PitchLense

A comprehensive Model Context Protocol (MCP) package for analyzing startup investment risks using AI-powered assessment across multiple risk categories. Built with FastMCP and LLM.

python

GitHub Stars

python

Language

6 months ago

First Indexed

2 months 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": {
    "connectaman-pitchlense-mcp": {
      "command": "pitchlense-mcp",
      "args": [
        "server"
      ],
      "env": {
        "GEMINI_API_KEY": "YOUR_GEMINI_API_KEY",
        "SERPAPI_API_KEY": "YOUR_SERPAPI_API_KEY",
        "PERPLEXITY_API_KEY": "YOUR_PERPLEXITY_API_KEY"
      }
    }
  }
}

PitchLense MCP is an AI-powered startup risk analysis server that exposes a complete MCP interface to analyze and quantify startup risks across multiple categories. You can run the server locally, connect via an MCP client, and receive structured risk assessments to guide investment decisions, founder planning, and portfolio risk management.

How to use

To use the PitchLense MCP server, start the local MCP process and connect an MCP-compatible client. The server analyzes startup information you provide as a single organized text input, returning structured risk scores, category insights, and investment guidance. Use the server to perform a comprehensive risk scan or quick assessments, and leverage the integration with external data sources for news and contextual references.

How to install

Prerequisites you need before installing: a Python runtime and Git installed on your system. You will also need access to API keys for AI models and data sources used by the server.

Additional setup steps

Get Gemini API Key: obtain an API key from the Gemini AI service you are using. 2) Create the environment file with your keys and tokens. 3) Install the MCP package from PyPI or clone the source and install in editable mode, then install development dependencies if you plan to contribute.

Notes on usage patterns

Start the MCP server with the designated command, then connect your client to the local server endpoint. - Use the ComprehensiveRiskScanner to perform a full analysis, or employ individual risk analyzers for targeted questions. - Ensure all required API keys are available in the environment before starting the server.

Configuration and environment

The server relies on environment variables to access external AI services and data sources. Ensure you populate the Gemini API key, SERP API key, and Perplexity API key before starting the server.

Security and troubleshooting

Keep API keys secure and do not expose them in client configurations. If the server fails to start due to missing keys, verify the environment file and restart the server after inserting valid credentials.

Examples of common workflows

Run a full risk scan for a startup profile and export the results to a JSON file for review. - Run a quick risk assessment for speed-of-insight scenarios and compare results against benchmark peers.

Available tools

ComprehensiveRiskScanner

Orchestrates a full risk analysis across all risk categories and produces a unified risk report with an overall score and recommendations.

MarketRiskAnalyzer

Evaluates market-related risks such as TAM accuracy, growth expectations, and competitive dynamics.

ProductRiskAnalyzer

Assesses product-stage risk, PMF clarity, technical feasibility, and IP protection.

TeamRiskAnalyzer

Analyzes founder and team dynamics, credibility, and capability gaps.

FinancialRiskAnalyzer

Reviews financial metrics, burn, runway, and CAC/LTV projections.

CustomerRiskAnalyzer

Assesses traction, churn, retention, and concentration risk.

OperationalRiskAnalyzer

Evaluates delivery, GTM, supply chain, and execution risk.

CompetitiveRiskAnalyzer

Assesses defensibility, incumbents, and market entry barriers.

LegalRiskAnalyzer

Reviews regulatory exposure, compliance gaps, and IP considerations.

ExitRiskAnalyzer

Analyzes potential exit pathways and late-stage sector demand.

Built by

VeilStrat

AI signals for GTM teams