black-litterman-mcp 0.3.0

Black-Litterman Portfolio Optimization MCP Server

Black-Litterman Portfolio Optimization MCP Server

Black-Litterman portfolio optimization MCP server for AI agents

Works with Claude Desktop, Windsurf IDE, Google ADK, and any MCP-compatible AI

Features

• Portfolio Optimization - Calculate optimal weights using Black-Litterman model
• Investor Views - Express views like "AAPL will return 10%" or "NVDA will outperform MSFT"
• Backtesting - Validate strategies with historical data
• VaR Warnings - Auto-warn on overly optimistic predictions using EGARCH model
• Multiple Assets - S&P 500, NASDAQ 100, ETF, Crypto, and custom data support

---

Quick Start (Claude Desktop)

Step 1: Find uvx path

Run in terminal:

which uvx
# Example output: /Users/USERNAME/.local/bin/uvx

If uvx is not installed: curl -LsSf https://astral.sh/uv/install.sh | sh

Step 2: Configure Claude Desktop

Config file location:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json

File content (replace with your uvx path):

{
  "mcpServers": {
    "black-litterman": {
      "command": "/Users/USERNAME/.local/bin/uvx",
      "args": ["black-litterman-mcp"]
    }
  }
}

Step 3: Restart Claude Desktop

Cmd+Q (macOS) or fully quit and restart

Step 4: Use

Ask Claude:

"Optimize a portfolio with AAPL, MSFT, GOOGL. I think AAPL will return 10%."

First run: S&P 500 data auto-downloads (~30 seconds)

Tip: Want charts or dashboards? Just ask: "Show me a dashboard with the results" or "Create a visualization of the portfolio weights"

Example Use Cases

Try these prompts with Claude:

Basic Optimization + Visualization

"Optimize a portfolio with AAPL, MSFT, GOOGL. I think NVDA will outperform AAPL by 20%, confidence 0.8. Show me a dashboard."

Backtesting with Benchmark

"Backtest my portfolio for 3 years and compare with SPY."

Strategy Comparison

"Compare buy_and_hold, passive_rebalance, and risk_managed strategies for this portfolio."

Correlation Analysis

"Analyze the correlation between NVDA, AMD, and INTC."

Sensitivity Analysis

"Create a portfolio with AAPL and MSFT. I expect AAPL to return 15%. Run sensitivity analysis with confidence levels 0.3, 0.5, 0.7, 0.9."

---

Other Installation Methods

Windsurf IDE

.windsurf/mcp_config.json:

{
  "mcpServers": {
    "black-litterman": {
      "command": "/Users/USERNAME/.local/bin/uvx",
      "args": ["black-litterman-mcp"]
    }
  }
}

From Source (Developers)

git clone https://github.com/irresi/bl-view-mcp.git
cd bl-view-mcp
make install
make download-data  # S&P 500 data
make test-simple

Docker

docker build -t bl-mcp .
docker run -p 5000:5000 -v $(pwd)/data:/app/data bl-mcp

Web UI (Testing)

# Terminal 1: MCP server
make server-http

# Terminal 2: Web UI
make web-ui

Open http://localhost:8000 in browser

---

Supported Datasets

Dataset	Tickers	Description
snp500	~500	S&P 500 constituents (default)
nasdaq100	~100	NASDAQ 100 constituents
etf	~130	Popular ETFs
crypto	~100	Cryptocurrencies
custom	-	User-uploaded data

PyPI install: S&P 500 data auto-downloads on first run

Source install: Download additional datasets manually

make download-data       # S&P 500 (default)
make download-nasdaq100  # NASDAQ 100
make download-etf        # ETF
make download-crypto     # Crypto

---

MCP Tools

optimize_portfolio_bl

Calculate optimal portfolio weights using Black-Litterman model.

optimize_portfolio_bl(
    tickers=["AAPL", "MSFT", "GOOGL"],
    period="1Y",
    views={"P": [{"AAPL": 1}], "Q": [0.10]},  # AAPL expected 10% return
    confidence=0.7,
    investment_style="balanced"  # aggressive / balanced / conservative
)

Views examples:

# Absolute view: "AAPL will return 10%"
views = {"P": [{"AAPL": 1}], "Q": [0.10]}

# Relative view: "NVDA will outperform AAPL by 20%"
views = {"P": [{"NVDA": 1, "AAPL": -1}], "Q": [0.20]}

VaR Warning: When predicted returns exceed 40%, EGARCH-based VaR analysis is automatically included in the warnings field.

backtest_portfolio

Validate portfolio strategy with historical data.

backtest_portfolio(
    tickers=["AAPL", "MSFT", "GOOGL"],
    weights={"AAPL": 0.4, "MSFT": 0.35, "GOOGL": 0.25},
    period="3Y",
    strategy="passive_rebalance",  # buy_and_hold / passive_rebalance / risk_managed
    benchmark="SPY"
)

calculate_var_egarch

Calculate VaR for individual stocks using EGARCH(1,1) model.

calculate_var_egarch(
    ticker="NVDA",
    period="3Y",
    confidence_level=0.95
)

upload_price_data

Upload external data (international stocks, custom assets, etc.).

upload_price_data(
    ticker="005930.KS",  # Samsung Electronics
    prices=[
        {"date": "2024-01-02", "close": 78000.0},
        {"date": "2024-01-03", "close": 78500.0},
        ...
    ],
    source="custom"
)

upload_price_data_from_file

Load price data from CSV/Parquet files.

upload_price_data_from_file(
    ticker="CUSTOM_INDEX",
    file_path="/path/to/data.csv",
    date_column="Date",
    close_column="Close"
)

list_available_tickers

Query available tickers.

list_available_tickers(search="AAPL")        # Search
list_available_tickers(dataset="snp500")     # S&P 500 only
list_available_tickers(dataset="custom")     # Custom data

---

Documentation

Document	Description
QUICKSTART.md	5-minute start guide
CONTRIBUTING.md	Developer guide
TESTING.md	Testing guide
docs/WINDSURF_SETUP.md	Windsurf IDE setup
docs/ARCHITECTURE.md	Technical architecture

---

Tech Stack

• MCP Server: FastMCP
• Optimization: PyPortfolioOpt
• Risk Model: arch (EGARCH)
• Data: yfinance, ccxt (crypto)

---

License

MIT License - LICENSE

---

Troubleshooting

"spawn uvx ENOENT" / "uv binary not found"

Claude Desktop may not recognize system PATH. Use absolute path:

which uvx
# Use the output path in config

"Data file not found"

Source install:

make download-data

PyPI install: Auto-downloads on first run (~30 seconds).

"uv: command not found"

curl -LsSf https://astral.sh/uv/install.sh | sh

Need more help?

• GitHub Issues
• QUICKSTART.md