Mirobody
Lab results to LOINC codes and UCUM units, symptoms and diagnoses to ICPC-3. Offline, no API key.
作者による説明(英語の原文)
MCP server for Tebra/Kareo practice management — patients, billing, scheduling, FHIR (45 tools)
この3つを1つのスコアにまとめることはしません。意見、測定、人気はそれぞれ別のものだからです。
このサーバーのやさしい解説はまだ書いていません。以下はレジストリから読み取った事実です。
使っているAIアプリを選んで、設定をコピーしてください。
TEBRA_SOAP_USER, TEBRA_SOAP_PASSWORD, TEBRA_CUSTOMER_KEY「秘密」と表示された値は、あなたのアカウントの鍵です。絶対に人に教えたり、チャットに貼り付けたりしないでください。
必要なもの
どのアプリを使っていますか?
上でアプリを選んでください。選んだアプリを覚えておくので、次からはボタンに「…にインストール」と表示されます。
Claude Desktop → Settings → Developer → Edit Config を開き、claude_desktop_config.json にこれを貼り付けます
{
"mcpServers": {
"tebra": {
"command": "npx",
"args": [
"-y",
"tebra-mcp-server"
],
"env": {
"TEBRA_SOAP_USER": "your-value",
"TEBRA_SOAP_PASSWORD": "your-value",
"TEBRA_CUSTOMER_KEY": "your-value"
}
}
}
}ターミナルでこれを実行します
claude mcp add tebra --env TEBRA_SOAP_USER=your-value --env TEBRA_SOAP_PASSWORD=your-value --env TEBRA_CUSTOMER_KEY=your-value -- npx -y tebra-mcp-server動かす前に、空欄の値を入力してください。
プロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます
{
"mcpServers": {
"tebra": {
"command": "npx",
"args": [
"-y",
"tebra-mcp-server"
],
"env": {
"TEBRA_SOAP_USER": "your-value",
"TEBRA_SOAP_PASSWORD": "your-value",
"TEBRA_CUSTOMER_KEY": "your-value"
}
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
プロジェクトの .vscode/mcp.json に貼り付けます
{
"servers": {
"tebra": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"tebra-mcp-server"
],
"env": {
"TEBRA_SOAP_USER": "your-value",
"TEBRA_SOAP_PASSWORD": "your-value",
"TEBRA_CUSTOMER_KEY": "your-value"
}
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
これはパソコンで動くサーバーですが、ChatGPTがつなげるのはインターネット上のサーバーだけです。ほかのアプリを選んでください。
選んだアプリは、この端末のCookieに保存されます。アカウントは不要です。
この設定は、作者のレジストリ登録情報から作成しています。READMEと違う場合は、READMEに従ってください。
パソコンで動くサーバーです。インストールすると、ツール一覧がAIアプリに表示されます。
誰でも見られる情報をチェックしており、コードは読んでいません。当てはまらない項目は数に入れていません。 · 2026年11月6日にチェック
公開者(jamesrosingmd.com)がリポジトリの所有者(jamesrosing)ではありません。別の人が登録した可能性があります
このリポジトリはまだGitHubから読み取っていません
このリポジトリはまだGitHubから読み取っていません
これはパソコンで動くため、インターネット上のエンドポイントはありません
パソコンで動き、代わりにローカルの設定を使います
パソコンで動くサーバーです。ツール一覧を読み取れるのは、インターネット上のエンドポイントがある場合だけです
レジストリでこのカテゴリにある有効なすべてのサーバーと比較しています。スターは、公開者がリポジトリの所有者である場合だけ数えます。
当てはまる基本チェック1項目のうち0項目に合格しました。コードは読んでいません。キーやトークンを追加する前に、サーバーがどんなアクセスを求めているかを確認し、必要な権限だけを持つキーを使ってください。
入力が必要なもの:TEBRA_SOAP_USER, TEBRA_SOAP_PASSWORD, TEBRA_CUSTOMER_KEY
あなたのパソコンで動きます。必要なときにAIアプリが起動し、データは作者のサーバーを通りません(サーバー自体がオンラインサービスを呼び出す場合を除きます)。
GitHubリポジトリの最終更新は–、最新バージョン(0.2.5)がレジストリに届いたのは6 か月前です。
Claude Desktop、Claude Code、Cursor、VS CodeなどのMCP対応アプリで使えます。パソコンにNode.jsも必要です。
同じカテゴリには:Mirobody, FHIR MCP Server, Google Health MCP
同じカテゴリで、ほかの作者が作ったサーバー。スターの多い順。
カードの見方:★ GitHubスターi3つの柱:レビュー · チェック · 利用状況i更新=最新バージョンをレジストリに公開した日i
Lab results to LOINC codes and UCUM units, symptoms and diagnoses to ICPC-3. Offline, no API key.
