AristaMD Agentic Access
AristaMD exposes 42 API operations that an AI agent could call, of which 21 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: 21 read and 21 write.
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.
By consequence
Source
Agentic Access
generated: '2026-08-06'
method: generated
source: openapi/aristamd-openapi-original.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: 42
by_action_class:
acting: 21
connected: 21
by_consequence:
write: 21
read: 21
human_in_the_loop_required: 0
x-apievangelist-review:
# The per-operation contracts below are the UNMODIFIED mechanical output of
# derive-agentic-access.py. This block records where the generic heuristic is
# under-calibrated for this specific API. It does not override the generated
# classifications; it tells a reviewer what to change before deploying them.
reviewed: '2026-08-06'
domain: clinical / US protected health information
findings:
- id: consequence-underrated
detail: >-
The heuristic classifies all 21 writes as consequence "write" because none
matches its payment/order/transfer or control/stop/dispatch keyword sets.
In this API a write creates or alters a clinical record — a patient, an
eConsult, a specialist recommendation, a state transition on a care
episode. For a healthcare deployment these warrant a consequence tier at
least equivalent to "physical", not the default write tier.
affects: [POST /econsults, POST /patients, POST /HL7/messages,
'PUT /econsults/{econsultId}', 'PATCH /econsults/{econsultId}',
'DELETE /econsults/{econsultId}', 'POST /econsults/{eConsultId}/events',
'PUT /patients/{patientId}', 'PATCH /patients/{patientId}',
'DELETE /diagnostics/{diagnosticId}',
'POST /{request}/{requestId}/diagnostics/{diagnosticId}/events']
- id: human-in-the-loop-zero
detail: >-
human_in_the_loop_required is 0. For clinical record creation and care-state
transitions the correct value is "required", not the "conditional" the
heuristic assigned. Ten operations should be raised before any agent is
pointed at this API.
- id: reads-are-phi
detail: >-
Nine of the 21 read operations return protected health information
(patients, patient history, patient identifiers, top-referral patients,
Intergy passthrough, and any eConsult read, which embeds the patient). The
heuristic treats reads as low-consequence "connected"; here a read is a PHI
disclosure and needs audit and purpose-binding on a par with a write.
affects: [GET /patients, 'GET /patients/{patientId}', GET /patients/search,
'GET /patients/{patientId}/history', 'GET /patients/{patientId}/identifiers',
'GET /patients/top-patients/{length}', 'GET /intergy/patients/{id}',
GET /econsults, 'GET /econsults/{econsultId}']
- id: no-idempotency-backstop
detail: >-
The API publishes no idempotency key, so an agent retry on any acting
operation can duplicate a clinical record. Any deployment must supply
idempotency at the gateway; the API will not supply it.
- id: audience-unbound
detail: >-
`audience` is null on every operation, as designed. It must be bound per
deployment before these contracts mean anything.
disposition: >-
Treat this file as a starting point that needs clinical review, not as a
ready-to-apply policy. It is an API Evangelist artifact, not an AristaMD one.
operations:
- path: /comments
method: post
operationId: post
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /diagnostics/{diagnosticId}
method: delete
operationId: destroy
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /{request}/{requestId}/diagnostics/{diagnosticId}/events
method: post
operationId: events
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /econsults
method: get
operationId: index
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /econsults
method: post
operationId: store
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /econsults/{econsultId}
method: get
operationId: show
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /econsults/{econsultId}
method: put
operationId: update
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /econsults/{econsultId}
method: delete
operationId: destroy
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /econsults/{econsultId}
method: patch
operationId: patch
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /econsults/{econsultId}/assign-to-me
method: patch
operationId: patch
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /econsults/search
method: get
operationId: searchByStatus
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /econsults/logAvailability
method: post
operationId: LogPanelistAvailability
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /econsults/{eConsultId}/events
method: post
operationId: events
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /econsults/{eConsultId}/heartbeat
method: post
operationId: events
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /HL7/messages
method: post
operationId: store
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /intergy/patients/{id}
method: get
operationId: index
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /panelists
method: get
operationId: index
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /panelists/getNextAvailable/{code}/{patient_id}
method: get
operationId: index
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /patients
method: get
operationId: index
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /patients
method: post
operationId: store
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /patients/{patientId}
method: get
operationId: show
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /patients/{patientId}
method: put
operationId: update
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /patients/{patientId}
method: patch
operationId: patch
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /patients/search
method: get
operationId: show
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /patients/top-patients/{length}
method: get
operationId: getTopReferralPatients
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /patients/{patientId}/history
method: get
operationId: history
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /patients/{patientId}/identifiers
method: get
operationId: identifiers
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /reviews
method: get
operationId: get
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /reviews
method: post
operationId: post
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /reviews/{id}
method: get
operationId: get
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /reviews/{id}
method: put
operationId: post
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /specialties/{specialtyId}
method: get
operationId: show
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /specialties/{specialtyId}
method: put
operationId: update
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /specialties
method: post
operationId: store
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /specialties/withAvailablePanelists/{filter}
method: get
operationId: index
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /users
method: get
operationId: index
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /users/{user_id}
method: get
operationId: show
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /users/search
method: post
operationId: index
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /users/update
method: patch
operationId: update
x-agentic-access:
action-class: acting
consequence: write
subject: required
audience: null
token:
max-ttl: 900
escalation:
human-in-the-loop: conditional
triggers:
- abnormal
- high-value
audit: required
- path: /workup-checklists/specialties
method: get
operationId: specialties
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /workup-checklists/specialties/{specialtyCode}/chief-complaints
method: get
operationId: chiefComplaints
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
- path: /workup-checklists/specialties/{specialtyCode}/chief-complaints/{chiefComplaintCode}
method: get
operationId: searchBySpecialtyAndChiefComplaint
x-agentic-access:
action-class: connected
consequence: read
subject: optional
token:
max-ttl: 3600
audit: none
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.
Call it yourself
curl for this page
curl "https://apis.io/api/v1/search?q=aristamd-agentic-access&limit=10"
curl "https://apis.io/api/v1/tags/aristamd-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.
A second provider on the same verified email joins the account you already have.