English Français العربية

io.factorguide/factorguide

Registre officiel Autres

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

Code source Documentation

Installation

Ajoutez ceci à la configuration MCP de votre client (Claude Desktop : claude_desktop_config.json ; Cursor : .cursor/mcp.json ; VS Code et les autres utilisent la même forme « mcpServers »).

Remote (streamable-http)
Claude Code 
claude mcp add --transport http factorguide 'https://factorguide.io/mcp'
Configuration JSON (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "factorguide": {
            "type": "http",
            "url": "https://factorguide.io/mcp"
        }
    }
}

Documentation

Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.

Sommaire
  1. FactorGuide
  2. Quick Start
  3. Example
  4. Pricing
  5. Data Privacy
  6. Theoretical Foundation
  7. Links

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/mcp
HTTP REST
POST https://factorguide.io/navigate
POST https://factorguide.io/diagnose
POST https://factorguide.io/explain
POST https://factorguide.io/report_outcome
Agent Discovery
GET https://factorguide.io/llms.txt
GET https://factorguide.io/openapi.json

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:

PairICZoneRecommendation
z0–z10.6823PRESERVE
z0–z20.0311FACTORIZE
z1–z20.4532ASSESS
  • 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

TierPriceQueriesMax Variables
TrialFree15 per walletn ≤ 25
Starter$0.05/query50–200 bundlesn ≤ 100
Professional$0.03/query500–2000 bundlesn ≤ 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.

Built by CF Laboratory

Questions fréquentes

Qu'est-ce que io.factorguide/factorguide ?

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

Comment installer io.factorguide/factorguide ?

Il fonctionne comme serveur distant. Dans Claude Code : claude mcp add --transport http factorguide 'https://factorguide.io/mcp'. Pour les autres clients, collez la configuration JSON de cette page dans leurs réglages MCP.

Faut-il une clé API pour io.factorguide/factorguide ?

Son entrée au registre n'indique aucune clé ni secret obligatoire. Certaines fonctions peuvent tout de même demander un compte auprès du service auquel il se connecte.

io.factorguide/factorguide est-il open source ?

Son code est public sur GitHub, mais le dépôt ne déclare pas de licence standard.

Qui maintient io.factorguide/factorguide ?

Il est publié par Bwana7. AI.tn le référence sans le maintenir ni le recommander.

Issu du registre MCP officiel. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.