BNY Mellon · Agentic Access

BNY Mellon Agentic Access

x-agentic-access generated

BNY Mellon exposes 9 API operations that an AI agent could call, of which 2 are state-changing ‘acting’ operations. This is a recommended x-agentic-access execution contract — the scope, audience, consequence tier, short-lived token constraints, and escalation each action should carry before it is handed to an autonomous agent.

By consequence: 7 read and 2 physical.

Contracts are classified heuristically from the provider’s OpenAPI and refresh on every APIs.io network build; audience is bound per deployment. The model follows Curity’s Access Intelligence (apidays Munich 2026). Browse every provider’s agent contracts at agentic-access.apis.io.

Asset ServicingBankingInstitutional BankingPaymentsTreasuryWire TransfersFortune 500
Operations: 9 Acting: 2 Human-in-the-loop: 0 Method: generated

By consequence

read 7 physical 2

Highest-consequence actions

The physical and safety-critical operations an agent could invoke — the ones that most warrant scoped tokens, tight TTLs, and escalation. Full per-operation contracts are in the source below.

MethodPathConsequenceHuman-in-loop
POST /funds-transfers physical conditional
POST /payments physical conditional

Source

Agentic Access

Raw ↑ 
generated: '2026-07-15'
method: generated
source: openapi/bny-mellon-treasury-services-api-openapi.yml
description: Recommended x-agentic-access execution contracts, classified heuristically from
  the OpenAPI. A governance starting point for exposing this API to AI agents — review and bind
  audience per deployment. See research/curity/agentic-governance/.
summary:
  operations: 9
  by_action_class:
    connected: 7
    acting: 2
  by_consequence:
    read: 7
    physical: 2
  human_in_the_loop_required: 0
operations:
- path: /accounts
  method: get
  operationId: listAccounts
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /accounts/{accountId}
  method: get
  operationId: getAccount
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /accounts/{accountId}/balances
  method: get
  operationId: getAccountBalances
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /accounts/{accountId}/transactions
  method: get
  operationId: listTransactions
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /payments
  method: post
  operationId: initiatePayment
  x-agentic-access:
    action-class: acting
    consequence: physical
    subject: required
    audience: null
    token:
      max-ttl: 300
      exchange: true
      purpose-required: true
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /payments
  method: get
  operationId: listPayments
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /payments/{paymentId}
  method: get
  operationId: getPayment
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /funds-transfers
  method: post
  operationId: initiateFundsTransfer
  x-agentic-access:
    action-class: acting
    consequence: physical
    subject: required
    audience: null
    token:
      max-ttl: 300
      exchange: true
      purpose-required: true
    escalation:
      human-in-the-loop: conditional
      triggers:
      - abnormal
      - high-value
    audit: required
- path: /funds-transfers/{transferId}
  method: get
  operationId: getFundsTransfer
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none