FrootAI Setup Guide

Two tools, one setup page. Get FrootAI's MCP Server (for your AI agent) and VS Code Extension (for you) up and running in minutes.

Part 1: MCP Server Setup

Add AI architecture knowledge to any agent. Works with Claude Desktop, VS Code Copilot, Cursor, Windsurf, Azure AI Foundry.

Prerequisites

Node.js 18+ — Download here
Git — Download here
An MCP client — VS Code, Claude Desktop, Cursor, Windsurf, or Azure AI Foundry

Step 1: Install

Option A: npm (Recommended — zero clone)

Terminal

# Run directly (no install needed)
npx frootai-mcp@latest

# OR install globally
npm install -g frootai-mcp@latest
frootai-mcp

Option B: Docker (no Node.js needed)

Terminal

docker run -i ghcr.io/frootai/frootai-mcp

Option C: From GitHub

Terminal

git clone https://github.com/frootai/frootai.git
cd frootai/mcp-server
npm install

Step 2: Connect to Your Client

Claude Desktop / Cursor / Windsurf

claude_desktop_config.json

{
  "mcpServers": {
    "frootai": {
      "command": "npx",
      "args": ["frootai-mcp"]
    }
  }
}

Restart Claude Desktop. FrootAI appears in your tools list.

Part 2: VS Code Extension

Browse plays, init DevKit, search terms — right from your editor.

Terminal

code --install-extension pavleenbali.frootai

Or: Ctrl+Shift+X → search "FrootAI" → Install

Solution Plays (20)MCP Tools (22)Knowledge Hub (18)AI Glossary (200+)

Part 3: CLI

Ships with the MCP Server package. No extra install.

Terminal

npx frootai init        # Interactive project scaffolding
npx frootai search RAG  # Search knowledge base
npx frootai cost 01 dev # Estimate Azure costs
npx frootai doctor      # Check environment

Part 4: Docker

Zero Node.js required. Multi-arch (amd64 + arm64).

Terminal

docker run -i --rm ghcr.io/frootai/frootai-mcp:latest

MCP Server Details Extension Details Ecosystem Back to FrootAI