Python: [BREAKING] Replace Hosted*Tool classes with tool methods (#3634)

* Replace Hosted*Tool classes with client static factory methods

* fixed failing test

* mypy fix

* mypy fix 2

* declarative mypy fix

* addressed comments

* ToolProtocol removal

* fixed test

* agents mypy fix

* fix failing tests

* mypy fix

* addressed comments

* fixed tests

* addressed comments + added factory method overrides for azureai v2 client

* mypy fix

* added kwargs to azureai tool methods

* fixed in test

* _sessions fix

* test fix

python/samples/getting_started/agents/azure_openai/README.md

@@ -7,7 +7,7 @@ This folder contains examples demonstrating different ways to create and use age
 | File | Description |
 |------|-------------|
 | [`azure_assistants_basic.py`](azure_assistants_basic.py) | The simplest way to create an agent using `Agent` with `AzureOpenAIAssistantsClient`. Shows both streaming and non-streaming responses with automatic assistant creation and cleanup. |
-| [`azure_assistants_with_code_interpreter.py`](azure_assistants_with_code_interpreter.py) | Shows how to use the HostedCodeInterpreterTool with Azure agents to write and execute Python code. Includes helper methods for accessing code interpreter data from response chunks. |
+| [`azure_assistants_with_code_interpreter.py`](azure_assistants_with_code_interpreter.py) | Shows how to use `AzureOpenAIAssistantsClient.get_code_interpreter_tool()` with Azure agents to write and execute Python code. Includes helper methods for accessing code interpreter data from response chunks. |
 | [`azure_assistants_with_existing_assistant.py`](azure_assistants_with_existing_assistant.py) | Shows how to work with a pre-existing assistant by providing the assistant ID to the Azure Assistants client. Demonstrates proper cleanup of manually created assistants. |
 | [`azure_assistants_with_explicit_settings.py`](azure_assistants_with_explicit_settings.py) | Shows how to initialize an agent with a specific assistants client, configuring settings explicitly including endpoint and deployment name. |
 | [`azure_assistants_with_function_tools.py`](azure_assistants_with_function_tools.py) | Demonstrates how to use function tools with agents. Shows both agent-level tools (defined when creating the agent) and query-level tools (provided with specific queries). |
@@ -17,12 +17,13 @@ This folder contains examples demonstrating different ways to create and use age
 | [`azure_chat_client_with_function_tools.py`](azure_chat_client_with_function_tools.py) | Demonstrates how to use function tools with agents. Shows both agent-level tools (defined when creating the agent) and query-level tools (provided with specific queries). |
 | [`azure_chat_client_with_thread.py`](azure_chat_client_with_thread.py) | Demonstrates thread management with Azure agents, including automatic thread creation for stateless conversations and explicit thread management for maintaining conversation context across multiple interactions. |
 | [`azure_responses_client_basic.py`](azure_responses_client_basic.py) | The simplest way to create an agent using `Agent` with `AzureOpenAIResponsesClient`. Shows both streaming and non-streaming responses for structured response generation with Azure OpenAI models. |
-| [`azure_responses_client_code_interpreter_files.py`](azure_responses_client_code_interpreter_files.py) | Demonstrates using HostedCodeInterpreterTool with file uploads for data analysis. Shows how to create, upload, and analyze CSV files using Python code execution with Azure OpenAI Responses. |
+| [`azure_responses_client_code_interpreter_files.py`](azure_responses_client_code_interpreter_files.py) | Demonstrates using `AzureOpenAIResponsesClient.get_code_interpreter_tool()` with file uploads for data analysis. Shows how to create, upload, and analyze CSV files using Python code execution with Azure OpenAI Responses. |
 | [`azure_responses_client_image_analysis.py`](azure_responses_client_image_analysis.py) | Shows how to use Azure OpenAI Responses for image analysis and vision tasks. Demonstrates multi-modal messages combining text and image content using remote URLs. |
-| [`azure_responses_client_with_code_interpreter.py`](azure_responses_client_with_code_interpreter.py) | Shows how to use the HostedCodeInterpreterTool with Azure agents to write and execute Python code. Includes helper methods for accessing code interpreter data from response chunks. |
+| [`azure_responses_client_with_code_interpreter.py`](azure_responses_client_with_code_interpreter.py) | Shows how to use `AzureOpenAIResponsesClient.get_code_interpreter_tool()` with Azure agents to write and execute Python code. Includes helper methods for accessing code interpreter data from response chunks. |
 | [`azure_responses_client_with_explicit_settings.py`](azure_responses_client_with_explicit_settings.py) | Shows how to initialize an agent with a specific responses client, configuring settings explicitly including endpoint and deployment name. |
-| [`azure_responses_client_with_file_search.py`](azure_responses_client_with_file_search.py) | Demonstrates using HostedFileSearchTool with Azure OpenAI Responses Client for direct document-based question answering and information retrieval from vector stores. |
+| [`azure_responses_client_with_file_search.py`](azure_responses_client_with_file_search.py) | Demonstrates using `AzureOpenAIResponsesClient.get_file_search_tool()` with Azure OpenAI Responses Client for direct document-based question answering and information retrieval from vector stores. |
 | [`azure_responses_client_with_function_tools.py`](azure_responses_client_with_function_tools.py) | Demonstrates how to use function tools with agents. Shows both agent-level tools (defined when creating the agent) and query-level tools (provided with specific queries). |
+| [`azure_responses_client_with_hosted_mcp.py`](azure_responses_client_with_hosted_mcp.py) | Shows how to integrate Azure OpenAI Responses Client with hosted Model Context Protocol (MCP) servers using `AzureOpenAIResponsesClient.get_mcp_tool()` for extended functionality. |
 | [`azure_responses_client_with_local_mcp.py`](azure_responses_client_with_local_mcp.py) | Shows how to integrate Azure OpenAI Responses Client with local Model Context Protocol (MCP) servers using MCPStreamableHTTPTool for extended functionality. |
 | [`azure_responses_client_with_thread.py`](azure_responses_client_with_thread.py) | Demonstrates thread management with Azure agents, including automatic thread creation for stateless conversations and explicit thread management for maintaining conversation context across multiple interactions. |
 