MCP server providing seamless access to FHIR APIs for AI tools and healthcare applications
Privacy-first unofficial Google Health API v4 MCP server for health, sleep, activity, HR agents
作者のリポジトリから書かれたとおりにコピーしたものです。PopNx MCPは内容を確認・推奨していません。HTML、画像、スクリプトは取り除いています。リンクはこのサイトの外へ移動します。
MCP server for Tebra (formerly Kareo) practice management. Connects your existing Tebra account to Claude and other MCP-compatible AI agents, exposing 34 SOAP tools and 13 FHIR clinical tools for patients, encounters, appointments, billing, documents, insurance, and clinical data. Every request body is generated from the live Tebra WSDL contract (member names and sequence order verified against KareoServices.svc?xsd=xsd0/xsd7), with a regression suite locking the wire format in place. No data is accessible without valid Tebra API credentials.
This is an independent open-source project. It is not affiliated with, endorsed by, or supported by Tebra Technologies, Inc.; "Tebra" and "Kareo" are trademarks of their owner, used here only to identify the API this server talks to. Tool results contain protected health information: sending them to Claude requires a Claude plan under which Anthropic signs a Business Associate Agreement (BAA). Consumer Claude plans are not covered, and confirming coverage is the responsibility of the practice operating the server.
Do not want to manage credentials, hosting, and updates yourself? DOCK is the managed version of this server: encrypted per-practice auth, audit logs, draft-first write actions, and a workflow library. Founding practices lock lifetime pricing: Front Desk $49/mo (Zenoti), Billing Desk $99/mo (Tebra; DOCK signs its own BAA with the practice, separate from Anthropic's), Full Practice $129/mo (both). https://dockhq.vercel.app
npx tebra-mcp-server
| Variable | Required | Description |
|---|---|---|
TEBRA_SOAP_USER | Yes | SOAP API user (email) |
TEBRA_SOAP_PASSWORD | Yes | SOAP API password |
TEBRA_CUSTOMER_KEY | Yes | Customer key from Tebra PM admin |
TEBRA_SOAP_ENDPOINT | No | Override SOAP endpoint (for testing) |
| Variable | Required | Description |
|---|---|---|
TEBRA_FHIR_CLIENT_ID | For FHIR | OAuth2 client ID from Tebra appSphere registration |
TEBRA_FHIR_PRIVATE_KEY_PATH | For FHIR (JWKS registrations) | Path to the PEM (PKCS#8) private key for SMART Backend Services private_key_jwt; its public half is the JWKS you registered with Tebra. Takes precedence over the secret |
TEBRA_FHIR_KID | With the key path | The kid of that public key in your published JWKS (required whenever the key path is set) |
TEBRA_FHIR_CLIENT_SECRET | For FHIR (secret registrations) | OAuth2 client secret — the fallback used only when no key path is set |
TEBRA_FHIR_BASE_URL | No | FHIR R4 base URL (defaults to https://fhir.prd.cloud.tebra.com/fhir-request) |
TEBRA_FHIR_TOKEN_URL | No | OAuth2 token endpoint (defaults to Tebra production) |
TEBRA_FHIR_SCOPE | No | OAuth2 scope (defaults to system/*.read; match your appSphere registration) |
FHIR credentials are obtained through Tebra appSphere. The server uses the OAuth2 client credentials flow with automatic token caching, refresh 60s before expiry, and a one-shot retry on 401. Two client authentications are supported: SMART Backend Services `private_key_jwt` (an appSphere Backend App registered as "Confidential (URL for JWKS)" — the server signs an RS384 client assertion with iss=sub=client id, aud=token URL, a 5-minute exp and a unique jti, sent as client_assertion with client_assertion_type=urn:ietf:params:oauth:client-assertion-type:jwt-bearer; the private key is read from disk once and never transmitted) and the legacy `client_secret` flow. Set the key path for the former, the secret for the latter. Note: both the practice and the backend-service client must be activated by Tebra Customer Care before tokens are issued — a 401 can mean "not yet activated" rather than "bad credentials".
