# PitchLense MCP - Professional Startup Risk Analysis Package
[](https://www.python.org/downloads/)
[](https://pitchlense-mcp.readthedocs.io/)
[](https://opensource.org/licenses/MIT)
[](https://pypi.org/project/pitchlense-mcp/)
[](https://github.com/connectaman/Pitchlense-mcp/actions)
A comprehensive Model Context Protocol (MCP) package for analyzing startup investment risks using AI-powered assessment across multiple risk categories. Built with FastMCP and Google Gemini AI.
## 🚀 Features
### Individual Risk Analysis Tools
- **Market Risk Analyzer** - TAM, growth rate, competition, differentiation
- **Product Risk Analyzer** - Development stage, market fit, technical feasibility, IP protection
- **Team Risk Analyzer** - Leadership depth, founder stability, skill gaps, credibility
- **Financial Risk Analyzer** - Metrics consistency, burn rate, projections, CAC/LTV
- **Customer Risk Analyzer** - Traction levels, churn rate, retention, customer concentration
- **Operational Risk Analyzer** - Supply chain, GTM strategy, efficiency, execution
- **Competitive Risk Analyzer** - Incumbent strength, entry barriers, defensibility
- **Legal Risk Analyzer** - Regulatory environment, compliance, legal disputes
- **Exit Risk Analyzer** - Exit pathways, sector activity, late-stage appeal
### Comprehensive Analysis Tools & Data Sources
- **Comprehensive Risk Scanner** - Full analysis across all risk categories
- **Quick Risk Assessment** - Fast assessment of critical risk areas
- **Peer Benchmarking** - Compare metrics against sector/stage peers
- **SerpAPI Google News Tool** - Fetches first-page Google News with URLs and thumbnails
- **Perplexity Search Tool** - Answers with cited sources and URLs
## 📊 Risk Categories Covered
| Category | Key risks |
| --- | --- |
| Market | Small/overstated TAM; weak growth; crowded space; limited differentiation; niche dependence |
| Product | Early stage; unclear PMF; technical uncertainty; weak IP; poor scalability |
| Team/Founder | Single-founder risk; churn; skill gaps; credibility; misaligned incentives |
| Financial | Inconsistent metrics; high burn/short runway; optimistic projections; unfavorable CAC/LTV; low margins |
| Customer & Traction | Low traction; high churn; low retention; no marquee customers; concentration risk |
| Operational | Fragile supply chain; unclear GTM; operational inefficiency; poor execution |
| Competitive | Strong incumbents; low entry barriers; weak defensibility; saturation |
| Legal & Regulatory | Grey/untested areas; compliance gaps; disputes; IP risks |
| Exit | Unclear pathways; low sector exit activity; weak late‑stage appeal |
## 🛠️ Installation
### From PyPI (Recommended)
```bash
pip install pitchlense-mcp
```
### From Source
```bash
git clone https://github.com/pitchlense/pitchlense-mcp.git
cd pitchlense-mcp
pip install -e .
```
### Development Installation
```bash
git clone https://github.com/pitchlense/pitchlense-mcp.git
cd pitchlense-mcp
pip install -e ".[dev]"
```
## 🔑 Setup
### 1. Get Gemini API Key
1. Visit [Google AI Studio](https://makersuite.google.com/app/apikey)
2. Create a new API key
3. Copy the API key
### 2. Create .env
```bash
cp .env.template .env
# edit .env and fill in keys
```
Supported variables:
```
GEMINI_API_KEY=
SERPAPI_API_KEY=
PERPLEXITY_API_KEY=
```
## 🚀 Usage
### Command Line Interface
#### Run Comprehensive Analysis
```bash
# Create sample data
pitchlense-mcp sample --output my_startup.json
# Run comprehensive analysis
pitchlense-mcp analyze --input my_startup.json --output results.json
```
#### Run Quick Assessment
```bash
pitchlense-mcp quick --input my_startup.json --output quick_results.json
```
#### Start MCP Server
```bash
pitchlense-mcp server
```
### Python API
#### Basic Usage (single text input)
```python
from pitchlense_mcp import ComprehensiveRiskScanner
# Initialize scanner (reads GEMINI_API_KEY from env if not provided)
scanner = ComprehensiveRiskScanner()
# Provide all startup info as one organized text string
startup_info = """
Name: TechFlow Solutions
Industry: SaaS/Productivity Software
Stage: Series A
Business Model:
AI-powered workflow automation for SMBs; subscription pricing.
