diff --git a/litellm/responses/mcp/chat_completions_handler.py b/litellm/responses/mcp/chat_completions_handler.py
index 73dba5ba441..b914bb1e4aa 100644
--- a/litellm/responses/mcp/chat_completions_handler.py
+++ b/litellm/responses/mcp/chat_completions_handler.py
@@ -453,9 +453,7 @@ async def acompletion_with_mcp(
                 )
 
                 # Make follow-up call with streaming
-                follow_up_call_args: Final = LiteLLM_Proxy_MCP_Handler._prepare_follow_up_call_params(
-                    self.base_call_args
-                )
+                follow_up_call_args: Final = LiteLLM_Proxy_MCP_Handler._prepare_chained_call_params(self.base_call_args)
                 follow_up_call_args["messages"] = follow_up_messages
                 follow_up_call_args["stream"] = True
                 # Ensure follow-up call doesn't trigger MCP handler again
@@ -627,7 +625,7 @@ async def acompletion_with_mcp(
     )
 
     # Make follow-up call with original stream setting
-    follow_up_call_args: Final = LiteLLM_Proxy_MCP_Handler._prepare_follow_up_call_params(base_call_args)
+    follow_up_call_args: Final = LiteLLM_Proxy_MCP_Handler._prepare_chained_call_params(base_call_args)
     follow_up_call_args["messages"] = follow_up_messages
     follow_up_call_args["stream"] = stream
 
diff --git a/litellm/responses/mcp/litellm_proxy_mcp_handler.py b/litellm/responses/mcp/litellm_proxy_mcp_handler.py
index 46bb067eeeb..d72f335e89c 100644
--- a/litellm/responses/mcp/litellm_proxy_mcp_handler.py
+++ b/litellm/responses/mcp/litellm_proxy_mcp_handler.py
@@ -72,7 +72,7 @@ class LiteLLM_Proxy_MCP_Handler:
     """
 
     @staticmethod
-    def _prepare_follow_up_call_params(params: Mapping[str, Any]) -> dict[str, Any]:
+    def _prepare_chained_call_params(params: Mapping[str, Any]) -> dict[str, Any]:
         """Copy request params without state owned by the previous LLM call.
 
         MCP auto-execution keeps the trace identifier so chained rounds remain
diff --git a/litellm/responses/mcp/mcp_streaming_iterator.py b/litellm/responses/mcp/mcp_streaming_iterator.py
index 69e698f7f65..1e1cbd34ce2 100644
--- a/litellm/responses/mcp/mcp_streaming_iterator.py
+++ b/litellm/responses/mcp/mcp_streaming_iterator.py
@@ -782,7 +782,7 @@ class MCPEnhancedStreamingIterator(BaseResponsesAPIStreamingIterator):
                 )
 
                 # Make follow-up call with streaming
-                follow_up_params: Final = LiteLLM_Proxy_MCP_Handler._prepare_follow_up_call_params(
+                follow_up_params: Final = LiteLLM_Proxy_MCP_Handler._prepare_chained_call_params(
                     self.original_request_params
                 )
                 follow_up_params.update(
diff --git a/tests/test_litellm/responses/mcp/test_litellm_proxy_mcp_handler.py b/tests/test_litellm/responses/mcp/test_litellm_proxy_mcp_handler.py
index 429adb2962d..c552170a599 100644
--- a/tests/test_litellm/responses/mcp/test_litellm_proxy_mcp_handler.py
+++ b/tests/test_litellm/responses/mcp/test_litellm_proxy_mcp_handler.py
@@ -444,7 +444,7 @@ async def test_execute_tool_calls_uses_unique_call_ids_and_preserves_parent_cont
     assert all(item["metadata"]["parent_litellm_call_id"] == "cid" for item in captured)
 
 
-def test_prepare_follow_up_call_params_resets_per_call_logging_state():
+def test_prepare_chained_call_params_resets_per_call_logging_state():
     original = {
         "model": "gpt-4",
         "litellm_call_id": "parent-call",
@@ -457,7 +457,7 @@ def test_prepare_follow_up_call_params_resets_per_call_logging_state():
         },
     }
 
-    follow_up = LiteLLM_Proxy_MCP_Handler._prepare_follow_up_call_params(original)
+    follow_up = LiteLLM_Proxy_MCP_Handler._prepare_chained_call_params(original)
 
     assert "litellm_call_id" not in follow_up
     assert "litellm_logging_obj" not in follow_up