diff --git a/Quick-Start.md b/Quick-Start.md
new file mode 100644
index 0000000..4f7c10c
--- /dev/null
+++ b/Quick-Start.md
@@ -0,0 +1,53 @@
+# ⚡ Quick Start
+
+Get the Strava MCP Server running in under 2 minutes — no repository clone required.
+
+## Step 1: Authenticate
+
+Run the interactive setup wizard. It will open a browser window, guide you through creating a Strava API app, and save your credentials automatically.
+
+```bash
+uvx --from strava-mcp-server-hnrx auth
+```
+
+The wizard will:
+1. Open `http://localhost:8765` in your browser
+2. Show you how to create a Strava API application
+3. Accept your **Client ID** and **Client Secret**
+4. Redirect you to Strava for OAuth authorization
+5. Save all credentials to `~/.config/strava-mcp-server/config.env`
+
+> ℹ️ You only need to run `auth` once. The credentials are stored permanently in your user config directory.
+
+## Step 2: Run the Server
+
+```bash
+uvx --from strava-mcp-server-hnrx server
+```
+
+The server starts in **STDIO mode** by default — perfect for use with Claude Desktop, Cursor, or the MCP Inspector.
+
+For HTTP mode (e.g. for Docker or OpenWebUI):
+
+```bash
+MCP_TRANSPORT=http uvx --from strava-mcp-server-hnrx server
+```
+
+## Step 3: Connect your AI Client
+
+→ See [MCP Clients](MCP-Clients) for Claude Desktop, OpenWebUI, and other client configurations.
+
+---
+
+## What happens next?
+
+Once connected, your AI assistant can:
+- Analyze your training load and weekly volume
+- Compare activities across seasons
+- Identify your best segments and performances
+- Track gear mileage and recommend maintenance
+- Generate structured training reports
+
+---
+
+*Back to [Home](Home)*