AINumbers.co AP2 API
The AP2 API from AINumbers.co — 6 operation(s) for ap2.
Work with this as data
Every API here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for apis
7 MCP tools reach this
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
This API
curl "https://apis.io/api/v1/apis/ainumbers-co:ainumbers-co-ap2-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"Discovery needs no key. Ratings and market analysis are Pro.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
OpenAPI Specification
openapi: 3.2.0
info:
title: AINumbers.co Fintech Intelligence Suite AP2 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: AP2
paths:
/v1/tools/check_ap2_compatibility:
post:
operationId: check_ap2_compatibility
summary: AP2 Agentic Payments Compatibility Checker
description: 'Validates a payment payload or manual checklist against the AP2 (Agent-to-Agent Payments Protocol) specification. Scores compatibility, flags schema gaps, and generates a scaffold for non-compliant payloads.
**Tool URL:** https://ainumbers.co/tools/102-ap2-payments-checker.html
**AP2/Policy Mandate export:** yes'
tags:
- AP2
requestBody:
required: true
content:
application/json:
schema:
type: object
required:
- mode
properties:
mode:
type: string
enum:
- json
- manual
payload:
type: object
answers:
type: object
responses:
'200':
description: Successful tool execution result
content:
application/json:
schema:
type: object
properties:
compatibility_score:
type: number
minimum: 0
maximum: 100
band:
type: string
enum:
- AP2-Ready
- Partially Compatible
- Incompatible
- Unknown
dimensions:
type: array
items:
type: object
scaffold_generated:
type: boolean
x-mcp-tool-name: check_ap2_compatibility
x-tool-url: https://ainumbers.co/tools/102-ap2-payments-checker.html
x-source: manifest
x-ap2-export: true
/v1/tools/build_google_ap2_mandate:
post:
operationId: build_google_ap2_mandate
summary: Google AP2 Checkout/Payment Mandate (VDC) Builder & Validator
description: 'Builds and validates Google Agent Payments Protocol (AP2) Checkout Mandate and Payment Mandate Verifiable Digital Credentials across Open/Closed stages. This targets the EXTERNAL Google/FIDO AP2 spec (ap2-protocol.org), distinct from the AINumbers Policy Mandate export. Field names are illustrative — verify against the AP2 spec.
**Tool URL:** https://ainumbers.co/tools/285-google-ap2-mandate-builder.html
**AP2/Policy Mandate export:** yes'
tags:
- AP2
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
mandate_type:
type: string
description: checkout | payment
stage:
type: string
description: open | closed
fields:
type: object
responses:
'200':
description: Successful tool execution result
content:
application/json:
schema:
type: object
properties:
mandate:
type: object
findings:
type: array
x-mcp-tool-name: build_google_ap2_mandate
x-tool-url: https://ainumbers.co/tools/285-google-ap2-mandate-builder.html
x-source: manifest
x-ap2-export: true
/v1/tools/validate_ap2_mcp_policy:
post:
operationId: validate_ap2_mcp_policy
summary: AP2 MCP Policy Validator & Bridge
description: 'Validate Policy Mandate JSON payloads against the Unified Build Contract v1.0 schema, auto-generate MCP tool definitions, and simulate agent ingestion of agent_instructions.
**Tool URL:** https://ainumbers.co/tools/320-ap2-mcp-policy-validator.html
**AP2/Policy Mandate export:** yes'
tags:
- AP2
requestBody:
required: true
content:
application/json:
schema:
type: object
required:
- policy_mandate_json
properties:
policy_mandate_json:
type: string
validate_against:
type: string
generate_mcp_definition:
type: boolean
simulate_agent_ingestion:
type: boolean
responses:
'200':
description: Successful tool execution result
content:
application/json:
schema:
type: object
properties:
valid:
type: boolean
schema_errors:
type: array
mcp_tool_definition:
type: object
agent_ingestion_simulation:
type: object
export_json:
type: string
x-mcp-tool-name: validate_ap2_mcp_policy
x-tool-url: https://ainumbers.co/tools/320-ap2-mcp-policy-validator.html
x-source: manifest
x-ap2-export: true
/v1/tools/build_fraud_risk_ap2_mandate:
post:
operationId: build_fraud_risk_ap2_mandate
summary: AP2 Fraud & Risk Policy Mandate Builder
description: 'Builds a validated AP2 agent_guardrail_mandate for autonomous fraud decisioning agents across 4 dimensions: detection thresholds (synthetic ID, ATO cutoffs), APP scam controls (CoP, delay, PSR acknowledgement), loss tolerance (bps budget, CNP/ATO/APP rates), and reporting triggers (SAR threshold, board frequency). Built-in contradiction detection. MCP server deployable. Client-side. Works offline. Zero PII.
