AINumbers.co MCP API
The MCP API from AINumbers.co — 8 operation(s) for mcp.
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-mcp-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 MCP 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: MCP
paths:
/v1/tools/lint_mcp_tool_definition:
post:
operationId: lint_mcp_tool_definition
summary: MCP Tool-Definition Linter & Annotation Designer
description: 'Lints a Model Context Protocol tool definition (name, description, inputSchema, outputSchema, annotations) against JSON Schema 2020-12 and current MCP tool-naming and annotation rules, scores conformance, and designs a consistent annotation set. Reference rules are static and may age — verify against the live MCP specification.
**Tool URL:** https://ainumbers.co/tools/274-mcp-tool-definition-linter.html
**AP2/Policy Mandate export:** yes'
tags:
- MCP
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
tool_definition:
type: object
description: The MCP tool definition to lint.
required:
- tool_definition
responses:
'200':
description: Successful tool execution result
content:
application/json:
schema:
type: object
properties:
score:
type: number
findings:
type: array
items:
type: object
annotations:
type: object
x-mcp-tool-name: lint_mcp_tool_definition
x-tool-url: https://ainumbers.co/tools/274-mcp-tool-definition-linter.html
x-source: manifest
x-ap2-export: true
/v1/tools/validate_mcp_server_json:
post:
operationId: validate_mcp_server_json
summary: MCP server.json Validator & Registry-Ready Skeleton Generator
description: 'Validates an MCP server.json against the 2025-12-11 generic schema and the official MCP Registry publishing constraints (reverse-DNS namespace, _meta 4KB publisher cap, allowlisted registry base URLs, MCPB fileSha256, stdio/streamable-http transport), and generates a compliant skeleton for npm/PyPI/OCI/MCPB/remote servers. Reference rules are static and may age — verify against the live MCP Registry docs.
**Tool URL:** https://ainumbers.co/tools/275-mcp-server-json-validator.html
**AP2/Policy Mandate export:** yes'
tags:
- MCP
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
server_json:
type: object
description: The MCP server.json document to validate.
required:
- server_json
responses:
'200':
description: Successful tool execution result
content:
application/json:
schema:
type: object
properties:
score:
type: number
findings:
type: array
items:
type: object
skeleton:
type: object
x-mcp-tool-name: validate_mcp_server_json
x-tool-url: https://ainumbers.co/tools/275-mcp-server-json-validator.html
x-source: manifest
x-ap2-export: true
/v1/tools/audit_mcp_oauth:
post:
operationId: audit_mcp_oauth
summary: MCP OAuth 2.1 Authorization Auditor
description: 'Validates an MCP protected-resource-metadata (RFC 9728) document, visualizes the OAuth 2.1 discovery chain, checks RFC 8707 resource-indicator / audience binding, and self-assesses token-passthrough and confused-deputy risk. Reference rules are static and may age — verify against the live MCP authorization spec.
**Tool URL:** https://ainumbers.co/tools/278-mcp-oauth-authorization-auditor.html
**AP2/Policy Mandate export:** yes'
tags:
- MCP
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
protected_resource_metadata:
type: object
description: The /.well-known/oauth-protected-resource JSON.
canonical_resource:
type: string
description: Canonical MCP server resource URI.
responses:
'200':
description: Successful tool execution result
content:
application/json:
schema:
type: object
properties:
score:
type: number
findings:
type: array
x-mcp-tool-name: audit_mcp_oauth
x-tool-url: https://ainumbers.co/tools/278-mcp-oauth-authorization-auditor.html
x-source: manifest
x-ap2-export: true
/v1/tools/score_mcp_spec_revision:
post:
operationId: score_mcp_spec_revision
summary: MCP Spec-Revision Compliance Scorer & Stateless Migration Advisor
description: 'Scores an MCP server''s capability/handshake posture against a target spec revision (2025-06-18, 2025-11-25, or the 2026-07-28 release candidate) and advises on the breaking changes in the stateless protocol core. Reference rules are static and may age — verify against the live MCP specification.
