SMART App on FHIR connector for AI agents

SMART App on FHIR tools for AI agents

CALL ANY TOOL

12 tools covering allergy.

customsmartfhir_allergy_intolerance_create

Create a new fhir allergyintolerance resource recording a pa

Create a new fhir allergyintolerance resource recording a patient's allergy or intolerance to a substance.

Parameters

Name

Type

Required

Description

code

string

Required

Code identifying the substance (RxNorm, SNOMED, or NDF-RT)

code_system

string

Required

Code system URI for the substance code

patient_id

string

Required

FHIR logical ID of the patient

category

string

Optional

Category: food, medication, environment, biologic

clinical_status

string

Optional

Clinical status: active, inactive, resolved

code_display

string

Optional

Human-readable display for the substance

customsmartfhir_allergy_intolerance_delete

Delete a fhir allergyintolerance resource by its logical id.

customsmartfhir_allergy_intolerance_read

Retrieve a single fhir allergyintolerance resource by its lo

customsmartfhir_allergy_intolerance_search

Search for fhir allergyintolerance resources using parameter

customsmartfhir_allergy_intolerance_update

Update an existing fhir allergyintolerance resource by its i

customsmartfhir_appointment_create

Create a new fhir appointment resource to book a patient vis

customsmartfhir_appointment_delete

Delete a fhir appointment resource by its logical id.

customsmartfhir_appointment_read

Retrieve a single fhir appointment resource by its logical i

customsmartfhir_appointment_search

Search for fhir appointment resources using parameters like

customsmartfhir_appointment_update

Update an existing fhir appointment resource by its id, e.g.

customsmartfhir_condition_create

Create a new fhir condition resource representing a diagnosi

customsmartfhir_condition_delete

Delete a fhir condition resource by its logical id.

Build your Agent

Same auth pattern across every framework.

from langchain_mcp_adapters.client import MultiServerMCPClient
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="customsmartfhir")

mcp = MultiServerMCPClient({
    "customsmartfhir": {
        "url": "https://mcp.scalekit.com/customsmartfhir",
        "headers": {"Authorization": "Bearer " + token}
    }
})
tools = await mcp.get_tools()

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

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "customsmartfhir" });

const openai = new OpenAI();
// Connect to MCP at https://mcp.scalekit.com/customsmartfhir
// Pass: Authorization: Bearer + token

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

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "customsmartfhir" });

const anthropic = new Anthropic();
// Connect to MCP at https://mcp.scalekit.com/customsmartfhir
// Pass: Authorization: Bearer + token

from google.adk.agents import LlmAgent
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="customsmartfhir")
# Connect to MCP at https://mcp.scalekit.com/customsmartfhir
# Pass: Authorization: Bearer + token

Try these prompts

Paste any prompt into your agent to get started.

Get started

Copy the prompt

Copied

Create a new FHIR AllergyIntolerance resource recording a patient’s allergy or intolerance to a substance?

Copy the prompt

Copied

Delete a FHIR AllergyIntolerance resource by its logical ID?

Advanced

Copy the prompt

Copied

Retrieve a single FHIR AllergyIntolerance resource by its logical ID?

Copy the prompt

Copied

Search for FHIR AllergyIntolerance resources using parameters like patient, clinical status, type, category, and critica?

SEE HOW AUTH WORKS

User authorises once. Every agent call after uses their token with scope enforcement.

Authorize

Your user connects

SMART App on FHIR

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

SMART App on FHIR

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

SMART App on FHIR

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

SMART App on FHIR

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 connectors.

No items found.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought.

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential.

// shared token
 audit → bot_service_account

 // scalekit
 audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

One connector today. Ten 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 SMART App on FHIR as the user or as a shared key?
As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the SMART App on FHIR token stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in SMART App on FHIR?
Yes. Pass a tool name filter to listScopedTools so the AI agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches SMART App on FHIR.

What happens when a user revokes SMART App on FHIR 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.

How is patient data protected under SMART on FHIR?
Every FHIR read and write runs inside the authorizing clinician's SMART scopes, so EHR access rules apply per call. Scalekit vaults the token, enforces scopes pre-call, and logs each access for compliance review.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit