diff --git a/main.py b/main.py
index f1eb33a..cc024a4 100644
--- a/main.py
+++ b/main.py
@@ -1,5 +1,6 @@
 import concurrent.futures
 import os
+import signal
 import sys
 import time
 
@@ -21,6 +22,7 @@
 import tucana.generated.velorum.info_pb2_grpc as info_pb2_grpc
 import tucana.generated.velorum.info_pb2 as info_pb2
 from grpc_reflection.v1alpha import reflection
+from grpc_health.v1 import health, health_pb2, health_pb2_grpc
 
 from src.endpoint.info.info_endpoint import InfoService
 from src.endpoint.generation.generate_endpoint import GenerateService
@@ -34,6 +36,11 @@
     generate_pb2_grpc.add_GenerateServiceServicer_to_server(GenerateService(), server)
     info_pb2_grpc.add_InfoServiceServicer_to_server(InfoService(), server)
 
+    health_servicer = health.HealthServicer()
+    health_servicer.set('liveness', health_pb2.HealthCheckResponse.SERVING)
+    health_servicer.set('readiness', health_pb2.HealthCheckResponse.SERVING)
+    health_pb2_grpc.add_HealthServicer_to_server(health_servicer, server)
+
     port = "0.0.0.0:50051"
     server.add_insecure_port(port)
     print(f"Velorum GenerateService läuft auf {port}...")
@@ -47,9 +54,12 @@
 
     server.start()
 
-    try:
-        while True:
-            time.sleep(86400)
-    except KeyboardInterrupt:
+    def shutdown(signum, frame):
         print("\nServer wird sauber heruntergefahren...")
-        server.stop(0)
+        health_servicer.enter_graceful_shutdown()
+        server.stop(5).wait()
+
+    signal.signal(signal.SIGTERM, shutdown)
+    signal.signal(signal.SIGINT, shutdown)
+
+    server.wait_for_termination()
diff --git a/pyproject.toml b/pyproject.toml
index bfdf249..3b025d2 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -7,6 +7,7 @@ requires-python = ">=3.10,<3.13"
 dependencies = [
     "apscheduler>=3.11.2",
     "grpcio>=1.80.0",
+    "grpcio-health-checking>=1.80.0",
     "grpcio-reflection>=1.80.0",
     "instructor>=1.15.1",
     "PyJWT>=2.4.0",
diff --git a/src/interceptor/auth_interceptor.py b/src/interceptor/auth_interceptor.py
index 0bba06f..02660c2 100644
--- a/src/interceptor/auth_interceptor.py
+++ b/src/interceptor/auth_interceptor.py
@@ -8,6 +8,10 @@
 class AuthInterceptor(grpc.ServerInterceptor):
 
     def intercept_service(self, continuation, handler_call_details):
+        method = handler_call_details.method or ''
+        if method.startswith('/grpc.health.v1.Health/'):
+            return continuation(handler_call_details)
+
         metadata = dict(handler_call_details.invocation_metadata or [])
         auth_token = metadata.get('authorization', '')
 
diff --git a/uv.lock b/uv.lock
index be11fe7..60be949 100644
--- a/uv.lock
+++ b/uv.lock
@@ -501,6 +501,19 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/2f/2c/296f6138caca1f4b92a31ace4ae1b87dab692fc16a7a3417af3bb3c805bf/grpcio-1.80.0-cp312-cp312-win_amd64.whl", hash = "sha256:9fe648599c0e37594c4809d81a9e77bd138cc82eb8baa71b6a86af65426723ff", size = 4880944, upload-time = "2026-03-30T08:47:37.831Z" },
 ]
 
+[[package]]
+name = "grpcio-health-checking"
+version = "1.80.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "grpcio" },
+    { name = "protobuf" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/d1/a2/aa3cc47f19c03f8e5287b987317059753141a3af8f66b96d5a64b3be10b8/grpcio_health_checking-1.80.0.tar.gz", hash = "sha256:2cc5f08bc8b816b8655ab6f59c71450063ba20766d31e21a493e912e3560c8b1", size = 17117, upload-time = "2026-03-30T08:54:41.899Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/5e/d1/d97eb30386feff6ac2a662620e2ed68be352e9a182d62e06213db694906a/grpcio_health_checking-1.80.0-py3-none-any.whl", hash = "sha256:d804d4549cbb71e90ca2c7bf0c501060135dfd220aca8e2c54f96d3e79e210e5", size = 19125, upload-time = "2026-03-30T08:53:44.835Z" },
+]
+
 [[package]]
 name = "grpcio-reflection"
 version = "1.80.0"
@@ -2126,6 +2139,7 @@ source = { virtual = "." }
 dependencies = [
     { name = "apscheduler" },
     { name = "grpcio" },
+    { name = "grpcio-health-checking" },
     { name = "grpcio-reflection" },
     { name = "instructor" },
     { name = "litellm" },
@@ -2140,6 +2154,7 @@ dependencies = [
 requires-dist = [
     { name = "apscheduler", specifier = ">=3.11.2" },
     { name = "grpcio", specifier = ">=1.80.0" },
+    { name = "grpcio-health-checking", specifier = ">=1.80.0" },
     { name = "grpcio-reflection", specifier = ">=1.80.0" },
     { name = "instructor", specifier = ">=1.15.1" },
     { name = "litellm", specifier = "==1.83.7" },