Financials:
MRR: $45k; Burn: $35k; Runway: 8 months; LTV/CAC: 13.3
Traction:
250 customers; 1,200 MAU; Churn: 5% monthly; NRR: 110%
Team:
CEO: Sarah Chen; CTO: Michael Rodriguez; Team size: 12
Market & Competition:
TAM: $12B; Competitors: Zapier, Power Automate; Growth: 15% YoY
"""
# Run comprehensive analysis
results = scanner.comprehensive_startup_risk_analysis(startup_info)
print(f"Overall Risk Level: {results['overall_risk_level']}")
print(f"Overall Risk Score: {results['overall_score']}/10")
print(f"Investment Recommendation: {results['investment_recommendation']}")
```
#### Individual Risk Analysis (text input)
```python
from pitchlense_mcp import MarketRiskAnalyzer, GeminiLLM
# Initialize components
llm_client = GeminiLLM(api_key="your_api_key")
market_analyzer = MarketRiskAnalyzer(llm_client)
# Analyze market risks
market_results = market_analyzer.analyze(startup_info)
print(f"Market Risk Level: {market_results['overall_risk_level']}")
```
### MCP Server Integration
The package provides a complete MCP server that can be integrated with MCP-compatible clients:
```python
from pitchlense_mcp import ComprehensiveRiskScanner
# Start MCP server
scanner = ComprehensiveRiskScanner()
scanner.run()
```
## 📋 Input Data Format
The primary input is a single organized text string containing all startup information (details, metrics, traction, news, competitive landscape, etc.). This is the format used by all analyzers and MCP tools.
Example text input:
```
Name: AcmeAI
Industry: Fintech (Lending)
Stage: Seed
Summary:
Building AI-driven credit risk models for SMB lending; initial pilots with 5 lenders.
Financials:
MRR: $12k; Burn: $60k; Runway: 10 months; Gross Margin: 78%
Traction:
200 paying SMBs; 30% MoM growth; Churn: 3% monthly; CAC: $220; LTV: $2,100
Team:
Founders: Jane Doe (ex-Square), John Lee (ex-Stripe); Team size: 9
Market & Competition:
TAM: $25B; Competitors: Blend, Upstart; Advantage: faster underwriting via proprietary data partnerships
```
Tip: See `examples/text_input_example.py` for a complete end-to-end script and JSON export of results.
## 📊 Output Format
All tools return structured JSON responses with:
```json
{
"startup_name": "Startup Name",
"overall_risk_level": "low|medium|high|critical",
"overall_score": 1-10,
"risk_categories": [
{
"category_name": "Risk Category",
"overall_risk_level": "low|medium|high|critical",
"category_score": 1-10,
"indicators": [
{
"indicator": "Specific risk factor",
"risk_level": "low|medium|high|critical",
"score": 1-10,
"description": "Detailed risk description",
"recommendation": "Mitigation action"
}
],
"summary": "Category summary"
}
],
"key_concerns": ["Top 5 concerns"],
"investment_recommendation": "Investment advice",
"confidence_score": 0.0-1.0,
"analysis_metadata": {
"total_categories_analyzed": 9,
"successful_analyses": 9,
"analysis_timestamp": "2024-01-01T00:00:00Z"
}
}
```
## 🎯 Use Cases
- **Investor Due Diligence** - Comprehensive risk assessment for investment decisions
- **Startup Self-Assessment** - Identify and mitigate key risk areas
- **Portfolio Risk Management** - Assess risk across startup portfolio
- **Accelerator/Incubator Screening** - Evaluate startup applications
- **M&A Risk Analysis** - Assess acquisition targets
- **Research & Analysis** - Academic and industry research on startup risks
## 🏗️ Architecture
### Package Structure
```
pitchlense-mcp/
├── pitchlense_mcp/