python/samples/getting_started/agents/azure_openai/azure_assistants_with_code_interpreter.py

@@ -2,9 +2,8 @@
 
 import asyncio
 
-from agent_framework import Agent, AgentResponseUpdate, ChatResponseUpdate, HostedCodeInterpreterTool
+from agent_framework import Agent, AgentResponseUpdate, ChatResponseUpdate
 from agent_framework.azure import AzureOpenAIAssistantsClient
-from azure.identity import AzureCliCredential
 from openai.types.beta.threads.runs import (
     CodeInterpreterToolCallDelta,
     RunStepDelta,
@@ -16,7 +15,7 @@ from openai.types.beta.threads.runs.code_interpreter_tool_call_delta import Code
 """
 Azure OpenAI Assistants with Code Interpreter Example
 
-This sample demonstrates using HostedCodeInterpreterTool with Azure OpenAI Assistants
+This sample demonstrates using get_code_interpreter_tool() with Azure OpenAI Assistants
 for Python code execution and mathematical problem solving.
 """
 
@@ -41,15 +40,19 @@ def get_code_interpreter_chunk(chunk: AgentResponseUpdate) -> str | None:
 
 
 async def main() -> None:
-    """Example showing how to use the HostedCodeInterpreterTool with Azure OpenAI Assistants."""
+    """Example showing how to use the code interpreter tool with Azure OpenAI Assistants."""
     print("=== Azure OpenAI Assistants Agent with Code Interpreter Example ===")
 
+    # Create code interpreter tool using static method
+    client = AzureOpenAIAssistantsClient()
+    code_interpreter_tool = client.get_code_interpreter_tool()
+
     # For authentication, run `az login` command in terminal or replace AzureCliCredential with preferred
     # authentication option.
     async with Agent(
-        client=AzureOpenAIAssistantsClient(credential=AzureCliCredential()),
+        client=client,
         instructions="You are a helpful assistant that can write and execute Python code to solve problems.",
-        tools=HostedCodeInterpreterTool(),
+        tools=[code_interpreter_tool],
     ) as agent:
         query = "What is current datetime?"
         print(f"User: {query}")

python/samples/getting_started/agents/azure_openai/azure_assistants_with_existing_assistant.py

