athenahealth MCP server for AI agents

Live

SMART ON FHIR

CLINICAL RECORDS

AI

athenahealth gives your agent read-only access to clinical records through FHIR: search patients, read conditions, medications, allergies, labs, and vitals, and pull encounters, appointments, care plans, and clinical notes.

  • Per-user credentials: each call uses the actual user's token, never a shared bot.
  • Encrypted per-tenant vault: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: pre-call scope check, 90-day SIEM-exportable audit chain.
athenahealth
agent · Acme Q3
Run
What are the active medications for patient Maria Lopez?
S
athenahealth_medication_request_search
156ms
Clinical agent
Maria Lopez has 3 active medication requests: metformin 500 mg twice daily, lisinopril 10 mg daily, and atorvastatin 20 mg at bedtime.
Sources: athenahealth FHIR, 3 MedicationRequests
athenahealth
3 medications
18:29
Message Claude...

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

CALL ANY TOOL
55 tools for clinical records in athenahealth, all read-only: search and read FHIR patients, conditions, allergies, medications, observations, diagnostic reports, encounters, appointments, care plans, immunizations, and clinical documents.
athenahealth_allergy_intolerance_read
Read allergy intolerance
Retrieve one athenahealth FHIR AllergyIntolerance resource by its logical ID. Returns the AllergyIntolerance resource: allergies and intolerances recorded on a patient's chart, with substance code, clinical status, reaction, and criticality. Use this when you already have the allergy ID. Use athenahealth_allergy_intolerance_search to find allergies.
Parameters
Name
Type
Required
Description
allergy_intolerance_id
string
Required
Logical ID of the AllergyIntolerance resource (the id element, without the AllergyIntolerance/ prefix).
athenahealth_allergy_intolerance_search
Search allergy intolerance
athenahealth_appointment_read
Read appointment
athenahealth_care_plan_read
Read care plan
athenahealth_care_plan_search
Search care plan
athenahealth_condition_read
Read condition
athenahealth_condition_search
Search condition
athenahealth_device_read
Read device
athenahealth_device_search
Search device
athenahealth_document_reference_read
Read document reference
athenahealth_document_reference_search
Search document reference
athenahealth_family_member_history_read
Read family member history
athenahealth_family_member_history_search
Search family member history
athenahealth_immunization_read
Read immunization
athenahealth_immunization_search
Search immunization
athenahealth_media_read
Read media
athenahealth_medication_dispense_read
Read medication dispense
athenahealth_medication_dispense_search
Search medication dispense
athenahealth_medication_request_read
Read medication request
athenahealth_next_page
Next page
athenahealth_observation_search
Search observation
athenahealth_organization_read
Read organization
athenahealth_practitioner_read
Read practitioner
athenahealth_practitioner_search
Search practitioner
athenahealth_provenance_read
Read provenance
athenahealth_provenance_search
Search provenance
athenahealth_questionnaire_response_read
Read questionnaire response
athenahealth_questionnaire_search
Search questionnaire
athenahealth_service_request_read
Read service request
athenahealth_service_request_search
Search service request

For more tools, view docs.

Build your Agent
Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.
Python · LlamaIndex
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);

// athenahealth tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["athenahealth"], toolNames: [
    "athenahealth_patient_search",
    "athenahealth_medication_request_search",
    "athenahealth_observation_search"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "List active medications for patient Maria Lopez" }] });
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: ["athenahealth"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "List active medications for patient Maria Lopez" }],
  tools,
});

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

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "List active medications for patient Maria Lopez" }],
  tools,
});

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

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

await agent.run("List active medications for patient Maria Lopez");
Try these prompts
Copy any prompt into your agent. Each maps directly to a athenahealth tool. Click to copy, paste into your agent, done.
Patients
Copy the prompt
Copied
Find the patient Maria Lopez born 1968-04-12.
Copy the prompt
Copied
List Maria Lopez's active problems and diagnoses.
Copy the prompt
Copied
What allergies are recorded for patient 8812?
Labs and vitals
Copy the prompt
Copied
Show the latest A1c results for patient 8812.
Copy the prompt
Copied
List vital signs recorded for patient 8812 this year.
Copy the prompt
Copied
Get the most recent lipid panel report for patient 8812.
Care and documents
Copy the prompt
Copied
List the encounters for patient 8812 this year.
Copy the prompt
Copied
Show the active care plan for patient 8812.
Copy the prompt
Copied
Find clinical notes from patient 8812's March visit.
SEE HOW AUTH WORKS
Each user signs in to athenahealth once, and Scalekit stores and refreshes their tokens. Credentials stay vaulted, every call is scope checked, and every action is logged.
1
Authorize
Your user connects
athenahealth
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
2
Store
Their
athenahealth
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
3
Resolve
When your agent calls a
athenahealth
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
4
Audit
Every
athenahealth
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.
Test other agents
See the same per-user auth pattern across other healthcare connectors.
OPS
Meeting prep agent
Assemble the agenda, HubSpot attendee history, and open action items from Gmail before every meeting on the calendar.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
01.
Shared tokens break per-user analytics
A shared athenahealth token looks fine in a demo. In production every chart lookup 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.
athenahealth 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 athenahealth as the user or through a shared service account?
As the user. Each user signs in to athenahealth once, and Scalekit stores and refreshes their tokens. Every chart lookup the agent makes is attributed to that clinician in your audit trail, not a shared service account.
Where is the athenahealth 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 athenahealth?
Yes. Every athenahealth tool is read-only, so the agent can search and read FHIR resources but cannot change chart data. Filter by tool name in listScopedTools to narrow it further, for example to athenahealth_patient_search and athenahealth_observation_search. Scalekit also enforces scope checks before every API call.
What happens when a user revokes athenahealth 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.
Which patients can the agent see in athenahealth?
Only the records available to the signed-in clinician. Each search tool returns the FHIR resources that clinician can access through SMART on FHIR, and athenahealth_next_page follows the next link when a search returns more than one page.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""athenahealth"": {
""url"": ""https://mcp.scalekit.com/athenahealth"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.athenahealth]
url = ""https://mcp.scalekit.com/athenahealth""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""athenahealth"": {
""url"": ""https://mcp.scalekit.com/athenahealth"",
""type"": ""http""
}
}
}