_ registry / mcp streamable-http · checked 7h ago

canlicapital-validation-mcp

https://canlicapital.com

Registry code: 69a41fdae8222c1a

api record

Checks whether a backtest's result is real. For one strategy's returns, call audit_backtest, pointing returns_file at the backtest's CSV instead of pasting long series. For a Sharpe found by a search, validate_deflated_sharpe needs how many independent variants were tried and how their Sharpes spread; with every variant's returns, validate_overfitting gives the probability of backtest overfitting. To test a rule on prices, backtest_strategy runs a whole parameter grid and validates the best with the count actually run; summarize_series reads a long series in a hundred words; stress_test and…

endpoint
https://canlicapital.com/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is canlicapital-validation-mcp live?
Yes — it answered the hub's last check (checked 7h ago). It answered 99% of checks over the last 30 days.
Is canlicapital-validation-mcp free to use?
Yes — the hub reached it with no key and no payment.
What tools does canlicapital-validation-mcp have?
18 tools: validate_deflated_sharpe, validate_overfitting, validate_reality_check, validate_paper_evidence, validate_breadth, validate_track_record, validate_backtest_length, validate_haircut_sharpe, ….
Is canlicapital-validation-mcp safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
98.7%

90 days 99.3%· all time 99.3%

latency
268ms

last good check

priced tools
0

of 18 tools

_ answered our checks, 90 days 280 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • unknown → live
_ what it is for
topic
finance & markets
used for
  • audit a backtest
  • compute deflated sharpe ratio
  • estimate probability of backtest overfitting
  • get company financial history
takes → gives
data, documents → data
tools
12 reads
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 18 tools
1 open 17 never probed 1 of 18 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • service_status reads open 15h ago

    Whether the validation API is up, with its quotas; check after a timeout before resubmitting. No key. This verdict is about the series exactly as submitted. The service never saw the data source, its costs, survivorship, or any lookahead in how the series was built.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {},
  "additionalProperties": false
}
    arguments 6 lines
  • validate_deflated_sharpe reads unknown never probed

    Deflated Sharpe ratio: the probability (0 to 1) that the selected strategy's Sharpe beats the best that luck gives across the variants tried, with the probabilistic Sharpe and that luck benchmark. Send the seven statistics or a return series. With every variant's returns use validate_overfitting; luck as a trial count, validate_luck_trials; a multiple-testing haircut, validate_haircut_sharpe. A deflated Sharpe or overfitting probability above or below any threshold is not admission to anything and is not a forecast.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "skew": {
      "type": "number",
      "maximum": 20,
      "minimum": -20,
      "description": "Skewness of returns; 0 if Normal."
    },
    "returns": {
      "type": "array",
      "items": {
        "type": "number"
      },
      "maxItems": 20000,
      "minItems": 2,
      "description": "Periodic returns as fractions (0.01 = 1%), oldest first; replaces the Sharpe, observations, skew and kurtosis."
    },
    "observations": {
      "type": "integer",
      "maximum": 1000000,
      "minimum": 2,
      "description": "Number of return observations."
    },
    "periods_per_year": {
      "type": "number",
      "maximum": 10000,
      "minimum": 1,
      "description": "Periods per year: 252 daily, 365 crypto, 52 weekly, 12 monthly."
    },
    "non_excess_kurtosis": {
      "type": "number",
      "maximum": 100,
      "minimum": 1,
      "description": "Kurtosis, not excess kurtosis; 3 if Normal."
    },
    "observed_sharpe_annualized": {
      "type": "number",
      "maximum": 10,
      "minimum": -10,
      "description": "Annualized Sharpe as observed."
    },
    "effective_independent_trials": {
      "type": "integer",
      "maximum": 10000000,
      "minimum": 2,
      "description": "Independent variants tried before choosing this one."
    },
    "cross_trial_sharpe_sd_annualized": {
      "type": "number",
      "maximum": 10,
      "minimum": 0,
      "description": "Standard deviation of annualized Sharpe across those trials."
    }
  },
  "additionalProperties": false
}
    arguments 58 lines
  • validate_overfitting reads unknown never probed

