Mirobody
Lab results to LOINC codes and UCUM units, symptoms and diagnoses to ICPC-3. Offline, no API key.
Beschreibung vom Entwickler (englisches Original)
MCP server for Tebra/Kareo practice management — patients, billing, scheduling, FHIR (45 tools)
Diese drei werden nie zu einer Punktzahl zusammengefasst: Meinungen, Messungen und Beliebtheit sind verschiedene Dinge.
Für diesen Server haben wir noch keine Zusammenfassung in einfacher Sprache geschrieben. Unten stehen die Fakten, die wir aus der Registry gelesen haben.
Wähle die KI-App, die du nutzt, und kopiere die Einstellungen.
TEBRA_SOAP_USER, TEBRA_SOAP_PASSWORD, TEBRA_CUSTOMER_KEYAls geheim markierte Werte sind Schlüssel zu deinem Konto. Gib sie nie weiter und füge sie nie in einen Chat ein.
Du brauchst
Welche App nutzt du?
Wähle oben deine App. Wir merken sie uns, damit der Button beim nächsten Mal „In … installieren“ anzeigt.
Öffne Claude Desktop → Settings → Developer → Edit Config und füge dies in claude_desktop_config.json ein
{
"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"
}
}
}
}Führe das in deinem Terminal aus
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-serverTrag die leeren Werte ein, bevor du ihn startest.
In .cursor/mcp.json in deinem Projekt oder in ~/.cursor/mcp.json einfügen
{
"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"
}
}
}
}Dein Browser fragt, ob er die App öffnen darf, dann zeigt die App die Einstellungen und bittet dich um Bestätigung. Schlüsselwerte bleiben leer, damit du sie selbst einträgst.
In .vscode/mcp.json in deinem Projekt einfügen
{
"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"
}
}
}
}Dein Browser fragt, ob er die App öffnen darf, dann zeigt die App die Einstellungen und bittet dich um Bestätigung. Schlüsselwerte bleiben leer, damit du sie selbst einträgst.
Dieser Server läuft auf deinem Computer, und ChatGPT kann sich nur mit Servern im Internet verbinden. Wähle eine andere App.
Deine Auswahl bleibt in einem Cookie auf diesem Gerät; kein Konto nötig.
Diese Einstellungen werden aus dem Registry-Eintrag des Entwicklers erzeugt. Wenn in der README etwas anderes steht, folge der README.
Läuft auf deinem Computer; die Tool-Liste erscheint nach der Installation in deiner KI-App.
Wir prüfen Informationen, die jeder sehen kann; den Code haben wir nicht gelesen. Checks, die nicht zutreffen, werden nicht mitgezählt. · Geprüft am 7. Nov. 2026
Der Herausgeber (jamesrosingmd.com) ist nicht der Repo-Inhaber (jamesrosing); vielleicht hat jemand anderes ihn eingetragen
Dieses Repo haben wir noch nicht von GitHub gelesen
Dieses Repo haben wir noch nicht von GitHub gelesen
Dieser Server läuft auf deinem Computer; es gibt keinen Endpunkt im Internet
Läuft auf deinem Computer und nutzt stattdessen lokale Einstellungen
Läuft auf deinem Computer; Tool-Listen können wir nur von Endpunkten im Internet lesen
Verglichen mit allen aktiven Servern dieser Kategorie in der Registry. Sterne zählen nur, wenn dem Herausgeber das Repo gehört.
Er hat 0 von 1 zutreffenden Basischecks bestanden. Den Code haben wir nicht gelesen. Bevor du einen Schlüssel oder Token hinzufügst, sieh nach, welche Zugriffe der Server verlangt, und nutze einen Schlüssel, der nur die Berechtigungen hat, die du brauchst.
Das musst du eintragen: TEBRA_SOAP_USER, TEBRA_SOAP_PASSWORD, TEBRA_CUSTOMER_KEY
Er läuft auf deinem Computer. Deine KI-App startet ihn bei Bedarf, und die Daten laufen nicht über die Server des Entwicklers (außer der Server ruft selbst einen Onlinedienst auf).
Das GitHub-Repo wurde zuletzt – geändert, und die neueste Version (0.2.5) kam vor 6 Monaten in die Registry.
Apps, die MCP unterstützen, etwa Claude Desktop, Claude Code, Cursor und VS Code. Außerdem brauchst du Node.js auf deinem Computer.
In derselben Kategorie: Mirobody, FHIR MCP Server, Google Health MCP
Server derselben Kategorie von anderen Entwicklern, sortiert nach Sternen.
So liest du eine Karte:★ GitHub-SterneiDrei Säulen: Bewertungen · Checks · NutzungiAktualisiert = neueste Version in der Registry veröffentlichti
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
Unverändert aus dem Repo des Entwicklers übernommen. PopNx MCP hat den Inhalt weder geprüft noch empfiehlt es ihn. HTML, Bilder und Skripte wurden entfernt. Links führen von dieser Website weg.
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
Nur der Anfang wird gezeigt; den Rest findest du im Repo