-MCP.git
cd LMStudio-MCP

python3 -m venv venv
source venv/bin/activate

pip install requests "mcp[cli]" openai

MCP config:

json
{
  "mcpServers": {
    "lmstudio-mcp": {
      "type": "stdio",
      "command": "/bin/bash",
      "args": [
        "-c",
        "cd ~/LMStudio-MCP && source venv/bin/activate && python lmstudio_bridge.py"
      ]
    }
  }
}

Reload Antigravity.

Test

Ask:

text
Use lmstudio-mcp health_check

Or:

text
Use lmstudio-mcp to explain this file

How It Works

text
Antigravity
    ↓
MCP Bridge
    ↓
LM Studio
    ↓
Local Model

This does not replace Antigravity's main model.

It gives Antigravity access to your local model as an MCP tool, allowing you to use Gemma, Qwen, Llama, DeepSeek, or any model loaded in LM Studio.

Repository:

https://github.com/infinitimeless/LMStudio-MCP