    Probability of backtest overfitting (0 to 1) by CSCV: how often the in-sample best variant falls below the out-of-sample median. Needs every variant's returns (periods by variants); with summary statistics only, use validate_deflated_sharpe. A deflated Sharpe or overfitting probability above or below any threshold is not admission to anything and is not a forecast.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "matrix"
  ],
  "properties": {
    "seed": {
      "type": "number",
      "description": "Sampling seed; default 42."
    },
    "matrix": {
      "type": "array",
      "items": {
        "type": "array",
        "items": {
          "type": "number"
        },
        "maxItems": 200
      },
      "maxItems": 20000,
      "minItems": 2,
      "description": "Returns as fractions, one row per period, one column per variant."
    },
    "n_splits": {
      "type": "integer",
      "description": "Even number of blocks, at least 2; default 16.",
      "exclusiveMinimum": 0
    },
    "max_combinations": {
      "type": "integer",
      "maximum": 2000,
      "description": "Most splits evaluated, up to 2000 (default).",
      "exclusiveMinimum": 0
    }
  },
  "additionalProperties": false
}
    arguments 38 lines
  • validate_reality_check reads unknown never probed

    Data-snooping tests on every variant a search tried: Hansen's SPA p-value that the best beat the benchmark only by luck, White's Reality Check, and the variants Romano-Wolf StepM finds better. Send all variants tried, not only the winners. A deflated Sharpe or overfitting probability above or below any threshold is not admission to anything and is not a forecast.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "reps": {
      "type": "integer",
      "maximum": 400000,
      "minimum": 500,
      "description": "Bootstrap draws; default 2000."
    },
    "seed": {
      "type": "integer",
      "description": "Sampling seed; default 42."
    },
    "alpha": {
      "type": "number",
      "maximum": 0.5,
      "description": "Familywise error for StepM; default 0.05.",
      "exclusiveMinimum": 0
    },
    "matrix": {
      "type": "array",
      "items": {
        "type": "array",
        "items": {
          "type": "number"
        },
        "maxItems": 200
      },
      "maxItems": 20000,
      "minItems": 30,
      "description": "Returns of every variant the search tried, one row per period, one column per variant."
    },
    "benchmark": {
      "type": "array",
      "items": {
        "type": "number"
      },
      "maxItems": 20000,
      "minItems": 30,
      "description": "Benchmark return per period; default zero."
    },
    "matrix_file": {
      "type": "string",
      "maxLength": 4096,
      "minLength": 1,
      "description": "Path to a CSV or JSON with one numeric column per variant, instead of matrix."
    },
    "block_length": {
      "type": "integer",
      "maximum": 10000,
      "minimum": 1,
      "description": "Mean bootstrap block in periods; default round(n^(1/3))."
    }
  },
  "additionalProperties": false
}
    arguments 57 lines
  • validate_paper_evidence reads unknown never probed

    Checks paper-evidence.v0 structure and disclosures. With CANLI_LOCAL=1, record_file reads an export bundle and journal_file verifies signatures, source hashes and recomputed claims. Without a journal, source facts and signatures are unchecked. Local files are never uploaded. This verdict is about the series exactly as submitted. The service never saw the data source, its costs, survivorship, or any lookahead in how the series was built.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "record": {
      "type": "object",
      "description": "A canli.paper-evidence.v0 record."
    },
    "signature": {
      "type": "object",
      "required": [
        "scheme",
        "public_key",
        "signature"
      ],
      "properties": {
        "scheme": {
          "type": "string",
          "const": "Ed25519"
        },
        "signature": {
          "type": "string",
          "maxLength": 128
        },
        "public_key": {
          "type": "string",
          "maxLength": 64
        }
      },
      "description": "Detached record signature for a signed inline record; requires journal_file.",
      "additionalProperties": false
    },
    "record_file": {
      "type": "string",
      "maxLength": 1000,
      "minLength": 1,
      "description": "Local record or export-bundle JSON path; requires CANLI_LOCAL=1."
    },
    "journal_file": {
      "type": "string",
      "maxLength": 1000,
      "minLength": 1,
      "description": "Local signed journal to recompute and bind; requires CANLI_LOCAL=1."
    }
  },
  "additionalProperties": false
}
    arguments 47 lines
  • validate_breadth reads unknown never probed

