quantifyme-mcp 0.2.0

Claude MCP server for QuantifyMe — deploy trading strategies from natural language.

quantifyme-mcp

Claude MCP server for QuantifyMe — deploy algorithmic trading strategies from natural language.

Install

# Recommended — isolates the install, no Python version fiddling
pipx install quantifyme-mcp
claude mcp add quantifyme quantifyme-mcp

Or with uvx (no install):

claude mcp add quantifyme uvx quantifyme-mcp

Or plain pip if your default Python is 3.10+:

pip install quantifyme-mcp
claude mcp add quantifyme quantifyme-mcp

Use in Claude

Once registered, ask Claude:

Deploy a strategy that buys EURUSD when RSI hits 30 and sells when it hits 70.

Claude will call the one_shot tool, which generates the strategy code, trains a model on 28 days of OHLC data, and deploys it live. You get a webhook/Telegram-ready URL back.

Environment

• QUANTIFYME_API_KEY — your personal key (optional; anonymous trial key auto-created if unset)
• QUANTIFYME_BASE_URL — override API base (default https://api.quantifyme.ai)

Tools exposed

Tool	Purpose
one_shot	Prompt → generate → train → deploy → live signal URL
list_models	User's trained models with train/test stats
list_deployed	Currently live models
get_trial_key	Anonymous trial key (50 credits, no signup)
generate_strategy	Code-only generation (no training)

License

MIT