Add to .mcp.json in your project root:
{
"mcpServers": { "tebra": { "command": "npx", "args": ["-y", "tebra-mcp-server"], "env": { "TEBRA_SOAP_USER": "user@practice.com", "TEBRA_SOAP_PASSWORD": "your-password", "TEBRA_CUSTOMER_KEY": "your-customer-key", "TEBRA_FHIR_CLIENT_ID": "optional-fhir-client-id", "TEBRA_FHIR_CLIENT_SECRET": "optional-fhir-client-secret" } } } }
Add to your claude_desktop_config.json:
{
"mcpServers": { "tebra": { "command": "npx", "args": ["-y", "tebra-mcp-server"], "env": { "TEBRA_SOAP_USER": "user@practice.com", "TEBRA_SOAP_PASSWORD": "your-password", "TEBRA_CUSTOMER_KEY": "your-customer-key" } } } }
Add to your MCP settings:
{
"mcpServers": { "tebra": { "command": "npx", "args": ["-y", "tebra-mcp-server"], "env": { "TEBRA_SOAP_USER": "user@practice.com", "TEBRA_SOAP_PASSWORD": "your-password", "TEBRA_CUSTOMER_KEY": "your-customer-key" } } } }
| Tool | Description |
|---|---|
tebra_search_patients | Search patients by name, DOB range, insurance, practice, and more (16 server-side filters) |
tebra_get_patient | Get full patient record (by Tebra ID or external ID) with cases, insurance policies, and authorizations |
tebra_create_patient | Register a new patient with demographics, insurance, and guarantor |
tebra_update_patient | Update patient demographics and contact info |
tebra_get_all_patients | Bulk patient retrieval with pagination (for sync operations) |
| Tool | Description |
|---|---|
tebra_get_appointments | Search appointments by date range, resource (provider), patient, status, location |
tebra_get_appointment_detail | Get full appointment detail including recurrence, group data, and resources |
tebra_create_appointment | Create an appointment (provider, location, start time + duration/end) |
tebra_update_appointment | Update or reschedule an existing appointment |
tebra_update_appointment_status | Change only the status (Confirmed, CheckedIn, NoShow, Cancelled, ...) |
tebra_delete_appointment | Permanently delete an appointment |
tebra_get_appointment_reasons | List configured appointment types/reasons for the practice |
tebra_create_appointment_reason | Create a new appointment type/reason |
| Tool | Description |
|---|---|
tebra_get_encounter | Get encounter details with status, providers, and service line IDs |
tebra_create_encounter | Create an encounter (superbill) with per-line diagnoses and procedures |
tebra_update_encounter_status | Workflow transitions: Draft -> Submitted -> Approved / Rejected / Unpayable |
tebra_get_charges | Search charges with 18 filters (dates, patient name, provider, status) |
tebra_get_payments | Search payment records by post date, payer, batch, reference number |
tebra_create_payment | Post a payment to a patient account |
| Tool | Description |
|---|---|
tebra_get_patient_authorizations | Get all authorizations with status, remaining visits, and CPT codes |
tebra_check_insurance_eligibility | Check eligibility from on-file insurance data |
| Tool | Description |
|---|---|
tebra_get_providers | List all providers with IDs, specialties, and NPI numbers |
tebra_get_service_locations | List practice locations with addresses and contact info |
tebra_get_practices | Get practice metadata (name, tax ID, billing info) |
tebra_get_procedure_codes | Get procedure code catalog with descriptions and default fees |