@@ -19,7 +19,9 @@ using existing assistant IDs rather than creating new ones.
 """
 
 
-# NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production; see samples/getting_started/tools/function_tool_with_approval.py and samples/getting_started/tools/function_tool_with_approval_and_threads.py.
+# NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production;
+# see samples/getting_started/tools/function_tool_with_approval.py
+# and samples/getting_started/tools/function_tool_with_approval_and_threads.py.
 @tool(approval_mode="never_require")
 def get_weather(
     location: Annotated[str, Field(description="The location to get the weather for.")],

python/samples/getting_started/agents/azure_openai/azure_assistants_with_explicit_settings.py

@@ -18,7 +18,9 @@ settings rather than relying on environment variable defaults.
 """
 
 
-# NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production; see samples/getting_started/tools/function_tool_with_approval.py and samples/getting_started/tools/function_tool_with_approval_and_threads.py.
+# NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production;
+# see samples/getting_started/tools/function_tool_with_approval.py
+# and samples/getting_started/tools/function_tool_with_approval_and_threads.py.
 @tool(approval_mode="never_require")
 def get_weather(
     location: Annotated[str, Field(description="The location to get the weather for.")],

python/samples/getting_started/agents/azure_openai/azure_assistants_with_function_tools.py

@@ -18,7 +18,9 @@ showing both agent-level and query-level tool configuration patterns.
 """
 
 
-# NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production; see samples/getting_started/tools/function_tool_with_approval.py and samples/getting_started/tools/function_tool_with_approval_and_threads.py.
+# NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production;
+# see samples/getting_started/tools/function_tool_with_approval.py
+# and samples/getting_started/tools/function_tool_with_approval_and_threads.py.
 @tool(approval_mode="never_require")
 def get_weather(
     location: Annotated[str, Field(description="The location to get the weather for.")],

python/samples/getting_started/agents/azure_openai/azure_assistants_with_thread.py

@@ -17,7 +17,9 @@ automatic thread creation with explicit thread management for persistent context
 """
 
 
-# NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production; see samples/getting_started/tools/function_tool_with_approval.py and samples/getting_started/tools/function_tool_with_approval_and_threads.py.
+# NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production;
+# see samples/getting_started/tools/function_tool_with_approval.py
+# and samples/getting_started/tools/function_tool_with_approval_and_threads.py.
 @tool(approval_mode="never_require")
 def get_weather(
     location: Annotated[str, Field(description="The location to get the weather for.")],

python/samples/getting_started/agents/azure_openai/azure_chat_client_basic.py

@@ -17,7 +17,9 @@ interactions, showing both streaming and non-streaming responses.
 """
 
 
-# NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production; see samples/getting_started/tools/function_tool_with_approval.py and samples/getting_started/tools/function_tool_with_approval_and_threads.py.
+# NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production;
+# see samples/getting_started/tools/function_tool_with_approval.py
+# and samples/getting_started/tools/function_tool_with_approval_and_threads.py.
 @tool(approval_mode="never_require")
 def get_weather(
     location: Annotated[str, Field(description="The location to get the weather for.")],

python/samples/getting_started/agents/azure_openai/azure_chat_client_with_explicit_settings.py

@@ -18,7 +18,9 @@ settings rather than relying on environment variable defaults.
 """
 
 
-# NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production; see samples/getting_started/tools/function_tool_with_approval.py and samples/getting_started/tools/function_tool_with_approval_and_threads.py.
+# NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production;
+# see samples/getting_started/tools/function_tool_with_approval.py
+# and samples/getting_started/tools/function_tool_with_approval_and_threads.py.
 @tool(approval_mode="never_require")
 def get_weather(
     location: Annotated[str, Field(description="The location to get the weather for.")],

python/samples/getting_started/agents/azure_openai/azure_chat_client_with_function_tools.py

@@ -18,7 +18,9 @@ showing both agent-level and query-level tool configuration patterns.
 """
 
 
-# NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production; see samples/getting_started/tools/function_tool_with_approval.py and samples/getting_started/tools/function_tool_with_approval_and_threads.py.
+# NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production;
+# see samples/getting_started/tools/function_tool_with_approval.py
+# and samples/getting_started/tools/function_tool_with_approval_and_threads.py.
 @tool(approval_mode="never_require")
 def get_weather(
     location: Annotated[str, Field(description="The location to get the weather for.")],

python/samples/getting_started/agents/azure_openai/azure_chat_client_with_thread.py

