Wattwatchers · Agentic Access

Wattwatchers Agentic Access

x-agentic-access generated

Wattwatchers exposes 14 API operations that an AI agent could call, of which 1 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: 13 read and 1 physical.

1 operation are classed safety-critical and should require human-in-the-loop approval at runtime.

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.

EnergyAustraliaUtilitiesElectricitySmart MeteringEnergy DataIoTSolarDERDemand Response
Operations: 14 Acting: 1 Human-in-the-loop: 1 Method: generated

By consequence

read 13 physical 1

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
PATCH /devices/{device-id} physical required

Source

Agentic Access

Raw ↑ 
generated: '2026-07-27'
method: generated
source: openapi/wattwatchers-rest-api-v3-openapi.json
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: 14
  by_action_class:
    connected: 13
    acting: 1
  by_consequence:
    read: 13
    physical: 1
  human_in_the_loop_required: 1
  curated_operations: 1
operations:
- path: /devices
  method: get
  operationId: listDevices
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /devices/{device-id}
  method: get
  operationId: getDevice
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /devices/{device-id}
  method: patch
  operationId: updateDevice
  curated: true
  curation_note: 'Raised from the heuristic default (consequence write / human-in-the-loop conditional)
    to consequence PHYSICAL with human-in-the-loop REQUIRED. This single operation carries the API''s
    entire actuation surface: the `switches` array in the PATCH body opens or closes a real relay on +3SW
    hardware (6M+3SW, 6W+3SW, 3RM+3SW), energising or de-energising a live electrical circuit. Wattwatchers
    document a dedicated switching guide for it. The keyword heuristic could not see this because the
    path and method carry no control/dispatch token — the consequence lives in the request body. Evidence:
    https://docs.wattwatchers.com.au/api/tips/switching-example.html and openapi #/components/schemas/DevicePatchBody.switches.'
  x-agentic-access:
    action-class: acting
    consequence: physical
    subject: required
    audience: null
    token:
      max-ttl: 300
      exchange: required
      purpose-required: true
    escalation:
      human-in-the-loop: required
      triggers:
      - switch-state-change
      - abnormal
      - high-value
    audit: required
- path: /devices/channel-categories
  method: get
  operationId: getChannelCategories
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /devices/models
  method: get
  operationId: getDeviceModels
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /short-energy/{device-id}
  method: get
  operationId: getShortEnergyData
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /short-energy/{device-id}/first
  method: get
  operationId: getFirstShortEnergyData
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /short-energy/{device-id}/latest
  method: get
  operationId: getLatestShortEnergyData
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /long-energy/{device-id}
  method: get
  operationId: getLongEnergyData
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /long-energy/{device-id}/first
  method: get
  operationId: getFirstLongEnergyData
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /long-energy/{device-id}/latest
  method: get
  operationId: getLatestLongEnergyData
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /modbus/{device-id}
  method: get
  operationId: getModbusData
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /modbus/{device-id}/first
  method: get
  operationId: getFirstModbusData
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /modbus/{device-id}/latest
  method: get
  operationId: getLatestModbusData
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
curation: updateDevice raised to consequence=physical / human-in-the-loop=required after review; see the
  curation_note on that operation.

Work with this as data

Every access contract here is available over the APIs.io API and to AI agents over MCP. Agentic Access is not yet its own endpoint on the v1 API. Reach it through catalog search and the tag graph, or the MCP server.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for agentic access

3 MCP tools reach this
  • 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.
All 92 tools →

Call it yourself

curl for this page
Search the catalog 
curl "https://apis.io/api/v1/search?q=wattwatchers-agentic-access&limit=10"
Everything under a tag 
curl "https://apis.io/api/v1/tags/wattwatchers-agentic-access"

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.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.