│ ├── __init__.py
│ ├── cli.py # Command-line interface
│ ├── core/ # Core functionality
│ │ ├── __init__.py
│ │ ├── base.py # Base classes
│ │ ├── gemini_client.py # Gemini AI integration
│ │ └── comprehensive_scanner.py
│ ├── models/ # Data models
│ │ ├── __init__.py
│ │ └── risk_models.py
│ ├── analyzers/ # Individual risk analyzers
│ │ ├── __init__.py
│ │ ├── market_risk.py
│ │ ├── product_risk.py
│ │ ├── team_risk.py
│ │ ├── financial_risk.py
│ │ ├── customer_risk.py
│ │ ├── operational_risk.py
│ │ ├── competitive_risk.py
│ │ ├── legal_risk.py
│ │ └── exit_risk.py
│ └── utils/ # Utility functions
├── tests/ # Test suite
├── docs/ # Documentation
├── examples/ # Example usage
├── setup.py
├── pyproject.toml
├── requirements.txt
└── README.md
```
### Key Components
1. **Base Classes** (`core/base.py`)
- `BaseLLM` - Abstract base for LLM integrations
- `BaseRiskAnalyzer` - Base class for all risk analyzers
- `BaseMCPTool` - Base class for MCP tools
2. **Gemini Integration** (`core/gemini_client.py`)
- `GeminiLLM` - Main LLM client
- `GeminiTextGenerator` - Text generation
- `GeminiImageAnalyzer` - Image analysis
- `GeminiVideoAnalyzer` - Video analysis
- `GeminiAudioAnalyzer` - Audio analysis
- `GeminiDocumentAnalyzer` - Document analysis
3. **Risk Analyzers** (`analyzers/`)
- Individual analyzers for each risk category
- Consistent interface and output format
- Extensible architecture
4. **Models** (`models/risk_models.py`)
- Pydantic models for type safety
- Structured data validation
- Clear data contracts
## 🔧 Development
### Setup Development Environment
```bash
git clone https://github.com/pitchlense/pitchlense-mcp.git
cd pitchlense-mcp
pip install -e ".[dev]"
pre-commit install
```
### Run Tests
```bash
# Create and activate a virtual environment (recommended)
python3 -m venv .venv
source .venv/bin/activate
# Install dev extras (pytest, pytest-cov, linters)
pip install -e ".[dev]"
# Run tests with coverage and avoid global plugin conflicts
PYTEST_DISABLE_PLUGIN_AUTOLOAD=1 pytest -q -p pytest_cov
```
Notes:
- Coverage reports are written to `htmlcov/index.html` and `coverage.xml`.
- If you see errors about unknown `--cov` options, ensure you passed `-p pytest_cov` when `PYTEST_DISABLE_PLUGIN_AUTOLOAD=1` is set.
### Example Scripts
```bash
python examples/basic_usage.py
python examples/text_input_example.py
```
### Code Formatting
```bash
black pitchlense_mcp/
flake8 pitchlense_mcp/
mypy pitchlense_mcp/
```
### Build Package
```bash
python -m build
```
## 📝 Notes
- All risk scores are on a 1-10 scale (1 = lowest risk, 10 = highest risk)
- Risk levels: low (1-3), medium (4-6), high (7-8), critical (9-10)
- Individual tools can be used independently or combined for comprehensive analysis
- The system handles API failures gracefully with fallback responses
- All tables and structured data are returned in JSON format
- Professional package architecture with proper separation of concerns
## 🤝 Contributing
We welcome contributions! Please see our [Contributing Guide](CONTRIBUTING.md) for details.
1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests
5. Submit a pull request
## 📄 License
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
## 🆘 Support
- **Documentation**: [https://pitchlense-mcp.readthedocs.io/](https://pitchlense-mcp.readthedocs.io/)
- **Issues**: [GitHub Issues](https://github.com/pitchlense/pitchlense-mcp/issues)
