QuantWorlds
Option, backtest, portfolio, and pairs checks for agents.
我该使用它吗
质量与安全性
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高,可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中:
{
"mcpServers": {
"quantworlds": {
"url": "https://api.quantworlds.com/mcp"
}
}
}远程端点
https://api.quantworlds.com/mcpstreamable-httphttps://api.quantworlds.com/ssesse它能做什么
工具清单
工具(4)
⚪options_surface_pricer(spot, strikes, time_to_expiry_years, risk_free_rate, dividend_yield, ...)
Use this instead of estimating Greeks or adding a handmade American premium. European prices are Black-Scholes. American puts, and calls with dividends, use a 128-step binomial tree plus a European control variate. A zero-dividend American call matches the European call. The call surface is checked for arbitrage. Supply spot, strikes, and implied volatilities. Not investment advice.
输入模式
{
"type": "object",
"properties": {
"spot": {
"title": "Spot",
"type": "number"
},
"strikes": {
"items": {
"type": "number"
},
"title": "Strikes",
"type": "array"
},
"time_to_expiry_years": {
"title": "Time To Expiry Years",
"type": "number"
},
"risk_free_rate": {
"title": "Risk Free Rate",
"type": "number"
},
"dividend_yield": {
"title": "Dividend Yield",
"type": "number"
},
"iv_array": {
"items": {
"type": "number"
},
"title": "Iv Array",
"type": "array"
},
"option_type": {
"default": "call",
"title": "Option Type",
"type": "string"
},
"is_american": {
"default": true,
"title": "Is American",
"type": "boolean"
}
},
"required": [
"spot",
"strikes",
"time_to_expiry_years",
"risk_free_rate",
"dividend_yield",
"iv_array"
],
"title": "mcp_options_surface_pricerArguments"
}⚪instant_signal_backtest(prices, raw_signals, fee_bps, order_book_depth_usd, trade_size_usd, ...)
Verify a signal before recommending it. The signal earns the next bar only, so same-bar prices are not treated as tradable. Slippage is one square-root impact from depth and size, not a live order book. Returns Sharpe, Sortino, drawdown, and an approximate deflated Sharpe. Not investment advice.
输入模式
{
"type": "object",
"properties": {
"prices": {
"items": {
"type": "number"
},
"title": "Prices",
"type": "array"
},
"raw_signals": {
"items": {
"type": "number"
},
"title": "Raw Signals",
"type": "array"
},
"fee_bps": {
"default": 2,
"title": "Fee Bps",
"type": "number"
},
"order_book_depth_usd": {
"default": 500000,
"title": "Order Book Depth Usd",
"type": "number"
},
"trade_size_usd": {
"default": 50000,
"title": "Trade Size Usd",
"type": "number"
},
"trials_tested_by_agent": {
"default": 10,
"title": "Trials Tested By Agent",
"type": "integer"
}
},
"required": [
"prices",
"raw_signals"
],
"title": "mcp_instant_signal_backtestArguments"
}⚪portfolio_stress_verifier(current_weights, proposed_weights, asset_vols_annual, asset_betas, correlation_matrix, ...)
Run this before suggesting a rebalance. Normal VaR understates the tail: the report also returns a Student-t copula CVaR and Euler risk contributions. Crisis shocks repair the correlation matrix before applying the shock. Supply weights, vols, betas, and a correlation matrix. Not a historical path replay and not investment advice.
输入模式
{
"type": "object",
"properties": {
"current_weights": {
"items": {
"type": "number"
},
"title": "Current Weights",
"type": "array"
},
"proposed_weights": {
"items": {
"type": "number"
},
"title": "Proposed Weights",
"type": "array"
},
"asset_vols_annual": {
"items": {
"type": "number"
},
"title": "Asset Vols Annual",
"type": "array"
},
"asset_betas": {
"items": {
"type": "number"
},
"title": "Asset Betas",
"type": "array"
},
"correlation_matrix": {
"items": {
"items": {
"type": "number"
},
"type": "array"
},
"title": "Correlation Matrix",
"type": "array"
},
"confidence_level": {
"default": 0.99,
"title": "Confidence Level",
"type": "number"
},
"scenario": {
"default": "2020_COVID_LIQUIDITY_CRASH",
"title": "Scenario",
"type": "string"
}
},
"required": [
"current_weights",
"proposed_weights",
"asset_vols_annual",
"asset_betas",
"correlation_matrix"
],
"title": "mcp_portfolio_stress_verifierArguments"
}🟢microstructure_coint_test(series_y, series_x, bid_volumes, ask_volumes)
Use this for a two-asset pairs check instead of eyeballing a hedge ratio. Returns an Engle-Granger Dickey-Fuller p-value, OLS and Kalman hedge ratios, half-life, and z-score. Two series only. Not a Johansen test and not investment advice.
输入模式
{
"type": "object",
"properties": {
"series_y": {
"items": {
"type": "number"
},
"title": "Series Y",
"type": "array"
},
"series_x": {
"items": {
"type": "number"
},
"title": "Series X",
"type": "array"
},
"bid_volumes": {
"anyOf": [
{
"items": {
"type": "number"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Bid Volumes"
},
"ask_volumes": {
"anyOf": [
{
"items": {
"type": "number"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Ask Volumes"
}
},
"required": [
"series_y",
"series_x"
],
"title": "mcp_microstructure_coint_testArguments"
}社区
证据