@@ -17,7 +17,9 @@ automatic thread creation with explicit thread management for persistent context
 """
 
 
-# NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production; see samples/getting_started/tools/function_tool_with_approval.py and samples/getting_started/tools/function_tool_with_approval_and_threads.py.
+# NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production;
+# see samples/getting_started/tools/function_tool_with_approval.py
+# and samples/getting_started/tools/function_tool_with_approval_and_threads.py.
 @tool(approval_mode="never_require")
 def get_weather(
     location: Annotated[str, Field(description="The location to get the weather for.")],

python/samples/getting_started/agents/azure_openai/azure_responses_client_basic.py

@@ -17,7 +17,9 @@ response generation, showing both streaming and non-streaming responses.
 """
 
 
-# NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production; see samples/getting_started/tools/function_tool_with_approval.py and samples/getting_started/tools/function_tool_with_approval_and_threads.py.
+# NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production;
+# see samples/getting_started/tools/function_tool_with_approval.py
+# and samples/getting_started/tools/function_tool_with_approval_and_threads.py.
 @tool(approval_mode="never_require")
 def get_weather(
     location: Annotated[str, Field(description="The location to get the weather for.")],

python/samples/getting_started/agents/azure_openai/azure_responses_client_code_interpreter_files.py

@@ -4,7 +4,7 @@ import asyncio
 import os
 import tempfile
 
-from agent_framework import Agent, HostedCodeInterpreterTool
+from agent_framework import Agent
 from agent_framework.azure import AzureOpenAIResponsesClient
 from azure.identity import AzureCliCredential
 from openai import AsyncAzureOpenAI
@@ -12,7 +12,7 @@ from openai import AsyncAzureOpenAI
 """
 Azure OpenAI Responses Client with Code Interpreter and Files Example
 
-This sample demonstrates using HostedCodeInterpreterTool with Azure OpenAI Responses
+This sample demonstrates using get_code_interpreter_tool() with Azure OpenAI Responses
 for Python code execution and data analysis with uploaded files.
 """
 
@@ -76,10 +76,15 @@ async def main() -> None:
     temp_file_path, file_id = await create_sample_file_and_upload(openai_client)
 
     # Create agent using Azure OpenAI Responses client
+    client = AzureOpenAIResponsesClient(credential=credential)
+
+    # Create code interpreter tool with file access
+    code_interpreter_tool = client.get_code_interpreter_tool(file_ids=[file_id])
+
     agent = Agent(
-        client=AzureOpenAIResponsesClient(credential=credential),
+        client=client,
         instructions="You are a helpful assistant that can analyze data files using Python code.",
-        tools=HostedCodeInterpreterTool(inputs=[{"file_id": file_id}]),
+        tools=[code_interpreter_tool],
     )
 
     # Test the code interpreter with the uploaded file

python/samples/getting_started/agents/azure_openai/azure_responses_client_image_analysis.py

@@ -27,9 +27,9 @@ async def main():
     user_message = Message(
         role="user",
         contents=[
-            Content.from_text(text="What do you see in this image?"),
+            Content.from_text("What do you see in this image?"),
             Content.from_uri(
-                uri="https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
+                uri="https://images.unsplash.com/photo-1506905925346-21bda4d32df4?w=800",
                 media_type="image/jpeg",
             ),
         ],

python/samples/getting_started/agents/azure_openai/azure_responses_client_with_code_interpreter.py

@@ -2,7 +2,7 @@
 
 import asyncio
 
-from agent_framework import Agent, ChatResponse, HostedCodeInterpreterTool
+from agent_framework import Agent, ChatResponse
 from agent_framework.azure import AzureOpenAIResponsesClient
 from azure.identity import AzureCliCredential
 from openai.types.responses.response import Response as OpenAIResponse
@@ -11,21 +11,26 @@ from openai.types.responses.response_code_interpreter_tool_call import ResponseC
 """
 Azure OpenAI Responses Client with Code Interpreter Example
 