- **Email**: connectamanulla@gmail.com
## 🙏 Acknowledgments
- Google Gemini AI for providing the underlying AI capabilities
- FastMCP for the Model Context Protocol implementation
- The open-source community for inspiration and tools
---
**PitchLense MCP** - Making startup risk analysis accessible, comprehensive, and AI-powered.
Raw data
{
"_id": null,
"home_page": "https://github.com/pitchlense/pitchlense-mcp",
"name": "pitchlense-mcp",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": "Aman Ulla <connectamanulla@gmail.com>",
"keywords": "startup, risk, analysis, investment, mcp, model-context-protocol, gemini, ai, machine-learning, due-diligence, venture-capital",
"author": "Aman Ulla",
"author_email": "Aman Ulla <connectamanulla@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/70/e1/ce1a4a32322edd641ac8774fe0c5ec190cf0e049d81708de4ef40dbb1faa/pitchlense_mcp-1.0.3.tar.gz",
"platform": null,
"description": "# PitchLense MCP - Professional Startup Risk Analysis Package\n\n[](https://www.python.org/downloads/)\n[](https://pitchlense-mcp.readthedocs.io/)\n[](https://opensource.org/licenses/MIT)\n[](https://pypi.org/project/pitchlense-mcp/)\n[](https://github.com/connectaman/Pitchlense-mcp/actions)\n\nA comprehensive Model Context Protocol (MCP) package for analyzing startup investment risks using AI-powered assessment across multiple risk categories. Built with FastMCP and Google Gemini AI.\n\n## \ud83d\ude80 Features\n\n### Individual Risk Analysis Tools\n- **Market Risk Analyzer** - TAM, growth rate, competition, differentiation\n- **Product Risk Analyzer** - Development stage, market fit, technical feasibility, IP protection\n- **Team Risk Analyzer** - Leadership depth, founder stability, skill gaps, credibility\n- **Financial Risk Analyzer** - Metrics consistency, burn rate, projections, CAC/LTV\n- **Customer Risk Analyzer** - Traction levels, churn rate, retention, customer concentration\n- **Operational Risk Analyzer** - Supply chain, GTM strategy, efficiency, execution\n- **Competitive Risk Analyzer** - Incumbent strength, entry barriers, defensibility\n- **Legal Risk Analyzer** - Regulatory environment, compliance, legal disputes\n- **Exit Risk Analyzer** - Exit pathways, sector activity, late-stage appeal\n\n### Comprehensive Analysis Tools & Data Sources\n- **Comprehensive Risk Scanner** - Full analysis across all risk categories\n- **Quick Risk Assessment** - Fast assessment of critical risk areas\n- **Peer Benchmarking** - Compare metrics against sector/stage peers\n- **SerpAPI Google News Tool** - Fetches first-page Google News with URLs and thumbnails\n- **Perplexity Search Tool** - Answers with cited sources and URLs\n\n## \ud83d\udcca Risk Categories Covered\n\n| Category | Key risks |\n| --- | --- |\n| Market | Small/overstated TAM; weak growth; crowded space; limited differentiation; niche dependence |\n| Product | Early stage; unclear PMF; technical uncertainty; weak IP; poor scalability |\n| Team/Founder | Single-founder risk; churn; skill gaps; credibility; misaligned incentives |\n| Financial | Inconsistent metrics; high burn/short runway; optimistic projections; unfavorable CAC/LTV; low margins |\n| Customer & Traction | Low traction; high churn; low retention; no marquee customers; concentration risk |\n| Operational | Fragile supply chain; unclear GTM; operational inefficiency; poor execution |\n| Competitive | Strong incumbents; low entry barriers; weak defensibility; saturation |\n| Legal & Regulatory | Grey/untested areas; compliance gaps; disputes; IP risks |\n| Exit | Unclear pathways; low sector exit activity; weak late\u2011stage appeal |\n\n## \ud83d\udee0\ufe0f Installation\n\n### From PyPI (Recommended)\n```bash\npip install pitchlense-mcp\n```\n\n### From Source\n```bash\ngit clone https://github.com/pitchlense/pitchlense-mcp.git\ncd pitchlense-mcp\npip install -e .