**Tool URL:** https://ainumbers.co/tools/323-ap2-fraud-risk-policy-mandate-builder.html
**AP2/Policy Mandate export:** yes'
tags:
- AP2
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
synth_cutoff:
type: integer
ato_cutoff:
type: integer
cop_enforcement:
type: string
delay_policy:
type: string
psr_ack:
type: boolean
loss_budget_bps:
type: integer
cnp_rate_bps:
type: integer
ato_rate_bps:
type: integer
app_rate_bps:
type: integer
sar_threshold:
type: integer
board_freq:
type: string
required:
- synth_cutoff
- ato_cutoff
- cop_enforcement
- delay_policy
- psr_ack
- loss_budget_bps
- cnp_rate_bps
- ato_rate_bps
- app_rate_bps
- sar_threshold
- board_freq
responses:
'200':
description: Successful tool execution result
content:
application/json:
schema:
type: object
properties:
agent_instructions:
type: array
items:
type: string
config:
type: object
x-mcp-tool-name: build_fraud_risk_ap2_mandate
x-tool-url: https://ainumbers.co/tools/323-ap2-fraud-risk-policy-mandate-builder.html
x-source: manifest
x-ap2-export: true
/v1/tools/build_payment_ops_ap2_mandate:
post:
operationId: build_payment_ops_ap2_mandate
summary: AP2 Payment Ops Policy Mandate Builder
description: 'Builds a validated AP2 agent_guardrail_mandate for autonomous ops monitoring agents across 4 dimensions: liquidity policy (with T324 AP2 JSON import to auto-populate opening balance and rail), routing policy (primary/fallback rail per corridor, cost ceiling), SLA and monitoring policy (RT/batch targets, breach threshold, alert frequency), and incident policy (P1-P4 threshold, runbook URL, escalation role). MCP server deployable. Client-side. Works offline. Zero PII.
**Tool URL:** https://ainumbers.co/tools/326-ap2-payment-ops-policy-mandate-builder.html
**AP2/Policy Mandate export:** yes'
tags:
- AP2
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
prefund_target_m:
type: number
topup_threshold_pct:
type: integer
primary_rail_liq:
type: string
rail_us:
type: string
rail_eu:
type: string
rail_uk:
type: string
rail_xb:
type: string
fallback_rail:
type: string
cost_ceiling_bps:
type: integer
rt_sla_ms:
type: integer
batch_sla_hrs:
type: integer
sla_breach_pct:
type: integer
alert_freq:
type: string
p_level:
type: string
runbook_url:
type: string
escalation_role:
type: string
required:
- prefund_target_m
- topup_threshold_pct
- primary_rail_liq
- rail_us
- rail_eu
- rail_uk
- rail_xb
- fallback_rail
- cost_ceiling_bps
- rt_sla_ms
- batch_sla_hrs
- sla_breach_pct
- alert_freq
- p_level
responses:
'200':
description: Successful tool execution result
content:
application/json:
schema:
type: object
properties:
agent_instructions:
type: array
items:
type: string
config:
type: object
x-mcp-tool-name: build_payment_ops_ap2_mandate
x-tool-url: https://ainumbers.co/tools/326-ap2-payment-ops-policy-mandate-builder.html
x-source: manifest
x-ap2-export: true
/v1/tools/compose_ap2_prompt:
post:
operationId: compose_ap2_prompt
summary: AP2 Prompt Template Generator
description: 'Transforms any OpenChainGraph artifact JSON into a structured, regulator-framed prompt for any external LLM. Template registry v1.0.0 — one entry per mandate_type with regulatory citations, audience formats, stochastic-framing rules, and escalation conditions. No inference performed; pure template composition.
**Tool URL:** https://ainumbers.co/chaingraph/ptg-01-ap2-prompt-template-generator.html
**AP2/Policy Mandate export:** yes'
tags:
- AP2
requestBody:
required: true
content:
application/json:
schema:
type: object
required:
- task
- audience
properties:
artifact_json:
type: string
description: OpenChainGraph artifact JSON from any suite tool
task:
type: string
enum:
- board_memo
- regulatory_submission
- risk_memo
- remediation_plan
- plain_english_summary
- period_comparison
- top_3_risks
description: Output task type
audience:
type: string
enum:
- board
- risk_committee
- regulator
- quant
- ops
description: Target audience for the generated prompt
tone:
type: string
enum:
- formal
- technical
- plain
default: formal
include_citations:
type: boolean
default: true
x_schema_provenance: authored-from-page-embedded-manifest-and-kernel-fixture-0 2026-09-05
responses:
'200':
description: Successful tool execution result
content:
application/json:
schema:
type: object
properties:
audience:
type: string
claude_deeplink:
type: string
generated_prompt:
type: string
generated_prompt_length:
type: number
include_citations:
type: boolean
mandate_type_matched:
type: string
source_execution_hash:
type: string
source_tool_id:
type: string
task:
type: string
tone:
type: string
required:
- audience
- claude_deeplink
- generated_prompt
- generated_prompt_length
- include_citations
- mandate_type_matched
- source_execution_hash
- source_tool_id
- task
- tone
additionalProperties: false
x-mcp-tool-name: compose_ap2_prompt
x-tool-url: https://ainumbers.co/chaingraph/ptg-01-ap2-prompt-template-generator.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.