Oracle Health (Cerner) connector for AI agents

Tools your scheduling agent reaches for on Oracle Health, scoped per user.

CALL ANY TOOL

82 tools for clinical records in Oracle Health over FHIR: search and read patients, encounters, conditions, medications, and observations, book and cancel appointments, generate CCDs, and write notes, problems, vitals, and messages.

oraclehealth_allergy_intolerance_create

Create allergy intolerance

Record a new allergy or intolerance on a patient's chart in Oracle Health. Returns an empty body with HTTP 201 on success; Oracle Health puts the new resource's URL in the Location header and its version in the ETag header. Use it to add an allergy. Use oraclehealth_allergy_intolerance_update to change an existing one, and oraclehealth_allergy_intolerance_search to check for duplicates first.

Parameters

Name

Type

Required

Description

clinical_status

string

Required

Clinical status of the allergy: active, inactive, or resolved. Example: active. One of: `active`, `inactive`, `resolved`.

code

string

Required

Code of the allergen substance in code_system. Use a substance code, not a finding or disorder code: Oracle Health returns a 500 error for findings such as SNOMED 91936005 (allergy to penicillin). Example: 227493005 (cashew nut, SNOMED substance)

code_system

string

Required

Code system of the allergen. Example: http://snomed.info/sct (RxNorm http://www.nlm.nih.gov/research/umls/rxnorm is also common)

patient_id

string

Required

FHIR logical ID of the patient, without the 'Patient/' prefix. Find it with oraclehealth_patient_search. Example: 12345

category

string

Required

Condition category: problem-list-item or encounter-diagnosis (the only two Oracle Health accepts on create). An encounter-diagnosis needs encounter_id. Example: problem-list-item. One of: `problem-list-item`, `encounter-diagnosis`.

clinical_status

string

Required

Clinical status: active, recurrence, relapse, inactive, remission, or resolved. Only active is allowed for encounter-diagnosis. Example: active. One of: `active`, `recurrence`, `relapse`, `inactive`, `remission`, `resolved`.

code

string

Required

Condition code in code_system. Example: 44054006 (type 2 diabetes mellitus)

code_system

string

Required

Code system of the condition. Example: http://snomed.info/sct (ICD-10-CM is http://hl7.org/fhir/sid/icd-10-cm)

patient_id

string

Required

FHIR logical ID of the patient, without the 'Patient/' prefix. Find it with oraclehealth_patient_search. Example: 12345

abatement_date_time

string

Optional

When the condition resolved. Not allowed for encounter-diagnosis. ISO 8601 date-time with a time component and offset. Example: 2024-01-15T09:30:00Z

code_display

string

Optional

Display name for the code. Example: Type 2 diabetes mellitus

encounter_id

string

Optional

FHIR logical ID of the encounter, without the 'Encounter/' prefix. Required when category is encounter-diagnosis. Example: 67890

note

string

Optional

Free-text note about the condition. Can't be changed later. Example: Diet-controlled.

onset_date_time

string

Optional

When the condition began. Stored as a GMT date. ISO 8601 date-time with a time component and offset. Example: 2024-01-15T09:30:00Z

verification_status

string

Optional

Verification status: unconfirmed, provisional, differential, or confirmed. Example: confirmed. One of: `unconfirmed`, `provisional`, `differential`, `confirmed`.

oraclehealth_condition_search

Search condition

oraclehealth_device_read

Read device

oraclehealth_device_search

Search device

oraclehealth_encounter_read

Read encounter

oraclehealth_encounter_search

Search encounter

Search encounters in Oracle Health for a patient, account, or identifier, optionally by status and date. Returns a FHIR Bundle of Encounter resources (encounter class, type, status, period, location, participants, and reason) with a next link when more pages exist. If the result has a `next` link, use `oraclehealth_next_page` to get more. Use oraclehealth_encounter_search to find or list records. Use oraclehealth_encounter_read to fetch one known ID.

Parameters

Name

Type

Required

Description

_count

integer

Optional

Maximum number of results per page. Example: 20

_id

string

Optional

Logical ID of the encounter to return. Use instead of the other filters; Oracle Health rejects _id combined with most other parameters. Example: 12345

_lastUpdated

array

Optional

Filter encounters by when they were last updated. Pass one or two values as a JSON array; each value carries a FHIR prefix (eq, ge, gt, le, lt) and is sent as a repeated query parameter. Two values must form a range: the lower one with ge or gt, the upper one with le or lt. Example: ["ge2024-01-01T00:00:00Z"]

account

string

Optional

Financial account ID to return encounters for (provider persona only). Example: F000000

date

array

Optional

Filter by encounter period. Each value must use ge, gt, le, or lt. Pass one or two values as a JSON array; each value carries a FHIR prefix (eq, ge, gt, le, lt) and is sent as a repeated query parameter. Two values must form a range: the lower one with ge or gt, the upper one with le or lt. Example: ["ge2024-01-01T00:00:00Z", "lt2024-02-01T00:00:00Z"]

identifier

string

Optional

Encounter identifier as system|value, or the value alone (for example a financial number). Example: urn:oid:1.2.3.4|000000

patient

string

Optional

FHIR logical ID of the patient whose encounters to return. Required unless _id, account, or identifier is given. Oracle Health's docs say _count and status should be sent with patient. Find the ID with oraclehealth_patient_search. Example: 12345

status

string

Optional

Encounter status: planned, in-progress, finished, or cancelled. Example: finished. One of: `planned`, `in-progress`, `finished`, `cancelled`.

oraclehealth_immunization_read

Read immunization

oraclehealth_immunization_search

Search immunization

oraclehealth_immunization_update

Update immunization

oraclehealth_medication_administration_read

Read medication administration

oraclehealth_medication_administration_search

Search medication administration

oraclehealth_medication_request_create

Create medication request

oraclehealth_medication_request_read

Read medication request

oraclehealth_nutrition_order_search

Search nutrition order

oraclehealth_organization_read

Read organization

oraclehealth_patient_search

Search patient

Search patients in Oracle Health by name, birth date, identifier, phone, email, postal code, or gender. Returns a FHIR Bundle of Patient resources (demographics, identifiers (such as MRN), contact details, and links to related people) with a next link when more pages exist. If the result has a `next` link, use `oraclehealth_next_page` to get more. Use oraclehealth_patient_search to find or list records. Use oraclehealth_patient_read to fetch one known ID. Oracle Health returns a 422 error when more than 1000 patients match a search, so narrow name searches with birthdate or gender.