\n```\n\n### Development Installation\n```bash\ngit clone https://github.com/pitchlense/pitchlense-mcp.git\ncd pitchlense-mcp\npip install -e \".[dev]\"\n```\n\n## \ud83d\udd11 Setup\n\n### 1. Get Gemini API Key\n1. Visit [Google AI Studio](https://makersuite.google.com/app/apikey)\n2. Create a new API key\n3. Copy the API key\n\n### 2. Create .env\n```bash\ncp .env.template .env\n# edit .env and fill in keys\n```\nSupported variables:\n```\nGEMINI_API_KEY=\nSERPAPI_API_KEY=\nPERPLEXITY_API_KEY=\n```\n\n## \ud83d\ude80 Usage\n\n### Command Line Interface\n\n#### Run Comprehensive Analysis\n```bash\n# Create sample data\npitchlense-mcp sample --output my_startup.json\n\n# Run comprehensive analysis\npitchlense-mcp analyze --input my_startup.json --output results.json\n```\n\n#### Run Quick Assessment\n```bash\npitchlense-mcp quick --input my_startup.json --output quick_results.json\n```\n\n#### Start MCP Server\n```bash\npitchlense-mcp server\n```\n\n### Python API\n\n#### Basic Usage (single text input)\n```python\nfrom pitchlense_mcp import ComprehensiveRiskScanner\n\n# Initialize scanner (reads GEMINI_API_KEY from env if not provided)\nscanner = ComprehensiveRiskScanner()\n\n# Provide all startup info as one organized text string\nstartup_info = \"\"\"\nName: TechFlow Solutions\nIndustry: SaaS/Productivity Software\nStage: Series A\n\nBusiness Model:\nAI-powered workflow automation for SMBs; subscription pricing.\n\nFinancials:\nMRR: $45k; Burn: $35k; Runway: 8 months; LTV/CAC: 13.3\n\nTraction:\n250 customers; 1,200 MAU; Churn: 5% monthly; NRR: 110%\n\nTeam:\nCEO: Sarah Chen; CTO: Michael Rodriguez; Team size: 12\n\nMarket & Competition:\nTAM: $12B; Competitors: Zapier, Power Automate; Growth: 15% YoY\n\"\"\"\n\n# Run comprehensive analysis\nresults = scanner.comprehensive_startup_risk_analysis(startup_info)\n\nprint(f\"Overall Risk Level: {results['overall_risk_level']}\")\nprint(f\"Overall Risk Score: {results['overall_score']}/10\")\nprint(f\"Investment Recommendation: {results['investment_recommendation']}\")\n```\n\n#### Individual Risk Analysis (text input)\n```python\nfrom pitchlense_mcp import MarketRiskAnalyzer, GeminiLLM\n\n# Initialize components\nllm_client = GeminiLLM(api_key=\"your_api_key\")\nmarket_analyzer = MarketRiskAnalyzer(llm_client)\n\n# Analyze market risks\nmarket_results = market_analyzer.analyze(startup_info)\nprint(f\"Market Risk Level: {market_results['overall_risk_level']}\")\n```\n\n### MCP Server Integration\n\nThe package provides a complete MCP server that can be integrated with MCP-compatible clients:\n\n```python\nfrom pitchlense_mcp import ComprehensiveRiskScanner\n\n# Start MCP server\nscanner = ComprehensiveRiskScanner()\nscanner.run()\n```\n\n## \ud83d\udccb Input Data Format\n\nThe primary input is a single organized text string containing all startup information (details, metrics, traction, news, competitive landscape, etc.). This is the format used by all analyzers and MCP tools.\n\nExample text input:\n```\nName: AcmeAI\nIndustry: Fintech (Lending)\nStage: Seed\n\nSummary:\nBuilding AI-driven credit risk models for SMB lending; initial pilots with 5 lenders.\n\nFinancials:\nMRR: $12k; Burn: $60k; Runway: 10 months; Gross Margin: 78%\n\nTraction:\n200 paying SMBs; 30% MoM growth; Churn: 3% monthly; CAC: $220; LTV: $2,100\n\nTeam:\nFounders: Jane Doe (ex-Square), John Lee (ex-Stripe); Team size: 9\n\nMarket & Competition:\nTAM: $25B; Competitors: Blend, Upstart; Advantage: faster underwriting via proprietary data partnerships\n```\n\nTip: See `examples/text_input_example.py` for a complete end-to-end script and JSON export of results.