    Book Sharpe ceiling from adding sleeves of this quality and correlation, the Sharpe at a sleeve count, and the sleeves a target needs. For portfolio construction; it validates no single strategy. This verdict is about the series exactly as submitted. The service never saw the data source, its costs, survivorship, or any lookahead in how the series was built.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "sleeve_sharpe",
    "average_pairwise_correlation"
  ],
  "properties": {
    "target": {
      "type": "number",
      "description": "Target book Sharpe, for the sleeves it needs.",
      "exclusiveMinimum": 0
    },
    "sleeves": {
      "type": "integer",
      "maximum": 500,
      "minimum": 1,
      "description": "Sleeve count, for that book's Sharpe."
    },
    "sleeve_sharpe": {
      "type": "number",
      "description": "Annualized Sharpe of one sleeve.",
      "exclusiveMinimum": 0
    },
    "average_pairwise_correlation": {
      "type": "number",
      "maximum": 1,
      "minimum": -1,
      "description": "Average correlation between sleeves, -1 to 1."
    }
  },
  "additionalProperties": false
}
    arguments 33 lines
  • validate_track_record reads unknown never probed

    Minimum track record length (observations and years) for an observed Sharpe to beat a benchmark at a confidence level; with observations, the record's probabilistic Sharpe so far. For live or paper records; to size a backtest for its trials, use validate_backtest_length. A deflated Sharpe or overfitting probability above or below any threshold is not admission to anything and is not a forecast.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "observed_sharpe_annualized",
    "periods_per_year",
    "skew",
    "non_excess_kurtosis"
  ],
  "properties": {
    "skew": {
      "type": "number",
      "maximum": 20,
      "minimum": -20,
      "description": "Skewness of returns; 0 if Normal."
    },
    "confidence": {
      "type": "number",
      "description": "Between 0 and 1; default 0.95.",
      "exclusiveMaximum": 1,
      "exclusiveMinimum": 0
    },
    "observations": {
      "type": "integer",
      "maximum": 1000000,
      "minimum": 2,
      "description": "Record length so far, for its probabilistic Sharpe."
    },
    "periods_per_year": {
      "type": "number",
      "maximum": 10000,
      "minimum": 1,
      "description": "Periods per year: 252 daily, 365 crypto, 52 weekly, 12 monthly."
    },
    "non_excess_kurtosis": {
      "type": "number",
      "maximum": 100,
      "minimum": 1,
      "description": "Kurtosis, not excess kurtosis; 3 if Normal."
    },
    "observed_sharpe_annualized": {
      "type": "number",
      "maximum": 10,
      "minimum": -10,
      "description": "Annualized Sharpe as observed."
    },
    "benchmark_sharpe_annualized": {
      "type": "number",
      "maximum": 10,
      "minimum": -10,
      "description": "Annualized Sharpe to beat; default 0."
    }
  },
  "additionalProperties": false
}
    arguments 55 lines
  • validate_backtest_length reads unknown never probed

    Minimum backtest length (years) before the best of N independent trials is not expected to reach a target Sharpe by luck; with backtest_years, the most trials those years allow. For planning a search; once it has a result, use validate_deflated_sharpe. A deflated Sharpe or overfitting probability above or below any threshold is not admission to anything and is not a forecast.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "backtest_years": {
      "type": "number",
      "maximum": 1000,
      "description": "Backtest length in years, for the most trials it allows.",
      "exclusiveMinimum": 0
    },
    "target_sharpe_annualized": {
      "type": "number",
      "maximum": 10,
      "description": "In-sample annualized Sharpe you would call a discovery; default 1.",
      "exclusiveMinimum": 0
    },
    "effective_independent_trials": {
      "type": "integer",
      "maximum": 1000000000,
      "minimum": 2,
      "description": "Independent trials tried (backtests, parameter sets, ideas)."
    }
  },
  "additionalProperties": false
}
    arguments 25 lines
  • validate_haircut_sharpe reads unknown never probed

