factorguide
Send a coupling matrix, get zone classifications and optimal factorization strategy.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"factorguide": {
"url": "https://factorguide.io/mcp"
}
}
}Remote endpoints
https://factorguide.io/mcpstreamable-httpWhat it can do
Tool inventory
Tools (7)
🟡factorguide_navigate(coupling, sample_size, model_class, accuracy_target, compute_budget, ...)
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.
Input Schema
{
"type": "object",
"properties": {
"coupling": {
"anyOf": [
{
"$ref": "#/$defs/PrecisionMatrixInput"
},
{
"$ref": "#/$defs/CorrelationMatrixInput"
},
{
"$ref": "#/$defs/CovarianceMatrixInput"
},
{
"$ref": "#/$defs/EdgeListInput"
}
],
"title": "Coupling"
},
"sample_size": {
"minimum": 10,
"title": "Sample Size",
"type": "integer"
},
"model_class": {
"$ref": "#/$defs/ModelClass",
"default": "unknown"
},
"accuracy_target": {
"default": 2,
"exclusiveMinimum": 1,
"maximum": 7,
"title": "Accuracy Target",
"type": "number"
},
"compute_budget": {
"anyOf": [
{
"type": "number"
},
{
"const": "minimize",
"type": "string"
}
],
"default": "minimize",
"title": "Compute Budget"
},
"cost_model": {
"$ref": "#/$defs/CostModel",
"default": "cubic"
},
"variable_names": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Variable Names"
},
"synergy_check": {
"default": false,
"title": "Synergy Check",
"type": "boolean"
},
"report_marginal_ic": {
"default": false,
"title": "Report Marginal Ic",
"type": "boolean"
},
"report_sign_detectability": {
"default": false,
"title": "Report Sign Detectability",
"type": "boolean"
},
"task_type": {
"$ref": "#/$defs/TaskType",
"default": "inference"
},
"distribution_diagnostics": {
"anyOf": [
{
"$ref": "#/$defs/DistributionDiagnostics"
},
{
"type": "null"
}
],
"default": null
},
"encoding_label": {
"anyOf": [
{
"maxLength": 128,
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Encoding Label"
}
},
"required": [
"coupling",
"sample_size"
],
"$defs": {
"CorrelationMatrixInput": {
"properties": {
"correlation_matrix": {
"items": {
"items": {
"type": "number"
},
"type": "array"
},
"title": "Correlation Matrix",
"type": "array"
}
},
"required": [
"correlation_matrix"
],
"title": "CorrelationMatrixInput",
"type": "object"
},
"CostModel": {
"enum": [
"cubic",
"quadratic",
"linear",
"information_cost"
],
"title": "CostModel",
"type": "string"
},
"CovarianceMatrixInput": {
"properties": {
"covariance_matrix": {
"items": {
"items": {
"type": "number"
},
"type": "array"
},
"title": "Covariance Matrix",
"type": "array"
}
},
"required": [
"covariance_matrix"
],
"title": "CovarianceMatrixInput",
"type": "object"
},
"DistributionDiagnostics": {
"properties": {
"excess_kurtosis": {
"anyOf": [
{
"items": {
"type": "number"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Excess Kurtosis"
},
"skewness": {
"anyOf": [
{
"items": {
"type": "number"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Skewness"
},
"spearman_rank_correlation": {
"anyOf": [
{
"items": {
"items": {
"type": "number"
},
"type": "array"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Spearman Rank Correlation"
}
},
"title": "DistributionDiagnostics",
"type": "object"
},
"EdgeListInput": {
"properties": {
"edge_list": {
"items": {},
"title": "Edge List",
"type": "array"
},
"n": {
"minimum": 2,
"title": "N",
"type": "integer"
}
},
"required": [
"edge_list",
"n"
],
"title": "EdgeListInput",
"type": "object"
},
"ModelClass": {
"enum": [
"filtering",
"hierarchical",
"deep_hierarchy",
"graphical_model",
"gp",
"vae",
"unknown",
"constitutive",
"inductive"
],
"title": "ModelClass",
"type": "string"
},
"PrecisionMatrixInput": {
"properties": {
"precision_matrix": {
"items": {
"items": {
"type": "number"
},
"type": "array"
},
"title": "Precision Matrix",
"type": "array"
}
},
"required": [
"precision_matrix"
],
"title": "PrecisionMatrixInput",
"type": "object"
},
"TaskType": {
"enum": [
"inference",
"control"
],
"title": "TaskType",
"type": "string"
}
},
"title": "NavigateRequest"
}⚪factorguide_diagnose(i, j, coupling_value, sample_size, variance_i, ...)
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.
Input Schema
{
"type": "object",
"properties": {
"i": {
"type": "string",
"description": "First variable name"
},
"j": {
"type": "string",
"description": "Second variable name"
},
"coupling_value": {
"type": "number",
"description": "IC or coupling value"
},
"sample_size": {
"type": "integer",
"minimum": 10
},
"variance_i": {
"type": "number"
},
"variance_j": {
"type": "number"
}
},
"required": [
"i",
"j",
"coupling_value",
"sample_size"
]
}🟡factorguide_submit_payment(tx_hash, chain)
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.
Input Schema
{
"type": "object",
"properties": {
"tx_hash": {
"type": "string",
"description": "On-chain transaction hash"
},
"chain": {
"type": "string",
"description": "Chain identifier, e.g. 'eip155:8453' or 'tempo:4217'"
}
},
"required": [
"tx_hash",
"chain"
]
}🟢factorguide_report_outcome(prediction_hash, approach_taken, ess_ratio, psis_khat, log_lik_gap, ...)
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.
Input Schema
{
"type": "object",
"properties": {
"prediction_hash": {
"title": "Prediction Hash",
"type": "string"
},
"approach_taken": {
"$ref": "#/$defs/ApproachTaken"
},
"ess_ratio": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Ess Ratio"
},
"psis_khat": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Psis Khat"
},
"log_lik_gap": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Log Lik Gap"
},
"actual_mse_ratio": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Actual Mse Ratio"
},
"n_replications": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "N Replications"
},
"runtime_seconds": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Runtime Seconds"
}
},
"required": [
"prediction_hash",
"approach_taken"
],
"$defs": {
"ApproachTaken": {
"enum": [
"factorized",
"structured",
"hybrid"
],
"title": "ApproachTaken",
"type": "string"
}
},
"title": "OutcomeReport"
}🟢factorguide_explain(prediction_hash)
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.
Input Schema
{
"type": "object",
"properties": {
"prediction_hash": {
"type": "string",
"description": "prediction_hash from a previous navigate response"
}
},
"required": [
"prediction_hash"
]
}⚪factorguide_regime_detect
Detect coupling regime changes in time series via windowed IC. Specification pending — v1.1 target.
Input Schema
{
"type": "object",
"properties": {}
}⚪factorguide_synergy_detect(walsh_coefficients, n_variables, transform_method, n_samples, ic_matrix_ref)
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.
Input Schema
{
"type": "object",
"properties": {
"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"
}
}
}
}
}
},
"n_variables": {
"type": "integer"
},
"transform_method": {
"type": "string",
"enum": [
"exact",
"sampled"
]
},
"n_samples": {
"type": [
"integer",
"null"
]
},
"ic_matrix_ref": {
"type": "string"
}
}
}Community
Evidence