\n\n## \ud83d\udcca Output Format\n\nAll tools return structured JSON responses with:\n\n```json\n{\n \"startup_name\": \"Startup Name\",\n \"overall_risk_level\": \"low|medium|high|critical\",\n \"overall_score\": 1-10,\n \"risk_categories\": [\n {\n \"category_name\": \"Risk Category\",\n \"overall_risk_level\": \"low|medium|high|critical\",\n \"category_score\": 1-10,\n \"indicators\": [\n {\n \"indicator\": \"Specific risk factor\",\n \"risk_level\": \"low|medium|high|critical\",\n \"score\": 1-10,\n \"description\": \"Detailed risk description\",\n \"recommendation\": \"Mitigation action\"\n }\n ],\n \"summary\": \"Category summary\"\n }\n ],\n \"key_concerns\": [\"Top 5 concerns\"],\n \"investment_recommendation\": \"Investment advice\",\n \"confidence_score\": 0.0-1.0,\n \"analysis_metadata\": {\n \"total_categories_analyzed\": 9,\n \"successful_analyses\": 9,\n \"analysis_timestamp\": \"2024-01-01T00:00:00Z\"\n }\n}\n```\n\n## \ud83c\udfaf Use Cases\n\n- **Investor Due Diligence** - Comprehensive risk assessment for investment decisions\n- **Startup Self-Assessment** - Identify and mitigate key risk areas\n- **Portfolio Risk Management** - Assess risk across startup portfolio\n- **Accelerator/Incubator Screening** - Evaluate startup applications\n- **M&A Risk Analysis** - Assess acquisition targets\n- **Research & Analysis** - Academic and industry research on startup risks\n\n## \ud83c\udfd7\ufe0f Architecture\n\n### Package Structure\n```\npitchlense-mcp/\n\u251c\u2500\u2500 pitchlense_mcp/\n\u2502 \u251c\u2500\u2500 __init__.py\n\u2502 \u251c\u2500\u2500 cli.py # Command-line interface\n\u2502 \u251c\u2500\u2500 core/ # Core functionality\n\u2502 \u2502 \u251c\u2500\u2500 __init__.py\n\u2502 \u2502 \u251c\u2500\u2500 base.py # Base classes\n\u2502 \u2502 \u251c\u2500\u2500 gemini_client.py # Gemini AI integration\n\u2502 \u2502 \u2514\u2500\u2500 comprehensive_scanner.py\n\u2502 \u251c\u2500\u2500 models/ # Data models\n\u2502 \u2502 \u251c\u2500\u2500 __init__.py\n\u2502 \u2502 \u2514\u2500\u2500 risk_models.py\n\u2502 \u251c\u2500\u2500 analyzers/ # Individual risk analyzers\n\u2502 \u2502 \u251c\u2500\u2500 __init__.py\n\u2502 \u2502 \u251c\u2500\u2500 market_risk.py\n\u2502 \u2502 \u251c\u2500\u2500 product_risk.py\n\u2502 \u2502 \u251c\u2500\u2500 team_risk.py\n\u2502 \u2502 \u251c\u2500\u2500 financial_risk.py\n\u2502 \u2502 \u251c\u2500\u2500 customer_risk.py\n\u2502 \u2502 \u251c\u2500\u2500 operational_risk.py\n\u2502 \u2502 \u251c\u2500\u2500 competitive_risk.py\n\u2502 \u2502 \u251c\u2500\u2500 legal_risk.py\n\u2502 \u2502 \u2514\u2500\u2500 exit_risk.py\n\u2502 \u2514\u2500\u2500 utils/ # Utility functions\n\u251c\u2500\u2500 tests/ # Test suite\n\u251c\u2500\u2500 docs/ # Documentation\n\u251c\u2500\u2500 examples/ # Example usage\n\u251c\u2500\u2500 setup.py\n\u251c\u2500\u2500 pyproject.toml\n\u251c\u2500\u2500 requirements.txt\n\u2514\u2500\u2500 README.md\n```\n\n### Key Components\n\n1. **Base Classes** (`core/base.py`)\n - `BaseLLM` - Abstract base for LLM integrations\n - `BaseRiskAnalyzer` - Base class for all risk analyzers\n - `BaseMCPTool` - Base class for MCP tools\n\n2. **Gemini Integration** (`core/gemini_client.py`)\n - `GeminiLLM` - Main LLM client\n - `GeminiTextGenerator` - Text generation\n - `GeminiImageAnalyzer` - Image analysis\n - `GeminiVideoAnalyzer` - Video analysis\n - `GeminiAudioAnalyzer` - Audio analysis\n - `GeminiDocumentAnalyzer` - Document analysis\n\n3. **Risk Analyzers** (`analyzers/`)\n - Individual analyzers for each risk category\n - Consistent interface and output format\n - Extensible architecture\n\n4. **Models** (`models/risk_models.py`)\n - Pydantic models for type safety\n - Structured data validation\n - Clear data contracts\n\n## \ud83d\udd27 Development\n\n### Setup Development Environment\n```bash\ngit clone https://github.com/pitchlense/pitchlense-mcp.git\ncd pitchlense-mcp\npip install -e \".[dev]\"\npre-commit install\n```\n\n### Run Tests\n```bash\n# Create and activate a virtual environment (recommended)\npython3 -m venv .venv\nsource .venv/bin/activate\n\n# Install dev extras (pytest, pytest-cov, linters)\npip install -e \".[dev]\"\n\n# Run tests with coverage and avoid global plugin conflicts\nPYTEST_DISABLE_PLUGIN_AUTOLOAD=1 pytest -q -p pytest_cov\n```\n\nNotes:\n- Coverage reports are written to `htmlcov/index.html` and `coverage.xml`.