QGold

QGold is an MCP server that facilitates natural language querying of commodity and cryptocurrency prices alongside long-term financial withdrawal modeling. It connects AWS Lambda and Amazon DynamoDB storage to an external pricing API to track gold, silver, palladium, copper, bitcoin, and ethereum. Financial analysts, investors, and developers using command-line LLM environments like Amazon Q CLI use QGold to inspect historical or intraday price updates directly through chat prompts. Beyond raw asset quotes, QGold integrates financial projection tools that calculate principal depletion over a thirty-year horizon under variable growth and withdrawal rates. Users can simulate conservative scenarios, such as skipping withdrawals following negative market years, or test random annual return sequences. By standardizing quote retrieval into structured Model Context Protocol endpoints, QGold allows compatible AI clients to run multi-asset portfolio checks and retirement runway evaluations without manual spreadsheet configuration or external dashboard context switching.

Category: Data & Analytics

Tags: asset prices, financial modeling, nlp, withdrawal analysis

Visit QGold

How to install and configure QGold

1. Clone the repository and navigate into the mcp_server directory. 2. Install the required Python dependencies: bash pip install -r requirements.txt 3. Register the MCP server with the Amazon Q CLI: bash q mcp add --name qgold --command python3 4. Open .amazonq/mcp.json and configure the server entry: json { "mcpServers": { "qgold": { "command": "python3", "args": ["server.py"] } } } 5. Authenticate and start the Q CLI session with trusted tool permissions: bash q login q chat --trust-tools=qgold___get_asset_prices,qgold___model_financial_projections

What you can do with QGold

• Retrieve real-time and historical spot prices for precious metals including gold, silver, palladium, and copper using structured date filters. - Query daily cryptocurrency exchange rates for Bitcoin and Ethereum stored in DynamoDB through natural language chat interfaces. - Model thirty-year retirement nest egg trajectories comparing fixed principal withdrawal rates against projected annual portfolio investment yields. - Simulate volatile market returns across extended horizons using randomized growth percentages to evaluate sequence-of-returns portfolio risk. - Test dynamic drawdown strategies that skip annual retirement distributions immediately following portfolio losses to preserve underlying capital.

Key facts

• https://github.com/jcaple/qgold
• Data & Analytics, Finance, Crypto & Payments
• asset prices, financial modeling, nlp, withdrawal analysis

Part of MCP Servers

What can QGold do?

QGold exposes tools for querying commodity and cryptocurrency price data alongside long-term financial modeling calculators. It fetches pricing for gold, silver, palladium, copper, bitcoin, and ethereum stored in DynamoDB, allowing users to query specific date ranges or current quotes. Additionally, it models thirty-year portfolio drawdowns with adjustable withdrawal rates, fixed or randomized growth rates, and rules for skipping withdrawals after down years.

Which MCP clients work with QGold?

QGold is designed and documented for use with the Amazon Q CLI developer environment. However, because it complies with the standard Model Context Protocol specifications using standard Python scripts, it can also be configured with other compatible MCP hosts such as Claude Desktop or Cursor by pointing the client configuration to run python3 server.py within the mcp_server directory.

What assets are supported by QGold?

QGold tracks six specific assets: XAU (Gold), XAG (Silver), XPD (Palladium), HG (Copper), BTC (Bitcoin), and ETH (Ethereum). Price data for these assets is periodically harvested from gold-api.com via scheduled AWS Lambda executions and indexed by date in Amazon DynamoDB for historical comparison and retrieval.

How does QGold handle financial projections?

The model_financial_projections tool calculates principal balances over a thirty-year schedule based on an initial amount, annual growth rate, and target withdrawal percentage. It supports a random growth generator to simulate market volatility and includes a conditional logic flag that skips withdrawals in years following negative portfolio returns.