MCP ROI Server

Provides ROI predictions with Monte Carlo simulations, Dutch market validation, and real-time benchmarks.
  • typescript

0

GitHub Stars

typescript

Language

3 months ago

First Indexed

3 weeks ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "spaik-io-mcp-server-roi": {
      "command": "node",
      "args": [
        "/absolute/path/to/mcp-server-roi/dist/index.js"
      ],
      "env": {
        "LOG_LEVEL": "info",
        "SUPABASE_URL": "https://xxxxxxxxxxxxx.supabase.co",
        "SUPABASE_ANON_KEY": "your_supabase_anon_key",
        "PERPLEXITY_API_KEY": "your_perplexity_key",
        "SUPABASE_SERVICE_KEY": "your_service_key"
      }
    }
  }
}

You are equipped with a dedicated MCP server for ROI prediction and tracking, powered by Monte Carlo simulations, real-time benchmarks, and ML-powered insights. It includes Dutch market validation and natural language support to streamline how you specify projects and extract actionable financial intelligence.

How to use

You use this MCP server by connecting an MCP client or tool that can send requests to the server, then interpret the rich, multi-layered responses that combine executive summaries, detailed insights, and actionable recommendations. Start by validating your inputs, then run ROI predictions, multi-project comparisons, or help you explore examples and guidance through the built-in assistance tools. The server accepts natural language input for easier description of your use case, or structured input when you prefer explicit fields such as client, project, industry, budget, and timeline. Results incorporate Dutch market validation, realistic value adjustments, and confidence scores to help you decide on next steps.

How to install

Prerequisites: You need Node.js installed on your system to run the MCP server locally. You will also interact with environment variables for secure access to data sources and benchmarks.

Step 1: Install Node.js if you don’t already have it. Visit the Node.js download page and install the LTS version suitable for your operating system.

Step 2: Install the MCP ROI server package from npm or set up the source and build it if you prefer running from source.

Configuration

Set up environment variables to enable full functionality and real-time benchmarks. You need the Supabase configuration keys and the Perplexity API key for real-time market data and benchmarks.

Environment variables to configure (examples shown with placeholders):

# Required - Supabase Configuration
SUPABASE_URL=https://xxxxxxxxxxxxx.supabase.co
SUPABASE_ANON_KEY=your_supabase_anon_key

# Required for full functionality
SUPABASE_SERVICE_KEY=your_service_key  # Admin access
PERPLEXITY_API_KEY=your_perplexity_key # Real-time benchmarks

# Optional - Enhanced Features
FMP_API_KEY=your_fmp_key              # Financial market data
LOG_LEVEL=info                        # debug|info|warn|error
WORKER_POOL_SIZE=4                    # CPU cores
MAX_SIMULATION_ITERATIONS=100000      # Monte Carlo precision

Security considerations

The server uses secure keys to access data sources. Validate inputs with strict schemas and ensure API keys are stored securely and not committed to code repositories. Use the provided env var mechanism to inject sensitive data at runtime.

Troubleshooting

If you encounter permission or API errors, verify that your environment variables are correctly set and that your API keys are valid. The server includes graceful fallbacks to static benchmarks if external APIs are unavailable.

Development

If you want to run the server in development mode, install dependencies, build, and start the server as described in the development workflow. This enables you to test Monte Carlo simulations, NL P input, and the Dutch market validation logic.

Available tools

predict_roi

Generate ROI predictions using Monte Carlo simulations with Dutch market validation and natural language input support.

compare_projects

Compare multiple projects with ML-powered insights and risk assessments.

get_examples

Retrieve usage examples for any MCP tool.

help

Interactively obtain help and tool recommendations.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational