{
  "markdown": "# FactorGuide\n\n**Decision intelligence for AI agents.** Send a coupling matrix — get zone classifications, optimal factorization strategy, and calibrated risk predictions.\n\nEvery 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.\n\n## Quick Start\n\n### MCP (Model Context Protocol)\n\nFactorGuide is listed on the [Official MCP Registry](https://registry.modelcontextprotocol.io/). Any MCP-compatible agent discovers tools automatically:\n\n```\nmcp_endpoint: https://factorguide.io/mcp\n```\n\n### HTTP REST\n\n```\nPOST https://factorguide.io/navigate\nPOST https://factorguide.io/diagnose\nPOST https://factorguide.io/explain\nPOST https://factorguide.io/report_outcome\n```\n\n### Agent Discovery\n\n```\nGET https://factorguide.io/llms.txt\nGET https://factorguide.io/openapi.json\n```\n\n## Example\n\nSend a 3×3 correlation matrix:\n\n```json\n{\n  \"coupling\": {\n    \"covariance_matrix\": [\n      [1.00, 0.72, 0.05],\n      [0.72, 1.00, 0.48],\n      [0.05, 0.48, 1.00]\n    ]\n  },\n  \"sample_size\": 500,\n  \"model_class\": \"constitutive\"\n}\n```\n\nGet back zone classifications:\n\n| Pair | IC | Zone | Recommendation |\n|------|-----|------|----------------|\n| z0–z1 | 0.682 | 3 | **PRESERVE** |\n| z0–z2 | 0.031 | 1 | FACTORIZE |\n| z1–z2 | 0.453 | 2 | ASSESS |\n\n- **Zone 1**: Safe to factorize. Coupling below threshold.\n- **Zone 2**: Depends on functional role. Same IC, opposite recommendations for constitutive vs. inductive coupling.\n- **Zone 3**: Must preserve. Coupling is load-bearing regardless of model class.\n\n## Pricing\n\n| Tier | Price | Queries | Max Variables |\n|------|-------|---------|---------------|\n| Trial | Free | 15 per wallet | n ≤ 25 |\n| Starter | $0.05/query | 50–200 bundles | n ≤ 100 |\n| Professional | $0.03/query | 500–2000 bundles | n ≤ 1000 |\n\nPayment: USDC on Base via x402 or MPP. `report_outcome` is always free.\n\n## Data Privacy\n\nFactorGuide accepts only second-order summary statistics — covariance, precision, correlation matrices, or edge lists. No raw observations. Matrices are zeroed after IC computation.\n\n## Theoretical Foundation\n\nBuilt on [Circulatory Fidelity](https://circulatoryfidelity.com), 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.\n\nEvery prediction is falsifiable. When agents report outcomes, the flywheel refines future predictions.\n\n## Links\n\n- **Website**: [factorguide.io](https://factorguide.io)\n- **Theory**: [circulatoryfidelity.com](https://circulatoryfidelity.com)\n- **MCP Registry**: [registry.modelcontextprotocol.io](https://registry.modelcontextprotocol.io/)\n\n---\n\nBuilt by [CF Laboratory](https://circulatoryfidelity.com)\n",
  "bytes": 2926,
  "sha": "d4a746e698d5bfc951761027fd4d7ee96e18d1cb46809f4761be746825c5b0d6",
  "repo_slug": "bwana7/factorguide",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_factorguide_factorguide_2e5fd51e/readme"
}