Factorguide

Working · 4.8 s

io.factorguide/factorguidev1.2.1 Domain verified

Send a coupling matrix, get zone classifications and optimal factorization strategy.

Research & Knowledge

Source Registry entry

Maintain this server? Claim it

Try it

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

https://factorguide.io/mcp

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.

factorguide_diagnose

Quick single-pair diagnostic. IC with risk prediction for both model classes. Include variances for sign detectability. Requires X-Wallet header with your EVM wallet address (0x...). First 5 queries are free trial.

istring, required

First variable name

jstring, required

Second variable name

sample_sizeinteger, required

coupling_valuenumber, required

IC or coupling value

variance_inumber

variance_jnumber

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

Tools (7)

factorguide_diagnose

Argument	Type	Description
i*	string	First variable name
j*	string	Second variable name
variance_i	number
variance_j	number
sample_size*	integer
coupling_value*	number	IC or coupling value

Input schema (JSON)

{
  "type": "object",
  "required": [
    "i",
    "j",
    "coupling_value",
    "sample_size"
  ],
  "properties": {
    "i": {
      "type": "string",
      "description": "First variable name"
    },
    "j": {
      "type": "string",
      "description": "Second variable name"
    },
    "variance_i": {
      "type": "number"
    },
    "variance_j": {
      "type": "number"
    },
    "sample_size": {
      "type": "integer",
      "minimum": 10
    },
    "coupling_value": {
      "type": "number",
      "description": "IC or coupling value"
    }
  }
}

factorguide_explain

Plain-language explanation of a previous navigate response, including wave mechanics grounding for observational cost guidance. Requires a prediction_hash from a prior factorguide_navigate call. Consumes 1 query allocation. Available for starter and professional tiers. Requires X-Wallet header with your EVM wallet address (0x...). First 5 queries are free trial.

Argument	Type	Description
prediction_hash*	string	prediction_hash from a previous navigate response

Input schema (JSON)

{
  "type": "object",
  "required": [
    "prediction_hash"
  ],
  "properties": {
    "prediction_hash": {
      "type": "string",
      "description": "prediction_hash from a previous navigate response"
    }
  }
}

factorguide_navigate

Map the factorization terrain of your model. Send coupling structure (precision matrix preferred for n>2; covariance matrix recommended if sign or CC information is needed) and receive a block-diagonal strategy with calibrated risk prediction. Answers: 'How should I factorize, and what will it cost me?' Optional: set report_sign_detectability=true to get sign(ρ) for high-leverage pairs at no additional cost when variance ratio > 20. Requires X-Wallet header with your EVM wallet address (0x...). First 5 queries are free trial.

Argument	Type	Description
coupling*	any
task_type	any
cost_model	any
model_class	any
sample_size*	integer
synergy_check	boolean
compute_budget	any
encoding_label	any
variable_names	any

factorguide_regime_detect

Detect coupling regime changes in time series via windowed IC. Specification pending — v1.1 target.

No arguments.

Input schema (JSON)

{
  "type": "object",
  "properties": {}
}

factorguide_report_outcome

Complete the prediction loop — report inference diagnostics so future predictions improve. After running the approach FactorGuide recommended, return your ESS ratio, PSIS-khat, or log-likelihood gap. Zero additional computation required. Does not consume a query allocation.

Argument	Type	Description
ess_ratio	any
psis_khat	any
log_lik_gap	any
approach_taken*	any
n_replications	any
prediction_hash*	string
runtime_seconds	any
actual_mse_ratio	any

Input schema (JSON)

{
  "type": "object",
  "$defs": {
    "ApproachTaken": {
      "enum": [
        "factorized",
        "structured",
        "hybrid"
      ],
      "type": "string",
      "title": "ApproachTaken"
    }
  },
  "title": "OutcomeReport",
  "required": [
    "prediction_hash",
    "approach_taken"
  ],
  "properties": {
    "ess_ratio": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "title": "Ess Ratio",
      "default": null
    },
    "psis_khat": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "title": "Psis Khat",
      "default": null
    },
    "log_lik_gap": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "title": "Log Lik Gap",
      "default": null
    },
    "approach_taken": {
      "$ref": "#/$defs/ApproachTaken"
    },
    "n_replications": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "title": "N Replications",
      "default": null
    },
    "prediction_hash": {
      "type": "string",
      "title": "Prediction Hash"
    },
    "runtime_seconds": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "title": "Runtime Seconds",
      "default": null
    },
    "actual_mse_ratio": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "title": "Actual Mse Ratio",
      "default": null
    }
  }
}

factorguide_submit_payment

Submit payment proof after sending stablecoins to a FactorGuide wallet address. For x402: provide tx_hash and chain. For MPP: use in-band Authorization header instead — no separate submission needed.

Argument	Type	Description
chain*	string	Chain identifier, e.g. 'eip155:8453' or 'tempo:4217'
tx_hash*	string	On-chain transaction hash

Input schema (JSON)

{
  "type": "object",
  "required": [
    "tx_hash",
    "chain"
  ],
  "properties": {
    "chain": {
      "type": "string",
      "description": "Chain identifier, e.g. 'eip155:8453' or 'tempo:4217'"
    },
    "tx_hash": {
      "type": "string",
      "description": "On-chain transaction hash"
    }
  }
}

factorguide_synergy_detect

Detect hidden synergistic structure via Walsh-Hadamard spectral analysis. Accepts pre-computed Walsh coefficients — agent performs the transform locally and sends only the spectral summary. Specification pending — v1.1 target.