    Haircut Sharpe for multiple testing (Harvey and Liu 2015): the Sharpe a single test would have needed, by Bonferroni and independent tests, and with the other tests' Sharpes, Holm and BHY. For the probability the Sharpe is real, use validate_deflated_sharpe. A deflated Sharpe or overfitting probability above or below any threshold is not admission to anything and is not a forecast.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "observed_sharpe_annualized",
    "periods_per_year",
    "observations"
  ],
  "properties": {
    "tests": {
      "type": "integer",
      "maximum": 100000000,
      "minimum": 1,
      "description": "Tests run, this one included; gives the Bonferroni and independent-test haircuts."
    },
    "observations": {
      "type": "integer",
      "maximum": 1000000,
      "minimum": 3,
      "description": "Return observations behind the Sharpe."
    },
    "autocorrelation": {
      "type": "number",
      "description": "Lag-1 autocorrelation of returns, -1 to 1; default 0. Corrects the annualized Sharpe (Lo 2002).",
      "exclusiveMaximum": 1,
      "exclusiveMinimum": -1
    },
    "periods_per_year": {
      "type": "number",
      "maximum": 10000,
      "minimum": 1,
      "description": "Periods per year: 252 daily, 365 crypto, 52 weekly, 12 monthly."
    },
    "observed_sharpe_annualized": {
      "type": "number",
      "maximum": 10,
      "description": "Annualized Sharpe as observed.",
      "exclusiveMinimum": 0
    },
    "other_sharpe_ratios_annualized": {
      "type": "array",
      "items": {
        "type": "number",
        "maximum": 10,
        "minimum": -10
      },
      "maxItems": 10000,
      "minItems": 1,
      "description": "Annualized Sharpes of the other tests over the same observations; adds Holm and BHY."
    }
  },
  "additionalProperties": false
}
    arguments 53 lines
  • validate_luck_trials reads unknown never probed

    How many skill-less strategies a search would need for its best to reach this Sharpe by luck (Monte Carlo), and with a trial count, the chance it did. States luck as the best of N random tries; for the probability the Sharpe is real, use validate_deflated_sharpe. A deflated Sharpe or overfitting probability above or below any threshold is not admission to anything and is not a forecast.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "observed_sharpe_annualized",
    "periods_per_year",
    "observations"
  ],
  "properties": {
    "skew": {
      "type": "number",
      "maximum": 100,
      "minimum": -100,
      "description": "Skewness; below -0.5 the reading warns the counts are too generous."
    },
    "observations": {
      "type": "integer",
      "maximum": 1000000,
      "minimum": 3,
      "description": "Return observations behind the Sharpe."
    },
    "autocorrelation": {
      "type": "number",
      "description": "Lag-1 autocorrelation of returns, -1 to 1; default 0. Corrects the annualized Sharpe (Lo 2002).",
      "exclusiveMaximum": 1,
      "exclusiveMinimum": -1
    },
    "periods_per_year": {
      "type": "number",
      "maximum": 10000,
      "minimum": 1,
      "description": "Periods per year: 252 daily, 365 crypto, 52 weekly, 12 monthly."
    },
    "observed_sharpe_annualized": {
      "type": "number",
      "maximum": 20,
      "minimum": -20,
      "description": "Annualized Sharpe as observed."
    },
    "effective_independent_trials": {
      "type": "integer",
      "maximum": 1000000000,
      "minimum": 1,
      "description": "Independent trials tried; adds the chance the best reached this Sharpe by luck."
    }
  },
  "additionalProperties": false
}
    arguments 48 lines
  • audit_backtest reads unknown never probed