Parameters

Name

Type

Required

Description

_count

integer

Optional

Maximum number of results per page. Example: 20

_id

string

Optional

Logical ID of the patient to return. Use instead of the other filters; Oracle Health rejects _id combined with most other parameters. Example: 12345

address_postalcode

string

Optional

Postal code of the patient's address. Example: 00000

birthdate

array

Optional

Filter by date of birth (date only, no time). Pass one or two values as a JSON array; each value carries a FHIR prefix (eq, ge, gt, le, lt) and is sent as a repeated query parameter. Two values must form a range: the lower one with ge or gt, the upper one with le or lt. Example of an exact date: ["eq2000-01-01"]. Example: ["ge1990-01-01", "le1990-12-31"]

string

Optional

Patient email address. Example: patient@example.com

family

string

Optional

Start of the patient's family (last) name. Example: Testpatient

gender

string

Optional

Administrative gender: male, female, other, or unknown. One of: `male`, `female`, `other`, `unknown`.

given

string

Optional

Start of the patient's given (first) name. Requires family. Example: Testname

identifier

string

Optional

Patient identifier as system|value, or just the value to search every identifier system (for example an MRN). Example: urn:oid:1.2.3.4|0000000

name

string

Optional

Start of any part of the patient's name (given or family). At least 2 characters. Don't combine with family or given. Example: Testp

phone

string

Optional

Patient phone number. Example: 5550100000

oraclehealth_procedure_read

Read procedure

oraclehealth_procedure_search

Search procedure

oraclehealth_questionnaire_response_read

Read questionnaire response

oraclehealth_related_person_search

Search related person

oraclehealth_service_request_read

Read service request

For more tools, view docs.

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Oracle Health tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["oraclehealth"], toolNames: [
    "oraclehealth_patient_search",
    "oraclehealth_slot_search",
    "oraclehealth_appointment_create"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Find Maria Lopez and book her into Dr. Chen's next open follow-up slot" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["oraclehealth"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Find Maria Lopez and book her into Dr. Chen's next open follow-up slot" }],
  tools,
});

// Execute the tool call with the user's vaulted Oracle Health OAuth token
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["oraclehealth"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Find Maria Lopez and book her into Dr. Chen's next open follow-up slot" }],
  tools,
});

// Tool call runs with the user's vaulted Oracle Health OAuth token
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["oraclehealth"] }, pageSize: 100,
});

const agent = new Agent({
  name: "scheduling_agent",
  model: "gemini-2.5-pro",
  instruction: "Oracle Health tools scoped to this user",
  tools,
});

await agent.run("Find Maria Lopez and book her into Dr. Chen's next open follow-up slot");

Try these prompts

Copy any prompt into your agent. Each maps directly to a Oracle Health (Cerner) tool. Click to copy, paste into your agent, done.

Patient records

Copy the prompt

Copied

Search for patients named Maria Lopez born in 1984.

Copy the prompt

Copied

Generate a Continuity of Care Document for this patient.

Copy the prompt

Copied

List this patient's lab results from the last 30 days.

Scheduling

Copy the prompt

Copied

Find open follow-up slots with Dr. Chen next week.

Copy the prompt

Copied

Book this patient into the Monday 8:40am slot.

Copy the prompt

Copied

Cancel this patient's appointment on Friday.

Charting and messages

Copy the prompt

Copied

Write a final clinical note to this patient's chart.

Copy the prompt

Copied

Add hypertension to this patient's problem list.

Copy the prompt

Copied

Send a message to Dr. Chen's inbox about this patient's results.

SEE HOW AUTH WORKS

Each user signs in to Oracle Health once, and Scalekit stores and refreshes their tokens. Credentials stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

Oracle Health (Cerner)

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Oracle Health (Cerner)

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Oracle Health (Cerner)

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Oracle Health (Cerner)

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other healthcare connectors.

Support and Ops Teams

Meeting prep

Pulls agenda, participant context, and open action items before every meeting.

Engineering Teams

Slack triage

Polls Slack for new messages, classifies bugs and support requests with a LangGraph router, files GitHub issues or Zendesk tickets, and confirms in the thread.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Oracle Health token looks fine in a demo. In production every chart entry and booking looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Oracle Health today. Ten connectors tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Oracle Health as the user or through a shared service account?

As the user. Each user signs in to Oracle Health once with SMART on FHIR, and Scalekit stores and refreshes their tokens. Every chart read and write in your audit trail is attributed to that user, not a shared service account.

Where is the Oracle Health OAuth token stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in Oracle Health?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example the read and search tools without oraclehealth_appointment_cancel or oraclehealth_document_reference_create. The connector has no delete tools. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Oracle Health access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Can the agent message clinicians in Oracle Health?

Yes. oraclehealth_communication_create sends a message to practitioners' or pools' Oracle Health inboxes, and oraclehealth_communication_search reads inbox messages for a recipient by category or received date.