Argument	Type	Description
n_samples	integer \| null
n_variables	integer
ic_matrix_ref	string
transform_method	string
walsh_coefficients	object

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "n_samples": {
      "type": [
        "integer",
        "null"
      ]
    },
    "n_variables": {
      "type": "integer"
    },
    "ic_matrix_ref": {
      "type": "string"
    },
    "transform_method": {
      "enum": [
        "exact",
        "sampled"
      ],
      "type": "string"
    },
    "walsh_coefficients": {
      "type": "object",
      "properties": {
        "order_0": {
          "type": "number"
        },
        "order_1": {
          "type": "array",
          "items": {
            "type": "number"
          }
        },
        "order_2": {
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "pair": {
                "type": "array",
                "items": {
                  "type": "integer"
                }
              },
              "coefficient": {
                "type": "number"
              }
            }
          }
        },
        "order_3": {
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "triple": {
                "type": "array",
                "items": {
                  "type": "integer"
                }
              },
              "coefficient": {
                "type": "number"
              }
            }
          }
        }
      }
    }
  }
}

{ "type": "object", "$defs": { "TaskType": { "enum": [ "inference", "control" ], "type": "string", "title": "TaskType" }, "CostModel": { "enum": [ "cubic", "quadratic", "linear", "information_cost" ], "type": "string", "title": "CostModel" }, "ModelClass": { "enum": [ "filtering", "hierarchical", "deep_hierarchy", "graphical_model", "gp", "vae", "unknown", "constitutive", "inductive" ], "type": "string", "title": "ModelClass" }, "EdgeListInput": { "type": "object", "title": "EdgeListInput", "required": [ "edge_list", "n" ], "properties": { "n": { "type": "integer", "title": "N", "minimum": 2 }, "edge_list": { "type": "array", "items": {}, "title": "Edge List" } } }, "PrecisionMatrixInput": { "type": "object", "title": "PrecisionMatrixInput", "required": [ "precision_matrix" ], "properties": { "precision_matrix": { "type": "array", "items": { "type": "array", "items": { "type": "number" } }, "title": "Precision Matrix" } } }, "CovarianceMatrixInput": { "type": "object", "title": "CovarianceMatrixInput", "required": [ "covariance_matrix" ], "properties": { "covariance_matrix": { "type": "array", "items": { "type": "array", "items": { "type": "number" } }, "title": "Covariance Matrix" } } }, "CorrelationMatrixInput": { "type": "object", "title": "CorrelationMatrixInput", "required": [ "correlation_matrix" ], "properties": { "correlation_matrix": { "type": "array", "items": { "type": "array", "items": { "type": "number" } }, "title": "Correlation Matrix" } } }, "DistributionDiagnostics": { "type": "object", "title": "DistributionDiagnostics", "properties": { "skewness": { "anyOf": [ { "type": "array", "items": { "type": "number" } }, { "type": "null" } ], "title": "Skewness", "default": null }, "excess_kurtosis": { "anyOf": [ { "type": "array", "items": { "type": "number" } }, { "type": "null" } ], "title": "Excess Kurtosis", "default": null }, "spearman_rank_correlation": { "anyOf": [ { "type": "array", "items": { "type": "array", "items": { "type": "number" } } }, { "type": "null" } ], "title": "Spearman Rank Correlation", "default": null } } } }, "title": "NavigateRequest", "required": [ "coupling", "sample_size" ], "properties": { "coupling": { "anyOf": [ { "$ref": "#/$defs/PrecisionMatrixInput" }, { "$ref": "#/$defs/CorrelationMatrixInput" }, { "$ref": "#/$defs/CovarianceMatrixInput" }, { "$ref": "#/$defs/EdgeListInput" } ], "title": "Coupling" }, "task_type": { "$ref": "#/$defs/TaskType", "default": "inference" }, "cost_model": { "$ref": "#/$defs/CostModel", "default": "cubic" }, "model_class": { "$ref": "#/$defs/ModelClass", "default": "unknown" }, "sample_size": { "type": "integer", "title": "Sample Size", "minimum": 10 }, "synergy_check": { "type": "boolean", "title": "Synergy Check", "default": false }, "compute_budget": { "anyOf": [ { "type": "number" }, { "type": "string", "const": "minimize" } ], "title": "Compute Budget", "default": "minimize" }, "encoding_label": { "anyOf": [ { "type": "string", "maxLength": 128 }, { "type": "null" } ], "title": "Encoding Label", "default": null }, "variable_names": { "anyOf": [ { "type": "array", "items": { "type": "string" } }, { "type": "null" } ], "title": "Variable Names", "default": null }, "accuracy_target": { "type": "number", "title": "Accuracy Target", "default": 2, "maximum": 7, "exclusiveMinimum": 1 }, "report_marginal_ic": { "type": "boolean", "title": "Report Marginal Ic", "default": false }, "distribution_diagnostics": { "anyOf": [ { "$ref": "#/$defs/DistributionDiagnostics" }, { "type": "null" } ], "default": null }, "report_sign_detectability": { "type": "boolean", "title": "Report Sign Detectability", "default": false } } }