-This sample demonstrates using HostedCodeInterpreterTool with Azure OpenAI Responses
+This sample demonstrates using get_code_interpreter_tool() with Azure OpenAI Responses
 for Python code execution and mathematical problem solving.
 """
 
 
 async def main() -> None:
-    """Example showing how to use the HostedCodeInterpreterTool with Azure OpenAI Responses."""
+    """Example showing how to use the code interpreter tool with Azure OpenAI Responses."""
     print("=== Azure OpenAI Responses Agent with Code Interpreter Example ===")
 
     # For authentication, run `az login` command in terminal or replace AzureCliCredential with preferred
     # authentication option.
+    client = AzureOpenAIResponsesClient(credential=AzureCliCredential())
+
+    # Create code interpreter tool using instance method
+    code_interpreter_tool = client.get_code_interpreter_tool()
+
     agent = Agent(
-        client=AzureOpenAIResponsesClient(credential=AzureCliCredential()),
+        client=client,
         instructions="You are a helpful assistant that can write and execute Python code to solve problems.",
-        tools=HostedCodeInterpreterTool(),
+        tools=[code_interpreter_tool],
     )
 
     query = "Use code to calculate the factorial of 100?"

python/samples/getting_started/agents/azure_openai/azure_responses_client_with_explicit_settings.py

@@ -18,7 +18,9 @@ settings rather than relying on environment variable defaults.
 """
 
 
-# NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production; see samples/getting_started/tools/function_tool_with_approval.py and samples/getting_started/tools/function_tool_with_approval_and_threads.py.
+# NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production;
+# see samples/getting_started/tools/function_tool_with_approval.py
+# and samples/getting_started/tools/function_tool_with_approval_and_threads.py.
 @tool(approval_mode="never_require")
 def get_weather(
     location: Annotated[str, Field(description="The location to get the weather for.")],

python/samples/getting_started/agents/azure_openai/azure_responses_client_with_file_search.py

@@ -2,14 +2,14 @@
 
 import asyncio
 
-from agent_framework import Agent, Content, HostedFileSearchTool
+from agent_framework import Agent, Content
 from agent_framework.azure import AzureOpenAIResponsesClient
 from azure.identity import AzureCliCredential
 
 """
 Azure OpenAI Responses Client with File Search Example
 
-This sample demonstrates using HostedFileSearchTool with Azure OpenAI Responses Client
+This sample demonstrates using get_file_search_tool() with Azure OpenAI Responses Client
 for direct document-based question answering and information retrieval.
 
 Prerequisites:
@@ -51,12 +51,15 @@ async def main() -> None:
     # Make sure you're logged in via 'az login' before running this sample
     client = AzureOpenAIResponsesClient(credential=AzureCliCredential())
 
-    file_id, vector_store = await create_vector_store(client)
+    file_id, vector_store_id = await create_vector_store(client)
+
+    # Create file search tool using instance method
+    file_search_tool = client.get_file_search_tool(vector_store_ids=[vector_store_id])
 
     agent = Agent(
         client=client,
         instructions="You are a helpful assistant that can search through files to find information.",
-        tools=[HostedFileSearchTool(inputs=vector_store)],
+        tools=[file_search_tool],
     )
 
     query = "What is the weather today? Do a file search to find the answer."
@@ -64,7 +67,7 @@ async def main() -> None:
     result = await agent.run(query)
     print(f"Agent: {result}\n")
 
-    await delete_vector_store(client, file_id, vector_store.vector_store_id)
+    await delete_vector_store(client, file_id, vector_store_id)
 
 
 if __name__ == "__main__":

python/samples/getting_started/agents/azure_openai/azure_responses_client_with_function_tools.py

@@ -18,7 +18,9 @@ showing both agent-level and query-level tool configuration patterns.
 """
 
 
-# NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production; see samples/getting_started/tools/function_tool_with_approval.py and samples/getting_started/tools/function_tool_with_approval_and_threads.py.
+# NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production;
+# see samples/getting_started/tools/function_tool_with_approval.py
+# and samples/getting_started/tools/function_tool_with_approval_and_threads.py.
 @tool(approval_mode="never_require")
 def get_weather(
     location: Annotated[str, Field(description="The location to get the weather for.")],

python/samples/getting_started/agents/azure_openai/azure_responses_client_with_hosted_mcp.py