    One-call audit of a strategy's returns. Headline: one test whose false-positive rate was measured on nine return shapes (White's Reality Check with variants, luck trials with Lo's correction without). Then deflated Sharpe, minimum track record and, with variants, overfitting and out-of-sample decay, each with its receipt, plus fix_next. Send every variant tried (variants_file) so trials are counted; point returns_file at a CSV instead of pasting. A deflated Sharpe or overfitting probability above or below any threshold is not admission to anything and is not a forecast.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "periods_per_year"
  ],
  "properties": {
    "returns": {
      "type": "array",
      "items": {
        "type": "number"
      },
      "maxItems": 20000,
      "minItems": 2,
      "description": "Periodic returns as fractions (0.01 = 1%), oldest first; replaces the Sharpe, observations, skew and kurtosis."
    },
    "n_splits": {
      "type": "integer",
      "description": "Even number of blocks, at least 2; default 16.",
      "exclusiveMinimum": 0
    },
    "variants": {
      "type": "array",
      "items": {
        "type": "array",
        "items": {
          "type": "number"
        },
        "maxItems": 200
      },
      "maxItems": 20000,
      "minItems": 2,
      "description": "Optional returns of every variant tried (this one included), one row per period, one column per variant; adds the overfitting check."
    },
    "confidence": {
      "type": "number",
      "description": "Between 0 and 1; default 0.95.",
      "exclusiveMaximum": 1,
      "exclusiveMinimum": 0
    },
    "returns_file": {
      "type": "string",
      "maxLength": 4096,
      "minLength": 1,
      "description": "Path to a CSV or JSON of the returns on this machine (not on the hosted endpoint), instead of returns."
    },
    "variants_file": {
      "type": "string",
      "maxLength": 4096,
      "minLength": 1,
      "description": "Path to a CSV or JSON with one numeric column per variant, instead of variants."
    },
    "returns_column": {
      "anyOf": [
        {
          "type": "string",
          "maxLength": 200,
          "minLength": 1
        },
        {
          "type": "integer",
          "minimum": 1
        }
      ],
      "description": "Column name or 1-based position, when returns_file has several numeric columns."
    },
    "periods_per_year": {
      "type": "number",
      "maximum": 10000,
      "minimum": 1,
      "description": "Periods per year: 252 daily, 365 crypto, 52 weekly, 12 monthly."
    },
    "benchmark_sharpe_annualized": {
      "type": "number",
      "maximum": 10,
      "minimum": -10,
      "description": "Annualized Sharpe to beat; default 0."
    },
    "effective_independent_trials": {
      "type": "integer",
      "maximum": 10000000,
      "minimum": 2,
      "description": "Independent variants tried before choosing this one. Optional with variants: counted from them, and the larger number is used."
    },
    "cross_trial_sharpe_sd_annualized": {
      "type": "number",
      "maximum": 10,
      "minimum": 0,
      "description": "Standard deviation of annualized Sharpe across those trials. Optional with variants: measured from them, and the larger is used."
    }
  },
  "additionalProperties": false
}
    arguments 93 lines
  • verify_receipt reads unknown 7h ago

    Verify a receipt offline: its Ed25519 signature against the bundled canlicapital.com key, its output hash and its id. Send an id to fetch it first, or the receipt itself. The receipt is content-hashed, reproducible from the open-source core it names, and signed with Ed25519 by a key published at https://canlicapital.com/.well-known/canli-receipt-keys.json.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "id": {
      "type": "string",
      "pattern": "^[0-9a-f]{24}$",
      "description": "Receipt id from a validation result."
    },
    "receipt": {
      "type": "object",
      "description": "A receipt object, to verify without fetching."
    },
    "include_receipt": {
      "type": "boolean",
      "description": "With id: also return the stored receipt."
    }
  },
  "additionalProperties": false
}
    arguments 20 lines
  • summarize_series unknown 15h ago

    A long price or return series in about 100 words plus fields: growth, risk, dated drawdowns, trend, volatility regime, tails, jumps, stale data. Use instead of reading raw bars. Nothing here is a forecast or advice.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "name": {
      "type": "string",
      "description": "Label for the text."
    },
    "dates": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Optional ISO dates, one per value."
    },
    "prices": {
      "type": "array",
      "items": {
        "type": "number"
      },
      "description": "Prices, oldest first; or returns, or series_file."
    },
    "returns": {
      "type": "array",
      "items": {
        "type": "number"
      },
      "description": "Returns as fractions, oldest first."
    },
    "series_file": {
      "type": "string",
      "description": "CSV or JSON of prices or returns on this machine; local server only."
    },
    "series_kind": {
      "enum": [
        "prices",
        "returns"
      ],
      "type": "string",
      "description": "series_file holds; default prices."
    },
    "series_column": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "integer"
        }
      ],
      "description": "Column name or 1-based position."
    },
    "periods_per_year": {
      "type": "number",
      "description": "252 daily (default), 365 crypto, 52 weekly, 12 monthly."
    },
    "benchmark_returns": {
      "type": "array",
      "items": {
        "type": "number"
      },
      "description": "Same-period benchmark returns; adds beta."
    }
  },
  "additionalProperties": false
}
    arguments 66 lines
  • stress_test unknown 15h ago

