MCP Server Setup

Supercharge Your IDE with AI-Powered SDK Code Generation

The Luminary Cloud MCP (Model Context Protocol) Server transforms your coding experience by connecting AI assistants in popular IDEs like Visual Studio Code, Cursor, Windsurf and agentic coding tools like Claude Code, Gemini CLI directly to the Luminary Cloud platform. This integration gives AI agents insider knowledge of the Luminary Cloud Platform and SDK, dramatically improving their ability to write, refactor, and debug SDK scripts automatically.

Important

Key Benefit: Build Luminary Cloud scripts quickly using AI assistants that understand Luminary and generate SDK code on demand.

The Luminary Cloud MCP server provides AI coding assistants with the ability to:

  • Generate SDK code automatically with proper syntax and latest best practices

  • Browse and manage your Luminary Cloud projects programmatically

  • Access simulation results and data for analysis and post-processing

  • Query geometry and mesh information for workflow automation

  • Retrieve simulation setup configurations and modify them as needed

  • Search documentation and examples for context-aware code suggestions

MCP Server URL

The Luminary Cloud MCP server is hosted at:

https://app.luminarycloud.com/mcp

Use this URL for manual configuration or when setting up the MCP server in clients that don’t support one-click installation.

Quick Connection Guide

Visual Studio Code

Option 1: One-Click Install (Recommended):

  1. Click this install link: Install to VSCode (Note: This link only works if you have VSCode installed)

  2. Click “Install” when VSCode shows the installation window

  3. Open Copilot (icon near search bar) and select “Agent” mode

  4. Ask about Luminary Cloud - authentication will start automatically

Option 2: Manual Configuration:

  1. Open Command Palette and run MCP: Add Server

  2. Select “HTTP” as your server type

  3. Enter server URL: https://app.luminarycloud.com/mcp

  4. Add name: Luminary Cloud

  5. Choose your installation scope (Global/Remote/Workspace)

  6. Verify the configuration in your mcp.json file:

{
  "servers": {
    "Luminary Cloud": {
      "url": "https://app.luminarycloud.com/mcp",
      "type": "http"
    }
  }
}

Cursor

Option 1: One-Click Install (Recommended):

  1. Click this install link: Install to Cursor (Note: This link only works if you have Cursor installed)

  2. Complete authentication by clicking “Needs login”

  3. Verify the green dot shows “5 tools enabled”

Option 2: Manual Configuration:

  1. Open Cursor Settings: Cursor → Settings → Cursor Settings (or click gear icon)

  2. Select “Tools & Integrations” from the left panel

  3. Click “New MCP Server” at the bottom

  4. Add this configuration to the JSON file that opens:

{
  "mcpServers": {
    "Luminary Cloud": {
      "url": "https://app.luminarycloud.com/mcp"
    }
  }
}

  1. Save and close the JSON file

  2. Return to “Tools & Integrations” to see the server listed

  3. Complete authentication by clicking “Needs login”

Using Your IDE’s AI Agent

Once connected, the example questions you can ask your AI agent are:

  • “List my Luminary Cloud projects”

  • “Create a new simulation using the SDK”

  • “Generate code to upload and mesh this geometry file”

  • “Show me how to post-process simulation results”

Pro Tip: Remind your assistant to use MCP tools by adding: “Use the Luminary Cloud MCP tools to write accurate SDK code” in your prompt or context.

Complete Setup Guide

For detailed installation steps, manual configuration options, troubleshooting, and advanced features, visit:

Configuring MCP for Luminary Cloud

The comprehensive guide covers:

  • Manual configuration for both IDEs

  • Authentication troubleshooting

  • Advanced usage patterns

  • Custom instructions setup