AINumbers.co Cyber Insurance API

openapi: 3.2.0
info:
  title: AINumbers.co Fintech Intelligence Suite Cyber Insurance API
  version: 1.0.0
  description: '**1255 fintech intelligence tools** covering ISO 20022, A2A payments, CFPB §1033, EU AI Act, DORA, MiCA, AML/KYC, BaaS, DLT/tokenization, ESG/climate finance, agentic payments (AP2, ACP, x402, Visa TAP, Mastercard Agent Pay), PQC migration, sanctions screening, and OpenChainGraph v0.4 computation chains.


    ## Transport


    > **The live transport is MCP JSON-RPC 2.0 at `https://mcp.ainumbers.co/mcp` — not REST.**

    >

    > This OpenAPI file is a **descriptive data-room artifact** — a machine-readable index of all tools and their input/output schemas. The REST paths (`POST /v1/tools/{name}`) described here are a projection; they become functional only if the optional REST shim (Area 2 Path B) is deployed.

    >

    > To call tools today, connect via the official MCP client SDKs. TypeScript: `@modelcontextprotocol/sdk`. Python: `mcp`.


    ## Architecture


    All tools run **entirely client-side** (browser JavaScript). Zero PII. Zero server calls after page load. Deterministic, reproducible outputs. Licensed CC BY 4.0.


    OpenChainGraph v0.4 compute-binding nodes additionally run **server-side on the MCP Worker** and emit verifiable artifacts with `execution_hash` (WebCrypto SHA-256 over RFC 8785 canonical JSON).'
  contact:
    name: Post Oak Labs
    url: https://postoaklabs.com
    email: tim@postoaklabs.com
  license:
    name: CC BY 4.0
    url: https://creativecommons.org/licenses/by/4.0/
servers:
- url: https://ainumbers.co
  description: Static browser-based tool host (DreamHost). Tools run client-side — no REST gateway is active on this origin. See x-mcp for the live MCP endpoint.
tags:
- name: cyber-insurance
paths:
  /v1/tools/model_cyber_accumulation_pml:
    post:
      operationId: model_cyber_accumulation_pml
      summary: Cyber Insurance Accumulation & PML Modeler
      description: 'Estimate portfolio-level cyber insurance Probable Maximum Loss (PML) at multiple return periods by scenario type, using published industry severity curves by sector and coverage trigger (IBM/Ponemon 2024, FBI IC3 2024) and Lloyd''s RDS 2024 systemic PML scalars. Computes attritional expected loss, systemic PML by return period, combined PML upper bound, loss-ratio stress, and an accumulation alert at >25% of the aggregate limit. Client-side. Works offline. Zero PII; synthetic aggregate inputs only.


        **Tool URL:** https://ainumbers.co/tools/461-cyber-insurance-accumulation-modeler.html

        **AP2/Policy Mandate export:** yes'
      tags:
      - cyber-insurance
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
              - numRisks
              - avgRevenue
              - avgLimit
              - aggLimit
              - avgPremium
              properties:
                numRisks:
                  type: number
                avgRevenue:
                  type: number
                revDist:
                  type: string
                sector:
                  type: string
                avgLimit:
                  type: number
                avgRetention:
                  type: number
                avgPremium:
                  type: number
                aggLimit:
                  type: number
                mixRansomNum:
                  type: number
                mixBreachNum:
                  type: number
                mixBINum:
                  type: number
                mixLiabNum:
                  type: number
                mixFTFNum:
                  type: number
                correlation:
                  type: string
                cspConc:
                  type: string
                scaExp:
                  type: string
      responses:
        '200':
          description: Successful tool execution result
          content:
            application/json:
              schema:
                type: object
                properties:
                  attritional_el_m:
                    type: number
                    description: Attritional expected annual loss ($M)
                  pml_1in100_m:
                    type: number
                    description: Combined 1-in-100 PML ($M)
                  pml_1in250_m:
                    type: number
                    description: Combined 1-in-250 PML ($M)
                  pml_1in100_pct_of_aggregate:
                    type: number
                    description: 1-in-100 PML as % of aggregate limit
                  accumulation_alert:
                    type: boolean
                    description: True if 1-in-100 PML exceeds 25% of aggregate limit (Lloyd's RDS threshold)
                  loss_ratio_stress_pct:
                    type: object
                    description: Stressed loss ratio by return period
      x-mcp-tool-name: model_cyber_accumulation_pml
      x-tool-url: https://ainumbers.co/tools/461-cyber-insurance-accumulation-modeler.html
      x-source: manifest
      x-ap2-export: true
x-mcp:
  transport: MCP JSON-RPC 2.0 (streamable HTTP)
  endpoint: https://mcp.ainumbers.co/mcp
  protocol_version: '2025-11-25'
  authentication: none
  registry: co.ainumbers/tools (official MCP registry)
  note: Connect any MCP-compatible client (Claude, ChatGPT, custom agent) directly to this endpoint. The REST paths in this file are descriptive only — they do not exist on the live server unless the REST shim is deployed.