MEDITECH connector for AI agents

Tools your clinical agent reaches for on MEDITECH, scoped per user.

CALL ANY TOOL

61 tools for clinical records in MEDITECH over FHIR: search and read patients, encounters, conditions, medications, observations, documents, and messages, pull whole records, and save questionnaire responses.

meditech_allergy_intolerance_read

Read allergy intolerance

Get one allergy from MEDITECH by its FHIR ID. Returns a FHIR AllergyIntolerance resource with substance code, clinical and verification status, criticality, reactions, and recorded date. Use meditech_allergy_intolerance_read to fetch one known ID. Use meditech_allergy_intolerance_search to find allergies.

Parameters

Name

Type

Required

Description

allergy_intolerance_id

string

Required

FHIR logical ID of the allergy, without the 'AllergyIntolerance/' prefix. Example: 12345

meditech_allergy_intolerance_search

Search allergy intolerance

meditech_binary_read

Read binary

meditech_care_plan_search

Search care plan

meditech_care_team_read

Read care team

meditech_communication_search

Search communication

Search clinical messages in MEDITECH by patient, sender, recipient, sent date, or thread. Returns a FHIR Bundle of Communication resources (status, sender, recipients, sent time, subject patient, topic, thread links, and the message payload). If the result has a `next` link, use `meditech_next_page` to get more. Use meditech_communication_search to find or list records. Use meditech_communication_read to fetch one known ID.

Parameters

Name

Type

Required

Description

_count

integer

Optional

Maximum number of messages to return on one page. MEDITECH sets the default page size. Example: 20

_id

string

Optional

Logical ID of a single message to return. Use it on its own, without the other filters. Example: 12345

in_response_to

string

Optional

Reference to a message; returns only its direct replies. Example: Communication/11111

in_response_to_below

string

Optional

Reference to a message; returns every reply below it in the thread. Example: Communication/11111

in_response_to_missing

boolean

Optional

Set true to return only top-level messages (thread starters), or false to return only replies. Example: true

part_of

string

Optional

Reference to the root message of a thread; returns every message in that thread. Example: Communication/11111

patient

string

Optional

FHIR logical ID of the patient the messages are about. Example: 12345

recipient

string

Optional

Reference to a patient or practitioner who is one of the recipients. Example: Practitioner/67890

sender

string

Optional

Reference to the message sender: a Patient, Practitioner or RelatedPerson reference or ID. Example: Practitioner/67890

sent

array

Optional

Filter messages by the date and time they were sent. Pass one or two values as a JSON array; each value can start with a FHIR prefix (eq, ge, gt, le, lt) and is sent as a repeated query parameter. Use ge and le together for a range. Example: ["ge2024-01-01", "le2024-12-31"]

subject

string

Optional

Reference to the patient the messages are about, as an ID or Patient/<id>. Use patient or subject, not both. Example: Patient/12345

meditech_condition_read

Read condition

meditech_coverage_search

Search coverage

meditech_device_read

Read device

meditech_diagnostic_report_search

Search diagnostic report

meditech_document_reference_docref

Document reference docref

meditech_document_reference_read

Read document reference

meditech_encounter_search

Search encounter

meditech_goal_read

Read goal

meditech_immunization_search

Search immunization

meditech_location_read

Read location

meditech_medication_dispense_read

Read medication dispense

meditech_medication_dispense_search

Search medication dispense

meditech_medication_request_read

Read medication request

meditech_observation_search

Search observation

meditech_organization_read

Read organization

meditech_patient_search

Search patient

meditech_practitioner_read

Read practitioner

meditech_practitioner_search

Search practitioner

meditech_procedure_read

Read procedure

meditech_questionnaire_response_create

Create questionnaire response

meditech_questionnaire_response_read

Read questionnaire response

meditech_questionnaire_response_search

Search questionnaire response

meditech_questionnaire_response_update

Update questionnaire response

meditech_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);

// MEDITECH tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["meditech"], toolNames: [
    "meditech_patient_search",
    "meditech_observation_search",
    "meditech_document_reference_docref"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Find the patient with MRN 100482 and list their lab results from the last 30 days" }] });

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: ["meditech"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Find the patient with MRN 100482 and list their lab results from the last 30 days" }],
  tools,
});

// Execute the tool call with the user's vaulted MEDITECH 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: ["meditech"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Find the patient with MRN 100482 and list their lab results from the last 30 days" }],
  tools,
});

// Tool call runs with the user's vaulted MEDITECH 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: ["meditech"] }, pageSize: 100,
});

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

await agent.run("Find the patient with MRN 100482 and list their lab results from the last 30 days");

Try these prompts

Copy any prompt into your agent. Each maps directly to a MEDITECH tool. Click to copy, paste into your agent, done.

Patient records

Copy the prompt

Copied

Search for the patient with MRN 100482.

Copy the prompt

Copied

Pull this patient's whole record in one call.

Copy the prompt

Copied

Get a Continuity of Care Document for this patient's last encounter.

Clinical data

Copy the prompt

Copied

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

Copy the prompt

Copied

Show this patient's active medication orders.

Copy the prompt

Copied

List this patient's admissions from this year.

Forms and messages

Copy the prompt

Copied

List completed questionnaires for this patient.

Copy the prompt

Copied

Save this intake questionnaire response for the patient.

Copy the prompt

Copied

Search clinical messages sent about this patient this week.

SEE HOW AUTH WORKS

Each user signs in to MEDITECH 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

MEDITECH

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

MEDITECH

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

MEDITECH

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

MEDITECH

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 MEDITECH token looks fine in a demo. In production every chart read 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.

MEDITECH 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 MEDITECH as the user or through a shared service account?

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

Where is the MEDITECH 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 MEDITECH?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example the read and search tools without meditech_questionnaire_response_create or meditech_questionnaire_response_update, the only tools that write to MEDITECH. Scalekit also enforces scope checks before every API call.

What happens when a user revokes MEDITECH 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.

What can the agent write to MEDITECH?

Only questionnaire responses. meditech_questionnaire_response_create saves a completed or in-progress form for a patient, and meditech_questionnaire_response_update replaces an existing one with an edited copy. Every other tool reads records.