Watch

Olivier Chafik cce8d5c7a3

docs: add MCP client configuration to example READMEs

Add stdio transport configuration snippets near the top of each example
README to help users quickly set up the servers in their MCP clients.

- Node.js examples use npx with the published npm packages
- Python qr-server uses uv with local path
- Removed Claude Desktop-specific references from qr-server

2026-01-16 14:00:57 +00:00

3.1 KiB

Raw Blame History

Example: SaaS Scenario Modeler

A React-based demo MCP App that lets users adjust SaaS business parameters and see real-time 12-month projections of revenue, costs, and profitability with comparison against pre-built scenario templates.

MCP Client Configuration

Add to your MCP client configuration (stdio transport):

{
  "mcpServers": {
    "scenario-modeler": {
      "command": "npx",
      "args": [
        "-y",
        "--silent",
        "--registry=https://registry.npmjs.org/",
        "@modelcontextprotocol/server-scenario-modeler",
        "--stdio"
      ]
    }
  }
}

Features

Interactive Parameters: 5 sliders for Starting MRR, Growth Rate, Churn Rate, Gross Margin, and Fixed Costs
12-Month Projections: Line chart showing MRR, Gross Profit, and Net Profit over time
Scenario Templates: 5 pre-built business strategies (Bootstrapped, VC Rocketship, Cash Cow, Turnaround, Efficient Growth)
Template Comparison: Overlay dashed lines to compare your scenario against any template
Summary Metrics: Key metrics including Ending MRR, Total Revenue, Total Profit, and break-even month
Theme Support: Adapts to light/dark mode preferences

Running

Install dependencies:
```
npm install
```

Build and start the server:

npm run start:http  # for Streamable HTTP transport
# OR
npm run start:stdio  # for stdio transport

View using the basic-host example or another MCP Apps-compatible host.

Architecture

Server (`server.ts`)

Exposes a single get-scenario-data tool that returns:

5 pre-built scenario templates with parameters, projections, and summaries
Default input values for the sliders
Optionally computes custom projections when customInputs are provided

The tool is linked to a UI resource via _meta.ui.resourceUri.

App (`src/`)

Built with React for reactive slider updates and derived state management
Uses Chart.js for the line chart visualization
All projection calculations run client-side for instant slider feedback
Components: SliderRow, MetricCard, ProjectionChart
Template comparison shown as dashed overlay lines on the chart

3.1 KiB Raw Blame History