QuantWorlds

Working Security A

com.quantworlds.api/quantworldsv1.0.0 Domain verified

Option, backtest, portfolio, and pairs checks for agents.

Finance & Payments

Watch

Registry entry

Open in the registry

{
  "_meta": {
    "io.modelcontextprotocol.registry/official": {
      "status": "active",
      "isLatest": true,
      "updatedAt": "2026-11-14T11:28:27.012535Z",
      "publishedAt": "2026-11-14T11:28:27.012535Z",
      "statusChangedAt": "2026-11-14T11:28:27.012535Z"
    }
  },
  "server": {
    "name": "com.quantworlds.api/quantworlds",
    "title": "QuantWorlds",
    "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
    "remotes": [
      {
        "url": "https://api.quantworlds.com/mcp",
        "type": "streamable-http"
      },
      {
        "url": "https://api.quantworlds.com/sse",
        "type": "sse"
      }
    ],
    "version": "1.0.0",
    "description": "Option, backtest, portfolio, and pairs checks for agents."
  }
}

Maintain this server? Claim it

Try it

Call this server's tools from your browser. Nothing to install.

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

instant_signal_backtest

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.

pricesarray, required

raw_signalsarray, required

fee_bpsnumber

trade_size_usdnumber

order_book_depth_usdnumber

trials_tested_by_agentinteger

This tool isn't marked read-only, so it may change something on the server or in an account you connected.

I understand, run it anyway

Install

Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.

One click: Add to Cursor Add to VS Code Add to LM Studio Add to Goose

Run in a terminal

claude mcp add --transport http quantworlds https://api.quantworlds.com/mcp

Tools (4)

instant_signal_backtest

Argument	Type	Description
prices*	array
fee_bps	number
raw_signals*	array
trade_size_usd	number
order_book_depth_usd	number
trials_tested_by_agent	integer

Input schema (JSON)

{
  "type": "object",
  "title": "mcp_instant_signal_backtestArguments",
  "required": [
    "prices",
    "raw_signals"
  ],
  "properties": {
    "prices": {
      "type": "array",
      "items": {
        "type": "number"
      },
      "title": "Prices"
    },
    "fee_bps": {
      "type": "number",
      "title": "Fee Bps",
      "default": 2
    },
    "raw_signals": {
      "type": "array",
      "items": {
        "type": "number"
      },
      "title": "Raw Signals"
    },
    "trade_size_usd": {
      "type": "number",
      "title": "Trade Size Usd",
      "default": 50000
    },
    "order_book_depth_usd": {
      "type": "number",
      "title": "Order Book Depth Usd",
      "default": 500000
    },
    "trials_tested_by_agent": {
      "type": "integer",
      "title": "Trials Tested By Agent",
      "default": 10
    }
  }
}

microstructure_coint_test

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.

Argument	Type	Description
series_x*	array
series_y*	array
ask_volumes	any
bid_volumes	any

Input schema (JSON)

{
  "type": "object",
  "title": "mcp_microstructure_coint_testArguments",
  "required": [
    "series_y",
    "series_x"
  ],
  "properties": {
    "series_x": {
      "type": "array",
      "items": {
        "type": "number"
      },
      "title": "Series X"
    },
    "series_y": {
      "type": "array",
      "items": {
        "type": "number"
      },
      "title": "Series Y"
    },
    "ask_volumes": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "number"
          }
        },
        {
          "type": "null"
        }
      ],
      "title": "Ask Volumes",
      "default": null
    },
    "bid_volumes": {
      "anyOf": [
        {
          "type": "array",
          "items": {
            "type": "number"
          }
        },
        {
          "type": "null"
        }
      ],
      "title": "Bid Volumes",
      "default": null
    }
  }
}

options_surface_pricer

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.

Argument	Type	Description
spot*	number
strikes*	array
iv_array*	array
is_american	boolean
option_type	string
dividend_yield*	number
risk_free_rate*	number
time_to_expiry_years*	number

Input schema (JSON)

{
  "type": "object",
  "title": "mcp_options_surface_pricerArguments",
  "required": [
    "spot",
    "strikes",
    "time_to_expiry_years",
    "risk_free_rate",
    "dividend_yield",
    "iv_array"
  ],
  "properties": {
    "spot": {
      "type": "number",
      "title": "Spot"
    },
    "strikes": {
      "type": "array",
      "items": {
        "type": "number"
      },
      "title": "Strikes"
    },
    "iv_array": {
      "type": "array",
      "items": {
        "type": "number"
      },
      "title": "Iv Array"
    },
    "is_american": {
      "type": "boolean",
      "title": "Is American",
      "default": true
    },
    "option_type": {
      "type": "string",
      "title": "Option Type",
      "default": "call"
    },
    "dividend_yield": {
      "type": "number",
      "title": "Dividend Yield"
    },
    "risk_free_rate": {
      "type": "number",
      "title": "Risk Free Rate"
    },
    "time_to_expiry_years": {
      "type": "number",
      "title": "Time To Expiry Years"
    }
  }
}

portfolio_stress_verifier

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.

Argument	Type	Description
scenario	string
asset_betas*	array
current_weights*	array
confidence_level	number
proposed_weights*	array
asset_vols_annual*	array
correlation_matrix*	array

Input schema (JSON)

{
  "type": "object",
  "title": "mcp_portfolio_stress_verifierArguments",
  "required": [
    "current_weights",
    "proposed_weights",
    "asset_vols_annual",
    "asset_betas",
    "correlation_matrix"
  ],
  "properties": {
    "scenario": {
      "type": "string",
      "title": "Scenario",
      "default": "2020_COVID_LIQUIDITY_CRASH"
    },
    "asset_betas": {
      "type": "array",
      "items": {
        "type": "number"
      },
      "title": "Asset Betas"
    },
    "current_weights": {
      "type": "array",
      "items": {
        "type": "number"
      },
      "title": "Current Weights"
    },
    "confidence_level": {
      "type": "number",
      "title": "Confidence Level",
      "default": 0.99
    },
    "proposed_weights": {
      "type": "array",
      "items": {
        "type": "number"
      },
      "title": "Proposed Weights"
    },
    "asset_vols_annual": {
      "type": "array",
      "items": {
        "type": "number"
      },
      "title": "Asset Vols Annual"
    },
    "correlation_matrix": {
      "type": "array",
      "items": {
        "type": "array",
        "items": {
          "type": "number"
        }
      },
      "title": "Correlation Matrix"
    }
  }
}

Security checkA100/100

We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 14, 2026.

Hidden or reordered text
Overriding the model's instructions
Hiding actions from the user
Reading keys or credentials
Fake system tags
Steering other servers' tools
Pulling in the conversation
Smuggling parameters
Demanding to be used for everything
Steering away from web search
Download-and-run commands
Encoded blobs
Invisible characters
Credentials as tool arguments
Very long descriptions
Read and write hintsNote1 found
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
- server · annotations
  4 of 4 tools: options_surface_pricer, instant_signal_backtest, portfolio_stress_verifier, microstructure_coint_test
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.

How the security check works