    Stress a strategy's returns: bootstrap histories (how often the drawdown limit breaks or Sharpe turns negative) and named crash, volatility, repeat and stuck-position scenarios, with a fragility share. Frequencies over resampled histories are not forecasts of the future.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "seed": {
      "type": "integer",
      "description": "Default 42; reproduces exactly."
    },
    "block": {
      "type": "number",
      "description": "Mean block length; default cube root of n."
    },
    "crash": {
      "type": "number",
      "description": "Crash size, negative; default min(-0.2, 3x worst period).",
      "exclusiveMaximum": 0,
      "exclusiveMinimum": -1
    },
    "paths": {
      "type": "integer",
      "description": "Default 1000."
    },
    "returns": {
      "type": "array",
      "items": {
        "type": "number"
      },
      "description": "Strategy returns as fractions, oldest first."
    },
    "returns_file": {
      "type": "string",
      "description": "CSV or JSON of returns on this machine; local server only."
    },
    "drawdown_limit": {
      "type": "number",
      "description": "Fraction; default 0.2.",
      "exclusiveMaximum": 1,
      "exclusiveMinimum": 0
    },
    "outage_periods": {
      "type": "integer",
      "description": "Stuck periods after the worst; default 5."
    },
    "returns_column": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "integer"
        }
      ],
      "description": "Column name or 1-based position."
    },
    "periods_per_year": {
      "type": "number",
      "description": "252 daily (default), 365 crypto, 52 weekly, 12 monthly."
    },
    "volatility_multiplier": {
      "type": "number",
      "description": "Default 2."
    }
  },
  "additionalProperties": false
}
    arguments 65 lines
  • check_leakage unknown 3d ago

    Does a signal look ahead? plan gives cuts; rerun your code on the first cut rows for each, then compare. Rows that changed used later rows; the result names the pattern and horizon. No code is sent. A pass covers only these cuts: the columns are the caller's, and survivorship, vendor revisions or a leak no cut reaches leave no trace.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "action"
  ],
  "properties": {
    "cuts": {
      "type": "array",
      "items": {
        "type": "integer"
      },
      "description": "compare: plan's cuts."
    },
    "seed": {
      "type": "integer"
    },
    "action": {
      "enum": [
        "plan",
        "compare"
      ],
      "type": "string"
    },
    "columns": {
      "type": "object",
      "description": "compare: {name: {full: [all rows], prefixes: [[first cuts[i] rows], ...]}}, null for missing.",
      "additionalProperties": {
        "type": "object",
        "properties": {}
      }
    },
    "prefixes": {
      "type": "integer",
      "description": "plan: cuts, default 5."
    },
    "tolerance": {
      "type": "number",
      "description": "Default 1e-9."
    },
    "timestamps": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "columns_file": {
      "type": "string",
      "description": "compare, on your machine: a JSON file {cuts, columns} instead."
    },
    "observations": {
      "type": "integer",
      "description": "plan: rows in the series."
    }
  },
  "additionalProperties": false
}
    arguments 57 lines
  • placebo_test unknown never probed

    Does your pipeline find edges in noise? plan writes placebo files (your data's returns in random orders, so nothing is predictable); run the whole pipeline on real.csv and on each, then compare for a p-value that counts every choice it makes. Beating the placebos shows the pipeline finds more in the real order of the returns than in random orders of the same returns; it does not show the edge survives costs, capacity or the future.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "action"
  ],
  "properties": {
    "kind": {
      "enum": [
        "prices",
        "returns"
      ],
      "type": "string",
      "description": "plan: default prices."
    },
    "real": {
      "type": "number",
      "description": "compare: the pipeline's result on the real data."
    },
    "seed": {
      "type": "integer"
    },
    "action": {
      "enum": [
        "plan",
        "compare"
      ],
      "type": "string"
    },
    "method": {
      "enum": [
        "permute",
        "block_permute",
        "stationary_bootstrap"
      ],
      "type": "string"
    },
    "columns": {
      "type": "object",
      "description": "plan: {asset: [values]} instead of data_file.",
      "additionalProperties": {
        "type": "array",
        "items": {
          "type": "number"
        }
      }
    },
    "placebos": {
      "type": "integer",
      "description": "plan: default 19, up to 199."
    },
    "data_file": {
      "type": "string",
      "description": "plan, on your machine: CSV or JSON, a column per asset, dates optional."
    },
    "lower_is_better": {
      "type": "boolean"
    },
    "placebo_results": {
      "type": "array",
      "items": {
        "type": "number"
      },
      "description": "compare: its result on each placebo, in file order."
    }
  },
  "additionalProperties": false
}
    arguments 68 lines
  • check_feasibility unknown 7h ago

