diff --git a/backend/packages/harness/deerflow/agents/middlewares/mcp_routing_middleware.py b/backend/packages/harness/deerflow/agents/middlewares/mcp_routing_middleware.py
index 2aa744f4f..92ba8e983 100644
--- a/backend/packages/harness/deerflow/agents/middlewares/mcp_routing_middleware.py
+++ b/backend/packages/harness/deerflow/agents/middlewares/mcp_routing_middleware.py
@@ -11,9 +11,10 @@ from langchain.agents.middleware import AgentMiddleware
 from langchain_core.messages import HumanMessage
 from langgraph.runtime import Runtime
 
+from deerflow.agents.middlewares.message_utils import is_genuine_user_message
 from deerflow.agents.middlewares.tool_promotion_audit_middleware import record_tool_promotion
 from deerflow.config.tool_search_config import clamp_auto_promote_top_k
-from deerflow.utils.messages import get_original_user_content_text, is_real_user_message
+from deerflow.utils.messages import get_original_user_content_text
 
 logger = logging.getLogger(__name__)
 
@@ -73,8 +74,14 @@ class McpRoutingMiddleware(AgentMiddleware[AgentState]):
 
     @staticmethod
     def _latest_user_message(messages: list[Any]) -> HumanMessage | None:
+        """Latest user-authored message, including a hidden Human Input Card reply.
+
+        The card reply is hidden from the UI but is still the user's current
+        request, so ``is_genuine_user_message`` — not ``is_real_user_message``,
+        which drops every ``hide_from_ui`` message — decides this.
+        """
         for message in reversed(messages):
-            if is_real_user_message(message):
+            if is_genuine_user_message(message):
                 return message
         return None
 
diff --git a/backend/tests/test_mcp_routing_auto_promote.py b/backend/tests/test_mcp_routing_auto_promote.py
index 6ae6a9f8f..83f54b731 100644
--- a/backend/tests/test_mcp_routing_auto_promote.py
+++ b/backend/tests/test_mcp_routing_auto_promote.py
@@ -99,6 +99,31 @@ def test_matching_uses_latest_real_human_message_only():
     assert middleware._matched_names({"messages": [HumanMessage(content="metrics", name="summary"), HumanMessage(content="orders", additional_kwargs={"hide_from_ui": True})]}) == []
 
 
+def test_matching_uses_a_hidden_human_input_card_reply_as_the_latest_message():
+    """A card reply is hidden from the UI but is still the user's current request."""
+    middleware = McpRoutingMiddleware(
+        {"postgres_query": {"priority": 100, "keywords": ["orders"]}},
+        "hash1",
+        3,
+    )
+    reply = HumanMessage(
+        content='For your clarification "Which dataset?", my answer is: orders',
+        additional_kwargs={
+            "hide_from_ui": True,
+            "human_input_response": {
+                "version": 1,
+                "kind": "human_input_response",
+                "source": "ask_clarification",
+                "request_id": "clarification:call-abc",
+                "response_kind": "text",
+                "value": "orders",
+            },
+        },
+    )
+
+    assert middleware._matched_names({"messages": [HumanMessage(content="no match now"), reply]}) == ["postgres_query"]
+
+
 def test_matching_supports_casefold_chinese_priority_tiebreak_and_top_k():
     middleware = McpRoutingMiddleware(
         {