AINumbers.co Audit Sampling API
The audit-sampling API from AINumbers.co — 2 operation(s) for audit-sampling.
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-audit-sampling-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 Audit Sampling 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: audit-sampling
paths:
/v1/tools/derive_beacon_fair_sample_v2:
post:
operationId: derive_beacon_fair_sample_v2
summary: Beacon-Seeded Fair-Sampling Deriver V2
description: 'Derives a deterministic, offline-replayable audit sample, version 2 of the beacon-seeded fair-sampling family, from a caller-pasted public randomness beacon pulse (drand quicknet or NISTIR-8213) and an item-manifest hash committed before the pulse round, over the same HMAC-DRBG (SHA-256) stream as version 1 (art-583). Version 2 fixes three version 1 defects in a new node rather than editing the proven original: a threshold-rejection reduction replaces the raw modulo so index selection is exactly unbiased; a partial Fisher-Yates walk over an index array consumes exactly sample_size accepted draws with no draw cap, so full samples succeed at any population up to the 1,000,000-item ceiling (version 1''s draw cap failed near-full samples above roughly 12,000 items); and both hex inputs are validated as exactly 64 lowercase hex characters, with a structured refusal otherwise. The ceiling commits to a 4 MB index array at maximum population. The emitted per-draw transcript is capped at 50 entries and carries full draws_used and rejection counts, so the artifact stays bounded while the walk remains fully reconstructible offline from the declared inputs alone. The beacon pulse is caller-declared: this kernel does SHA-256/HMAC math only, never fetches a pulse and never verifies its signature. The version 1 node stays untouched and replayable for every receipt already issued against it; new runs should use this node.
**Tool URL:** https://ainumbers.co/chaingraph/art-774-beacon-seeded-fair-sampling-v2.html'
tags:
- audit-sampling
requestBody:
required: true
content:
application/json:
schema:
type: object
required:
- beacon_source
- beacon_round
- beacon_randomness
- item_manifest_hash
- item_count
- sample_size
- algorithm_id
properties:
beacon_source:
type: string
enum:
- drand_quicknet
- nistir_8213
description: The public randomness beacon family the pulse came from.
beacon_round:
type: string
description: The pulse round identifier, exactly as published.
beacon_randomness:
type: string
description: 'The pulse''s declared randomness value: exactly 64 lowercase hex characters (0-9, a-f), no prefix.'
item_manifest_hash:
type: string
description: 'Hash of the item manifest committed BEFORE the pulse round: exactly 64 lowercase hex characters (0-9, a-f), without a sha256: prefix.'
item_count:
type: integer
minimum: 1
maximum: 1000000
description: Population size. The ceiling commits to a 4 MB index array at maximum.
sample_size:
type: integer
minimum: 1
description: Number of items to select; cannot exceed item_count. 0 or missing is a refusal.
algorithm_id:
type: string
enum:
- hmac-drbg-sha256-v2
description: The algorithm id this kernel implements.
responses:
'200':
description: Successful tool execution result
content:
application/json:
schema:
type: object
properties:
verdict:
type: string
enum:
- DERIVED
- INDETERMINATE
reasons:
type: array
items:
type: string
beacon_source:
type:
- string
- 'null'
beacon_round:
type:
- string
- 'null'
beacon_randomness:
type:
- string
- 'null'
item_manifest_hash:
type:
- string
- 'null'
item_count:
type:
- integer
- 'null'
sample_size:
type:
- integer
- 'null'
algorithm_id:
type:
- string
- 'null'
seed_hex:
type: string
selected_indices:
type: array
items:
type: integer
draws_used:
type: integer
reduction_rejects:
type: integer
derivation_transcript:
type: array
items:
type: object
properties:
draw:
type: integer
hmac_hex:
type: string
result:
type: string
enum:
- selected
- rejected_reduction
position:
type: integer
swap_index:
type: integer
selected_index:
type: integer
transcript_truncated:
type: boolean
manual_review_required:
type: boolean
description: True exactly when the verdict is INDETERMINATE and an input must be fixed before re-running (flag-mirror member).
x-mcp-tool-name: derive_beacon_fair_sample_v2
x-tool-url: https://ainumbers.co/chaingraph/art-774-beacon-seeded-fair-sampling-v2.html
x-source: manifest
/v1/tools/compute_isa530_audit_sampling_mus:
post:
operationId: compute_isa530_audit_sampling_mus
summary: ISA 530 Audit Sampling + MUS Calculator
description: 'Deterministic audit-sampling arithmetic in three caller-declared functions dispatched on method. monetary_unit_sampling sizes a MUS engagement: n = ceil(book_value * confidence_factor / (performance_materiality - expected_misstatement)) and sampling interval = round(book_value / n), failing closed whenever expected_misstatement >= performance_materiality. misstatement_projection applies the tainting method to caller-supplied sampled items (taint = (book - audited) / book, projected misstatement = sum of taint * interval) and adds the basic-precision figure confidence_factor * interval. benford_screen compares the observed first-significant-digit distribution of caller-supplied positive amounts against the Benford expected proportions with a chi-square deviation flag at the 5% level (8 degrees of freedom, critical value 15.507). The method''s source standard is ISA 530 (iaasb.org): this node computes the arithmetic of the method and never certifies compliance with any standard, never opines on audit sufficiency, and never selects sample items. No randomness of any kind: any selection start point a caller uses is a caller-declared input, never generated here.
**Tool URL:** https://ainumbers.co/chaingraph/art-693-isa530-audit-sampling-mus.html
**AP2/Policy Mandate export:** yes'
tags:
- audit-sampling
requestBody:
required: true
content:
application/json:
schema:
type: object
required:
- method
properties:
method:
type: string
enum:
- monetary_unit_sampling
- misstatement_projection
- benford_screen
book_value:
type: number
exclusiveMinimum: 0
performance_materiality:
type: number
exclusiveMinimum: 0
expected_misstatement:
type: number
minimum: 0
confidence_factor:
type: number
exclusiveMinimum: 0
sampling_interval:
type: integer
exclusiveMinimum: 0
sampled_items:
type: array
amounts:
type: array
responses:
'200':
description: Successful tool execution result
content:
application/json:
schema:
type: object
required:
- trace
- overall
properties:
sample_size:
type:
- integer
- 'null'
sampling_interval:
type:
- integer
- 'null'
tolerable_misstatement:
type:
- number
- 'null'
confidence_factor:
type:
- number
- 'null'
item_count:
type: integer
usable_item_count:
type: integer
usable_count:
type: integer
per_item:
type: array
items:
type: object
properties:
seq:
type: integer
book_amount:
type: number
audited_amount:
type: number
taint_percent:
type: number
projected_amount:
type: number
projected_misstatement:
type:
- number
- 'null'
basic_precision:
type:
- number
- 'null'
basic_precision_note:
type: string
first_digit_counts:
type:
- object
- 'null'
additionalProperties:
type: integer
chi_square_statistic:
type:
- number
- 'null'
critical_value:
type: number
deviation_flag:
type:
- boolean
- 'null'
trace:
type: string
overall:
type: string
enum:
- SAMPLE_COMPUTED
- PROJECTED
- SCREENED_CONSISTENT
- SCREENED_DEVIATES
- INPUT_REJECTED
warnings:
type: array
items:
type: string
x_schema_provenance: derived-from-golden-fixtures 2026-09-03 (11 vectors, chaingraph/kernels/fixtures/art-693-isa530-audit-sampling-mus.fixtures.json)
x-mcp-tool-name: compute_isa530_audit_sampling_mus
x-tool-url: https://ainumbers.co/chaingraph/art-693-isa530-audit-sampling-mus.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.