@@ -3,7 +3,7 @@
 import asyncio
 from typing import TYPE_CHECKING, Any
 
-from agent_framework import Agent, HostedMCPTool
+from agent_framework import Agent
 from agent_framework.azure import AzureOpenAIResponsesClient
 from azure.identity import AzureCliCredential
 
@@ -33,7 +33,10 @@ async def handle_approvals_without_thread(query: str, agent: "SupportsAgentRun")
             new_inputs.append(Message(role="assistant", contents=[user_input_needed]))
             user_approval = input("Approve function call? (y/n): ")
             new_inputs.append(
-                Message(role="user", contents=[user_input_needed.to_function_approval_response(user_approval.lower() == "y")])
+                Message(
+                    role="user",
+                    contents=[user_input_needed.to_function_approval_response(user_approval.lower() == "y")],
+                )
             )
 
         result = await agent.run(new_inputs)
@@ -82,7 +85,8 @@ async def handle_approvals_with_thread_streaming(query: str, agent: "SupportsAge
                     user_approval = input("Approve function call? (y/n): ")
                     new_input.append(
                         Message(
-                            role="user", contents=[user_input_needed.to_function_approval_response(user_approval.lower() == "y")]
+                            role="user",
+                            contents=[user_input_needed.to_function_approval_response(user_approval.lower() == "y")],
                         )
                     )
                     new_input_added = True
@@ -94,21 +98,24 @@ async def run_hosted_mcp_without_thread_and_specific_approval() -> None:
     """Example showing Mcp Tools with approvals without using a thread."""
     print("=== Mcp with approvals and without thread ===")
     credential = AzureCliCredential()
+    client = AzureOpenAIResponsesClient(credential=credential)
+
+    # Create MCP tool with specific approval settings
+    mcp_tool = client.get_mcp_tool(
+        name="Microsoft Learn MCP",
+        url="https://learn.microsoft.com/api/mcp",
+        # we don't require approval for microsoft_docs_search tool calls
+        # but we do for any other tool
+        approval_mode={"never_require_approval": ["microsoft_docs_search"]},
+    )
+
     # Tools are provided when creating the agent
     # The agent can use these tools for any query during its lifetime
     async with Agent(
-        client=AzureOpenAIResponsesClient(
-            credential=credential,
-        ),
+        client=client,
         name="DocsAgent",
         instructions="You are a helpful assistant that can help with microsoft documentation questions.",
-        tools=HostedMCPTool(
-            name="Microsoft Learn MCP",
-            url="https://learn.microsoft.com/api/mcp",
-            # we don't require approval for microsoft_docs_search tool calls
-            # but we do for any other tool
-            approval_mode={"never_require_approval": ["microsoft_docs_search"]},
-        ),
+        tools=[mcp_tool],
     ) as agent:
         # First query
         query1 = "How to create an Azure storage account using az cli?"
@@ -127,22 +134,25 @@ async def run_hosted_mcp_without_approval() -> None:
     """Example showing Mcp Tools without approvals."""
     print("=== Mcp without approvals ===")
     credential = AzureCliCredential()
+    client = AzureOpenAIResponsesClient(credential=credential)
+
+    # Create MCP tool without approval requirements
+    mcp_tool = client.get_mcp_tool(
+        name="Microsoft Learn MCP",
+        url="https://learn.microsoft.com/api/mcp",
+        # we don't require approval for any function calls
+        # this means we will not see the approval messages,
+        # it is fully handled by the service and a final response is returned.
+        approval_mode="never_require",
+    )
+
     # Tools are provided when creating the agent
     # The agent can use these tools for any query during its lifetime
     async with Agent(
-        client=AzureOpenAIResponsesClient(
-            credential=credential,
-        ),
+        client=client,
         name="DocsAgent",
         instructions="You are a helpful assistant that can help with microsoft documentation questions.",
-        tools=HostedMCPTool(
-            name="Microsoft Learn MCP",
-            url="https://learn.microsoft.com/api/mcp",
-            # we don't require approval for any function calls
-            # this means we will not see the approval messages,
-            # it is fully handled by the service and a final response is returned.
-            approval_mode="never_require",
-        ),
+        tools=[mcp_tool],
     ) as agent:
         # First query
         query1 = "How to create an Azure storage account using az cli?"
@@ -161,20 +171,23 @@ async def run_hosted_mcp_with_thread() -> None:
     """Example showing Mcp Tools with approvals using a thread."""
     print("=== Mcp with approvals and with thread ===")
     credential = AzureCliCredential()
+    client = AzureOpenAIResponsesClient(credential=credential)
+
+    # Create MCP tool with always require approval
+    mcp_tool = client.get_mcp_tool(
+        name="Microsoft Learn MCP",
+        url="https://learn.microsoft.com/api/mcp",
+        # we require approval for all function calls
+        approval_mode="always_require",
+    )
+
     # Tools are provided when creating the agent
     # The agent can use these tools for any query during its lifetime
     async with Agent(
-        client=AzureOpenAIResponsesClient(
-            credential=credential,
-        ),
+        client=client,
         name="DocsAgent",
         instructions="You are a helpful assistant that can help with microsoft documentation questions.",
-        tools=HostedMCPTool(
-            name="Microsoft Learn MCP",
-            url="https://learn.microsoft.com/api/mcp",
-            # we require approval for all function calls
-            approval_mode="always_require",
-        ),
+        tools=[mcp_tool],
     ) as agent:
         # First query
         thread = agent.get_new_thread()
@@ -194,20 +207,23 @@ async def run_hosted_mcp_with_thread_streaming() -> None:
     """Example showing Mcp Tools with approvals using a thread."""
     print("=== Mcp with approvals and with thread ===")
     credential = AzureCliCredential()
+    client = AzureOpenAIResponsesClient(credential=credential)
+
+    # Create MCP tool with always require approval
+    mcp_tool = client.get_mcp_tool(
+        name="Microsoft Learn MCP",
+        url="https://learn.microsoft.com/api/mcp",
+        # we require approval for all function calls
+        approval_mode="always_require",
+    )
+
     # Tools are provided when creating the agent
     # The agent can use these tools for any query during its lifetime
     async with Agent(
-        client=AzureOpenAIResponsesClient(
-            credential=credential,
-        ),
+        client=client,
         name="DocsAgent",
         instructions="You are a helpful assistant that can help with microsoft documentation questions.",
-        tools=HostedMCPTool(
-            name="Microsoft Learn MCP",
-            url="https://learn.microsoft.com/api/mcp",
-            # we require approval for all function calls
-            approval_mode="always_require",
-        ),
+        tools=[mcp_tool],
     ) as agent:
         # First query
         thread = agent.get_new_thread()

