diff --git a/examples/server/tests/features/parallel.feature b/examples/server/tests/features/parallel.feature
index 6fe1e05de..c85f9de1d 100644
--- a/examples/server/tests/features/parallel.feature
+++ b/examples/server/tests/features/parallel.feature
@@ -2,7 +2,7 @@
 Feature: Parallel
 
   Background: Server startup
-    Given a server listening on 0.0.0.0:8080
+    Given a server listening on localhost:8080
     And   a model file stories260K.gguf
     And   a model alias tinyllama-2
     And   42 as server seed
diff --git a/examples/server/tests/features/security.feature b/examples/server/tests/features/security.feature
index dba0849d1..db06d3977 100644
--- a/examples/server/tests/features/security.feature
+++ b/examples/server/tests/features/security.feature
@@ -2,7 +2,7 @@
 Feature: Security
 
   Background: Server startup with an api key defined
-    Given a server listening on 0.0.0.0:8080
+    Given a server listening on localhost:8080
     And   a model file stories260K.gguf
     And   a server api key llama.cpp
     Then  the server is starting
diff --git a/examples/server/tests/features/server.feature b/examples/server/tests/features/server.feature
index 10941972e..b571582a7 100644
--- a/examples/server/tests/features/server.feature
+++ b/examples/server/tests/features/server.feature
@@ -2,7 +2,7 @@
 Feature: llama.cpp server
 
   Background: Server startup
-    Given a server listening on 0.0.0.0:8080
+    Given a server listening on localhost:8080
     And   a model file stories260K.gguf
     And   a model alias tinyllama-2
     And   42 as server seed
diff --git a/examples/server/tests/features/wrong_usages.feature b/examples/server/tests/features/wrong_usages.feature
index f4fc6a8a2..e228b2371 100644
--- a/examples/server/tests/features/wrong_usages.feature
+++ b/examples/server/tests/features/wrong_usages.feature
@@ -6,7 +6,7 @@ Feature: Wrong usage of llama.cpp server
   # to cap the number of tokens any completion request can generate
   # or pass n_predict/max_tokens in the request.
   Scenario: Infinite loop
-    Given a server listening on 0.0.0.0:8080
+    Given a server listening on localhost:8080
     And   a model file stories260K.gguf
     # Uncomment below to fix the issue
     #And   64 server max tokens to predict