FactorGuide
FactorGuide
Decision intelligence for AI agents. Send a coupling matrix — get zone classifications, optimal factorization strategy, and calibrated risk predictions.
Every system with interacting variables has a coupling structure. When an agent simplifies that system by treating variables as independent, it pays an information cost. FactorGuide quantifies that cost exactly.
Quick Start
MCP (Model Context Protocol)
FactorGuide is listed on the Official MCP Registry. Any MCP-compatible agent discovers tools automatically:
mcp_endpoint: https://factorguide.io/mcpHTTP REST
POST https://factorguide.io/navigate
POST https://factorguide.io/diagnose
POST https://factorguide.io/explain
POST https://factorguide.io/report_outcomeAgent Discovery
GET https://factorguide.io/llms.txt
GET https://factorguide.io/openapi.jsonRelated MCP server: AGI Cognitive MCP Server
Example
Send a 3×3 correlation matrix:
{
"coupling": {
"covariance_matrix": [
[1.00, 0.72, 0.05],
[0.72, 1.00, 0.48],
[0.05, 0.48, 1.00]
]
},
"sample_size": 500,
"model_class": "constitutive"
}Get back zone classifications:
Pair | IC | Zone | Recommendation |
z0–z1 | 0.682 | 3 | PRESERVE |
z0–z2 | 0.031 | 1 | FACTORIZE |
z1–z2 | 0.453 | 2 | ASSESS |
Zone 1: Safe to factorize. Coupling below threshold.
Zone 2: Depends on functional role. Same IC, opposite recommendations for constitutive vs. inductive coupling.
Zone 3: Must preserve. Coupling is load-bearing regardless of model class.
Pricing
Tier | Price | Queries | Max Variables |
Trial | Free | 15 per wallet | n ≤ 25 |
Starter | $0.05/query | 50–200 bundles | n ≤ 100 |
Professional | $0.03/query | 500–2000 bundles | n ≤ 1000 |
Payment: USDC on Base via x402 or MPP. report_outcome is always free.
Data Privacy
FactorGuide accepts only second-order summary statistics — covariance, precision, correlation matrices, or edge lists. No raw observations. Matrices are zeroed after IC computation.
Theoretical Foundation
Built on Circulatory Fidelity, a mathematical framework where IC (Inference Coupling) measures the partial correlation between variables. The cost function V(IC) gives the exact mutual information destroyed by severing a coupling. Risk curves are calibrated on 49,000+ validated datapoints.
Every prediction is falsifiable. When agents report outcomes, the flywheel refines future predictions.
Links
Website: factorguide.io
Theory: circulatoryfidelity.com
MCP Registry: registry.modelcontextprotocol.io
Built by CF Laboratory
This server cannot be deployed
Maintenance
Related MCP Connectors
Portfolio and strategy stress diagnostics with hedge-break detection and regime outlook. Free tier.
Market regime, 7-dimension risk vectors and payment hazard grades. Abstains when data is thin.
Detect causal dependencies in time series
Finds the simplest equation consistent with your data. SINDy and PySR symbolic regression via MCP.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables institutional-grade Monte Carlo risk analysis for portfolios, startups, real estate, and betting strategies using fat-tail distributions and proprietary algorithms. Provides comprehensive risk metrics including CVaR, VaR, ruin probability, and survival probability across multiple asset classes.1-
- FlicenseNot gradedqualityDmaintenanceProvides programmatic access to causal discovery, topological data analysis, Gaussian process belief updating, thermodynamic auditing, and HCHL inference for agents and researchers.-
- AlicenseNot gradedqualityCmaintenanceFuses five market signals into a five-state regime classifier to determine market conditions and recommend trading postures for risk management.MIT
- AlicenseNot gradedqualityBmaintenanceThe verifiable risk engine for autonomous agents: deterministic, self-verifying financial calculations that an agent can delegate and prove. It covers liquidation and funding, position sizing and risk of ruin, options Greeks and margin, LP divergence, treasury concentration and depeg, execution quality checks, plus intelligence on options, DeFi, prediction markets, and transaction safety analysis.10 npm1MIT