# Investment Statement MCP Server

Parse and query investment statements from multiple institutions using natural language.

## Features

- **Multi-Institution Support**: Questrade, Interactive Brokers, Scotia iTRADE, TD Direct Investing
- **Hybrid Storage**: SQLite for structured queries + LanceDB for semantic search
- **Natural Language Queries**: Ask questions like "What were my dividends in Q3?" or "Show my SPY holdings"
- **Structured Tools**: Programmatic access via MCP tools
- **Portfolio Analytics**: Risk metrics, performance tracking, benchmark comparisons
- **Monte Carlo Simulation**: 5-year portfolio projections with percentile analysis and visualizations
- **Archive Management**: Keeps original PDFs/CSVs and parsed JSON for reference

## Installation

```bash
# Install dependencies
pip install -e ".[dev]"
```

## Configuration

The server is configured via `.mcp.json`. Key environment variables:

- `LANCEDB_PATH`: Vector database location (default: `./data/lancedb`)
- `SQLITE_PATH`: SQLite database location (default: `./data/statements.db`)
- `PDF_ARCHIVE_PATH`: Original PDF storage (default: `./data/pdfs`)
- `JSON_ARCHIVE_PATH`: Parsed JSON storage (default: `./data/json`)
- `MODEL_NAME`: Embedding model (default: `all-MiniLM-L6-v2`)

## Usage

### Starting the Server

```bash
python -m src.server
```

### Indexing Statements

```python
# Via MCP tool
index_statement("/path/to/statement.pdf")
```

### Querying Data

**Natural Language Search:**
```python
search_statements("What were my total dividends in 2025?", limit=10)
```

**Structured Queries:**
```python
get_holdings_by_symbol("SPY")
get_transactions_by_date("2025-01-01", "2025-09-30")
get_account_balance("51516162", "2025-09-30")
```

**Monte Carlo Simulation:**
```python
# Run portfolio projection simulation
result = run_monte_carlo_simulation(
    n_simulations=10000,      # 10,000 simulation paths
    projection_years=5,        # Project 5 years into the future
    account_numbers=None,      # None = all accounts
    percentiles=[10, 25, 50, 75, 90]
)

# Results saved to:
# - Timestamped: data/reports/monte_carlo/2025-11-26_153034/
# - Latest: data/reports/monte_carlo/latest/
#
# Output includes:
# - 3 PNG charts (fan chart, distribution, confidence intervals)
# - 3 CSV files (projections, summary, historical_returns)
```

See [MONTE_CARLO.md](MONTE_CARLO.md) for detailed documentation.

### Resources

- `statements://catalog` - List all indexed statements
- `statements://{statement_id}` - Get specific statement
- `statements://{statement_id}/summary` - Account summary
- `statements://{statement_id}/holdings` - Holdings/positions
- `statements://{statement_id}/transactions` - Transaction history

## Supported Statements

### Questrade
- ✅ Account Summary (balances, FX rates, TFSA info)
- ✅ Holdings/Positions (securities with cost basis, P&L)
- ✅ Transactions (trades, dividends, deposits, withdrawals)

### Interactive Brokers (Coming Soon)
- ⏳ Planned

### Scotia (Coming Soon)
- ⏳ Planned

## Development

```bash
# Run tests
pytest

# Run tests with coverage
pytest --cov=src --cov-report=html

# Format code
black src tests

# Lint code
ruff check src tests
```

## Architecture

- **FastMCP 2.0**: MCP server framework
- **pymupdf4llm**: PDF parsing optimized for LLMs
- **LanceDB**: Vector database for semantic search
- **SQLite**: Structured metadata storage
- **sentence-transformers**: Embedding generation

## License

MIT