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.
claude mcp add --transport stdio connectaman-pitchlense-mcp python -m pitchlense_mcp \ --env GEMINI_API_KEY="Your Gemini API key (required for analysis)" \ --env SERPAPI_API_KEY="Your SerpAPI key (optional for news/queries)" \ --env PERPLEXITY_API_KEY="Your Perplexity API key (optional for cited sources)"
How to use
PitchLense is an MCP server that provides AI-powered startup risk analysis across multiple risk categories. It exposes a server component built with Python and the PitchLense MCP package, enabling clients to submit startup information and receive structured risk assessments, insights, and recommendations. The server integrates tools such as a ComprehensiveRiskScanner, MarketRiskAnalyzer, and other risk analyzers to produce an overall risk level, scores, and investment recommendations. You can run the server locally and connect via MCP-compatible clients or use the included Python API examples to trigger analyses programmatically. The server is designed to read configuration and API keys from environment variables, so you can securely provide access to Gemini, SerpAPI, and Perplexity services as you deploy.
How to install
Prerequisites:
- Python 3.8+ installed on your system
- Git installed to clone the repository or install from PyPI
- Internet access to download dependencies
Option A: Install from PyPI (recommended)
- Ensure Python and pip are up to date
- Install the package: pip install pitchlense-mcp
Option B: Install from Source
- Clone the repository: git clone https://github.com/pitchlense/pitchlense-mcp.git
- Navigate to the project folder: cd pitchlense-mcp
- Install in editable mode: pip install -e .
Option C: Development Installation (optional)
- Clone the repo
- Install dev dependencies: pip install -e ".[dev]"
After installation, prepare API keys and environment variables as described in the Setup section and you’re ready to run the MCP server.
Additional notes
Environment variables are required for external AI services. Suggested keys: GEMINI_API_KEY, SERPAPI_API_KEY, PERPLEXITY_API_KEY. If you do not use some services, you can omit their keys, but the corresponding features may be limited. When running the server, ensure your network allows outbound API calls to Gemini, SerpAPI, and Perplexity. If you encounter authentication errors, verify that API keys are correctly exported in your environment or provided via a .env file loaded at startup. To stop the server, use a keyboard interrupt (Ctrl+C) or the appropriate supervisor signal in your environment. The MCP server supports quick startup with the included CLI examples, and you can extend it by integrating additional analyzers as needed.
Related MCP Servers
jupyter
🪐 🔧 Model Context Protocol (MCP) Server for Jupyter.
mcp -odoo
A Model Context Protocol (MCP) server that enables AI assistants to securely interact with Odoo ERP systems through standardized resources and tools for data retrieval and manipulation.
falcon
Connect AI agents to CrowdStrike Falcon for automated security analysis and threat hunting
beemcp
BeeMCP: an unofficial Model Context Protocol (MCP) server that connects your Bee wearable lifelogger to AI via the Model Context Protocol
MCP-MultiServer-Interoperable-Agent2Agent-LangGraph-AI-System
This project demonstrates a decoupled real-time agent architecture that connects LangGraph agents to remote tools served by custom MCP (Modular Command Protocol) servers. The architecture enables a flexible and scalable multi-agent system where each tool can be hosted independently (via SSE or STDIO), offering modularity and cloud-deployable execut
Helios
An AI IDE secure coding MCP service