| Tool | Description |
|---|---|
tebra_create_document | Upload a document (PDF, image) to a patient's chart |
tebra_delete_document | Remove a document from a patient's chart |
| Tool | Description |
|---|---|
tebra_get_transactions | Get granular transaction data for financial reporting |
| Tool | Description |
|---|---|
tebra_validate_connection | Health check -- verifies SOAP credentials and connectivity |
tebra_get_throttles | Get current API rate limit status and remaining quota |
tebra_register_external_vendor | Register an external vendor for ID linking |
tebra_get_external_vendors | List registered external vendors |
tebra_update_patient_external_id | Link an external system ID to a Tebra patient |
tebra_set_primary_patient_case | Promote an existing patient case to primary (by case ID) |
These tools access clinical data via the Tebra FHIR R4 API. They require separate FHIR credentials (see Environment Variables above). If FHIR credentials are not configured, these tools will not be registered.
FHIR patient IDs are a different identifier space from SOAP patient IDs — use tebra_fhir_search_patients to resolve them. All FHIR searches follow Bundle pagination automatically (up to 10 pages), and the three resources where Tebra requires a second search parameter (MedicationRequest intent, CarePlan category, CareTeam status) get sensible defaults so they don't silently return empty.
| Tool | Description |
|---|---|
tebra_fhir_search_patients | Find FHIR patient IDs by name, birthdate, or identifier |
tebra_fhir_get_allergies | Patient allergy and intolerance list |
tebra_fhir_get_medications | Active and historical medication list |
tebra_fhir_get_conditions | Problem list / active conditions |
tebra_fhir_get_vitals | Recent vital signs (BP, HR, temp, weight, BMI) |
tebra_fhir_get_lab_results | Lab results and observation values |
tebra_fhir_get_immunizations | Vaccination records |
tebra_fhir_get_procedures | Procedures performed |
tebra_fhir_get_care_plans | Active care plans |
tebra_fhir_get_care_team | Care team members and roles |
tebra_fhir_get_diagnostic_reports | Diagnostic reports (radiology, pathology) |
tebra_fhir_get_documents | Clinical documents (CDA, notes) |
tebra_fhir_get_devices | Implantable devices (UDI data) |
The SOAP client enforces a minimum interval between calls per action, mirroring the throttling thresholds in the Tebra API Technical Guide. When a tool is called more frequently than its limit allows, the client sleeps just long enough to satisfy the interval before sending the request — calls are delayed, never dropped.
| Action | Min interval between calls |
|---|---|
GetPatient | 250 ms |
GetPractices, GetProviders, GetServiceLocations, GetProcedureCodes, GetEncounterDetails, GetAppointment, all Create* / Update* / Delete* | 500 ms |
GetPatients, GetAppointments, GetAppointmentReasons, GetCharges, GetPayments, GetTransactions, GetExternalVendors, UpdatePatient | 1000 ms |
GetAllPatients, GetThrottles | 5000 ms |
On top of client-side throttling, every SOAP call retries up to 3 times with exponential backoff (1s, 2s, 4s) before surfacing an error. Use tebra_get_throttles to query Tebra's server-side rate limit counters in real time.
1. tebra_get_providers -- Get provider IDs
冒頭だけを表示しています。続きはリポジトリで読めます