python/samples/getting_started/agents/azure_openai/azure_responses_client_with_local_mcp.py

@@ -48,14 +48,14 @@ async def main():
         url=MCP_URL,
     ) as mcp_tool:
         # First query — expect the agent to use the MCP tool if it helps
-        q1 = "How to create an Azure storage account using az cli?"
-        r1 = await agent.run(q1, tools=mcp_tool)
-        print("\n=== Answer 1 ===\n", r1.text)
+        first_query = "How to create an Azure storage account using az cli?"
+        first_response = await agent.run(first_query, tools=mcp_tool)
+        print("\n=== Answer 1 ===\n", first_response.text)
 
         # Follow-up query (connection is reused)
-        q2 = "What is Microsoft Agent Framework?"
-        r2 = await agent.run(q2, tools=mcp_tool)
-        print("\n=== Answer 2 ===\n", r2.text)
+        second_query = "What is Microsoft Agent Framework?"
+        second_response = await agent.run(second_query, tools=mcp_tool)
+        print("\n=== Answer 2 ===\n", second_response.text)
 
 
 if __name__ == "__main__":

python/samples/getting_started/agents/azure_openai/azure_responses_client_with_thread.py

@@ -17,7 +17,9 @@ automatic thread creation with explicit thread management for persistent context
 """
 
 
-# NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production; see samples/getting_started/tools/function_tool_with_approval.py and samples/getting_started/tools/function_tool_with_approval_and_threads.py.
+# NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production;
+# see samples/getting_started/tools/function_tool_with_approval.py
+# and samples/getting_started/tools/function_tool_with_approval_and_threads.py.
 @tool(approval_mode="never_require")
 def get_weather(
     location: Annotated[str, Field(description="The location to get the weather for.")],