\n- If you see errors about unknown `--cov` options, ensure you passed `-p pytest_cov` when `PYTEST_DISABLE_PLUGIN_AUTOLOAD=1` is set.\n\n### Example Scripts\n```bash\npython examples/basic_usage.py\npython examples/text_input_example.py\n```\n\n### Code Formatting\n```bash\nblack pitchlense_mcp/\nflake8 pitchlense_mcp/\nmypy pitchlense_mcp/\n```\n\n### Build Package\n```bash\npython -m build\n```\n\n## \ud83d\udcdd Notes\n\n- All risk scores are on a 1-10 scale (1 = lowest risk, 10 = highest risk)\n- Risk levels: low (1-3), medium (4-6), high (7-8), critical (9-10)\n- Individual tools can be used independently or combined for comprehensive analysis\n- The system handles API failures gracefully with fallback responses\n- All tables and structured data are returned in JSON format\n- Professional package architecture with proper separation of concerns\n\n## \ud83e\udd1d Contributing\n\nWe welcome contributions! Please see our [Contributing Guide](CONTRIBUTING.md) for details.\n\n1. Fork the repository\n2. Create a feature branch\n3. Make your changes\n4. Add tests\n5. Submit a pull request\n\n## \ud83d\udcc4 License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n## \ud83c\udd98 Support\n\n- **Documentation**: [https://pitchlense-mcp.readthedocs.io/](https://pitchlense-mcp.readthedocs.io/)\n- **Issues**: [GitHub Issues](https://github.com/pitchlense/pitchlense-mcp/issues)\n- **Email**: connectamanulla@gmail.com\n\n## \ud83d\ude4f Acknowledgments\n\n- Google Gemini AI for providing the underlying AI capabilities\n- FastMCP for the Model Context Protocol implementation\n- The open-source community for inspiration and tools\n\n---\n\n**PitchLense MCP** - Making startup risk analysis accessible, comprehensive, and AI-powered.\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Professional startup risk analysis using MCP and Google Gemini AI",
"version": "1.0.3",
"project_urls": {
"Bug Tracker": "https://github.com/pitchlense/pitchlense-mcp/issues",
"Documentation": "https://pitchlense-mcp.readthedocs.io/",
"Homepage": "https://pitchlense.com",
"Repository": "https://github.com/pitchlense/pitchlense-mcp"
},
"split_keywords": [
"startup",
" risk",
" analysis",
" investment",
" mcp",
" model-context-protocol",
" gemini",
" ai",
" machine-learning",
" due-diligence",
" venture-capital"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "a445475788b4e692a568cd2132aef7404059f9de86e93d9bdb230c6b618c17f6",
"md5": "020c4b9b4c673796829abf1bdfc51a35",
"sha256": "ffa8ce64209025b4bddfc030b90b0f1281dc3896b75474060b8aea5758f7852f"
},
"downloads": -1,
"filename": "pitchlense_mcp-1.0.3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "020c4b9b4c673796829abf1bdfc51a35",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 47428,
"upload_time": "2025-09-08T09:54:24",
"upload_time_iso_8601": "2025-09-08T09:54:24.561006Z",
"url": "https://files.pythonhosted.org/packages/a4/45/475788b4e692a568cd2132aef7404059f9de86e93d9bdb230c6b618c17f6/pitchlense_mcp-1.0.3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "70e1ce1a4a32322edd641ac8774fe0c5ec190cf0e049d81708de4ef40dbb1faa",
"md5": "3be361eb3edcadf182d8131ea3a69462",
"sha256": "62528f81d232e670bb22ff7d00b7f20c38792dfe47fdbae8ae89ba2ff94b1bf0"
},
"downloads": -1,
"filename": "pitchlense_mcp-1.0.3.tar.gz",
"has_sig": false,
"md5_digest": "3be361eb3edcadf182d8131ea3a69462",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 42920,
"upload_time": "2025-09-08T09:54:25",
"upload_time_iso_8601": "2025-09-08T09:54:25.689668Z",
"url": "https://files.pythonhosted.org/packages/70/e1/ce1a4a32322edd641ac8774fe0c5ec190cf0e049d81708de4ef40dbb1faa/pitchlense_mcp-1.0.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-09-08 09:54:25",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "pitchlense",
"github_project": "pitchlense-mcp",
"github_not_found": true,
"lcname": "pitchlense-mcp"
}
JSON