    Check a trading plan before it trades: broker order-rate and minimum-order limits, 2026 US day-trading rules, square-root market impact with crowding, and the capital where costs eat the return. Checks the plan as described against published broker limits and a market-impact model; it never contacts a broker or sees an account.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "capital_usd",
    "orders_per_rebalance",
    "rebalances_per_year",
    "turnover_per_year",
    "adv_usd",
    "daily_volatility"
  ],
  "properties": {
    "broker": {
      "enum": [
        "alpaca",
        "ibkr",
        "other"
      ],
      "type": "string",
      "description": "Default other."
    },
    "copies": {
      "type": "integer",
      "description": "Agents trading the same signal at once; default 1."
    },
    "account": {
      "enum": [
        "cash",
        "margin"
      ],
      "type": "string"
    },
    "adv_usd": {
      "type": "number",
      "description": "Daily dollar volume of a typical holding."
    },
    "asset_class": {
      "enum": [
        "us_equity",
        "crypto",
        "futures",
        "fx",
        "options"
      ],
      "type": "string"
    },
    "capital_usd": {
      "type": "number"
    },
    "daily_volatility": {
      "type": "number",
      "maximum": 1,
      "description": "Of a typical holding, e.g. 0.02."
    },
    "turnover_per_year": {
      "type": "number",
      "minimum": 0,
      "description": "Buys plus sells a year / capital."
    },
    "impact_coefficient": {
      "type": "number",
      "description": "Square-root law Y; default 1."
    },
    "rebalances_per_year": {
      "type": "number"
    },
    "spread_and_fees_bps": {
      "type": "number",
      "minimum": 0,
      "description": "Per trade; default 0."
    },
    "orders_per_rebalance": {
      "type": "integer"
    },
    "expected_gross_return": {
      "type": "number",
      "minimum": -1,
      "description": "Annual, before costs; adds capacity."
    },
    "minutes_per_rebalance": {
      "type": "number",
      "description": "Default 1."
    },
    "orders_per_minute_limit": {
      "type": "number",
      "description": "If the broker's is not on file."
    }
  },
  "additionalProperties": false
}
    arguments 90 lines
  • backtest_strategy unknown 7h ago

    Backtest a rule on your prices over a whole parameter grid, then validate the best with the count of variants actually run: deflated Sharpe, overfitting probability, minimum track record, vs buy and hold, after costs. A backtest, deflated or not, is not a forecast and not advice.

    mcp-tool

    {
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "family"
  ],
  "properties": {
    "grid": {
      "type": "object",
      "description": "Values per parameter, e.g. {\"fast\":[10,20],\"slow\":[50,200]}; every valid combination runs (max 200).",
      "additionalProperties": {
        "anyOf": [
          {
            "type": "number"
          },
          {
            "type": "array",
            "items": {
              "type": "number"
            }
          }
        ]
      }
    },
    "dates": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Optional ISO dates, one per value."
    },
    "family": {
      "enum": [
        "buy_and_hold",
        "sma_cross",
        "momentum",
        "mean_reversion",
        "breakout"
      ],
      "type": "string",
      "description": "sma_cross (fast, slow), momentum (lookback, skip), mean_reversion (window, entry_z), breakout (lookback), buy_and_hold."
    },
    "prices": {
      "type": "array",
      "items": {
        "type": "number"
      },
      "description": "Prices, oldest first."
    },
    "cost_bps": {
      "type": "number",
      "minimum": 0,
      "description": "Cost per unit of turnover, bps; default 5."
    },
    "allow_short": {
      "type": "boolean",
      "description": "Short instead of flat; default false."
    },
    "prices_file": {
      "type": "string",
      "description": "CSV or JSON of prices on this machine; local server only."
    },
    "prices_column": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "integer"
        }
      ],
      "description": "Column name or 1-based position."
    },
    "periods_per_year": {
      "type": "number",
      "description": "252 daily (default), 365 crypto, 52 weekly, 12 monthly."
    }
  },
  "additionalProperties": false
}
    arguments 80 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 69a41fdae8222c1a.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/69a41fdae8222c1a/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/69a41fdae8222c1a/badge.svg)](https://brick.blue/agent/69a41fdae8222c1a?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.