**Tool URL:** https://ainumbers.co/tools/280-mcp-spec-revision-compliance-scorer.html
**AP2/Policy Mandate export:** yes'
tags:
- MCP
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
target_revision:
type: string
description: Target MCP spec revision to score against
enum:
- '2025-06-18'
- '2025-11-25'
- 2026-07-28-rc
answers:
type: object
description: Capability answers
responses:
'200':
description: Successful tool execution result
content:
application/json:
schema:
type: object
properties:
score:
type: number
findings:
type: array
x-mcp-tool-name: score_mcp_spec_revision
x-tool-url: https://ainumbers.co/tools/280-mcp-spec-revision-compliance-scorer.html
x-source: manifest
x-ap2-export: true
/v1/tools/scan_tool_poisoning:
post:
operationId: scan_tool_poisoning
summary: MCP Tool-Poisoning & Prompt-Injection Manifest Scanner
description: 'Scans an MCP tool description or manifest for tool-poisoning and prompt-injection smells — instruction overrides, hidden/zero-width unicode, role-play framing, embedded model-directed instructions, and exfiltration hints. Heuristic pattern matcher mapped to OWASP ASI01 (Agent Goal Hijack); flags are signals, not proof.
**Tool URL:** https://ainumbers.co/tools/282-mcp-tool-poisoning-scanner.html
**AP2/Policy Mandate export:** yes'
tags:
- MCP
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
text:
type: string
description: The tool description or manifest text to scan
required:
- text
responses:
'200':
description: Successful tool execution result
content:
application/json:
schema:
type: object
properties:
risk:
type: number
findings:
type: array
x-mcp-tool-name: scan_tool_poisoning
x-tool-url: https://ainumbers.co/tools/282-mcp-tool-poisoning-scanner.html
x-source: manifest
x-ap2-export: true
/v1/tools/audit_mcp_transport:
post:
operationId: audit_mcp_transport
summary: MCP Transport & DNS-Rebinding Security Auditor
description: 'Audits an MCP server''s transport security posture — Origin/Host validation, loopback binding, DNS-rebinding protection, and token passthrough — against the spec requirements and the rmcp / mcp-toolbox CVE classes. Reference rules are static and may age — verify against the live MCP spec.
**Tool URL:** https://ainumbers.co/tools/284-mcp-transport-dns-rebinding-auditor.html
**AP2/Policy Mandate export:** yes'
tags:
- MCP
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
bind_address:
type: string
allowed_origins:
type: string
answers:
type: object
responses:
'200':
description: Successful tool execution result
content:
application/json:
schema:
type: object
properties:
score:
type: number
findings:
type: array
x-mcp-tool-name: audit_mcp_transport
x-tool-url: https://ainumbers.co/tools/284-mcp-transport-dns-rebinding-auditor.html
x-source: manifest
x-ap2-export: true
/v1/tools/score_mcp_readiness:
post:
operationId: score_mcp_readiness
summary: MCP Developer Readiness Scorecard
description: 'A composite ship-readiness scorecard for an MCP server across six sections — tool-definition quality, server.json registry-readiness, OAuth 2.1 authorization, transport security, tool-poisoning hygiene, and spec-revision compliance. Reference rules are static and may age — verify against the live MCP spec and the linked per-section tools.
**Tool URL:** https://ainumbers.co/tools/288-mcp-developer-readiness-scorecard.html
**AP2/Policy Mandate export:** yes'
tags:
- MCP
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
answers:
type: object
responses:
'200':
description: Successful tool execution result
content:
application/json:
schema:
type: object
properties:
overall:
type: number
sections:
type: array
x-mcp-tool-name: score_mcp_readiness
x-tool-url: https://ainumbers.co/tools/288-mcp-developer-readiness-scorecard.html
x-source: manifest
x-ap2-export: true
/v1/tools/run_kernel_vm:
post:
operationId: run_kernel_vm
summary: Kernel VM
description: 'Run a ChainGraph decision kernel''s compute(policy_parameters) inside a sandboxed, hermetic, in-browser QuickJS-ng WebAssembly VM under the ocg-deterministic-compute@2 profile (SPEC.md section 24) and inspect its execution_hash. Phase VM-1b: a custom guest-pinned build of quickjs-ng v0.15.1 (the exact revision in the zkVM guest), with the deterministic WebCrypto subset (section 24.5) and full native BigInt; zero-fetch, no CDN. Ships a small curated set of demo kernels; every conformance-fixtured gpu:false kernel is checked automatically in CI by chaingraph/kernels/vm-parity-gate.mjs, which diffs this same VM''s execution_hash against the worker''s own kernel registry.
**Tool URL:** https://ainumbers.co/tools/kernel-vm-widget.html'
tags:
- MCP
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
tool_id:
type: string
policy_parameters:
type: object
required:
- tool_id
- policy_parameters
responses:
'200':
description: Successful tool execution result
content:
application/json:
schema:
type: object
properties:
output_payload:
type: object
elapsed_ms:
type: number
x-mcp-tool-name: run_kernel_vm
x-tool-url: https://ainumbers.co/tools/kernel-vm-widget.html
x-source: manifest
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.