McpToolRegistrationService Class

Provides MCP tool registration services for Azure Foundry agents.

This service handles registration and management of MCP (Model Context Protocol) tool servers with Azure Foundry agents using the Azure AI SDK. It provides seamless integration between MCP servers and Azure Foundry's agent framework.

Features:

Automatic MCP server discovery and configuration
Azure identity integration with DefaultAzureCredential
Tool definitions and resources management
Support for both development (ToolingManifest.json) and production (gateway API) scenarios
Comprehensive error handling and logging

Constructor

McpToolRegistrationService()

Parameters

Name	Description
logger	Default value: None
credential	Default value: None

Examples


>>> service = McpToolRegistrationService()
>>> service.add_tool_servers_to_agent(project_client, agent_id, token)

Methods

__init__	Initialize the MCP Tool Registration Service for Azure Foundry.
__new__
add_tool_servers_to_agent	Adds MCP tool servers to an Azure Foundry agent.
send_chat_history	Retrieve and send chat history from Azure AI Foundry to the MCP platform. This method retrieves messages from the Azure AI Foundry Agents API using the provided client and thread ID, converts them to ChatHistoryMessage format, and sends them to the MCP platform.
send_chat_history_messages	Send Azure AI Foundry chat history messages to the MCP platform. This method accepts a sequence of Azure AI Foundry ThreadMessage objects, converts them to ChatHistoryMessage format, and sends them to the MCP platform for real-time threat protection.

init

Initialize the MCP Tool Registration Service for Azure Foundry.

__init__(logger: Logger | None = None, credential: DefaultAzureCredential | None = None)

Parameters

Name	Description
logger	Logger \| None Logger instance for logging operations. Default value: None
credential	<xref:azure.identity._credentials.default.DefaultAzureCredential> \| None Azure credential for authentication. If None, DefaultAzureCredential will be used. Default value: None

new

__new__(**kwargs)

add_tool_servers_to_agent

Adds MCP tool servers to an Azure Foundry agent.

async add_tool_servers_to_agent(project_client: AIProjectClient, auth: Authorization, auth_handler_name: str, context: TurnContext, auth_token: str | None = None) -> None

Parameters

Name	Description
project_client Required	<xref:azure.ai.projects._patch.AIProjectClient> The Azure Foundry AIProjectClient instance.
auth Required	Authorization Authorization handler for token exchange.
auth_handler_name Required	str Name of the authorization handler.
context Required	TurnContext Turn context for the current operation.
auth_token	str \| None Authentication token to access the MCP servers. Default value: None

Returns

Type	Description
None

Exceptions

Type	Description
ValueError	If project_client is None or required parameters are invalid.
Exception	If there's an error during MCP tool registration.

send_chat_history

Retrieve and send chat history from Azure AI Foundry to the MCP platform.

This method retrieves messages from the Azure AI Foundry Agents API using the provided client and thread ID, converts them to ChatHistoryMessage format, and sends them to the MCP platform.

async send_chat_history(agents_client: AgentsClient, thread_id: str, turn_context: TurnContext, tool_options: ToolOptions | None = None) -> OperationResult

Parameters

Name	Description
agents_client Required	<xref:azure.ai.agents._patch.AgentsClient> The Azure AI Foundry AgentsClient instance.
thread_id Required	str The thread ID containing the messages to send.
turn_context Required	TurnContext TurnContext from the Agents SDK containing conversation info.
tool_options	ToolOptions \| None Optional configuration for the request. Default value: None

Returns

Type	Description
OperationResult	OperationResult indicating success or failure.

Exceptions

Type	Description
ValueError	If agents_client, thread_id, or turn_context is None/empty.

Examples


>>> from azure.ai.agents import AgentsClient
>>> from azure.identity import DefaultAzureCredential
>>>
>>> client = AgentsClient(endpoint, credential=DefaultAzureCredential())
>>> service = McpToolRegistrationService()
>>> result = await service.send_chat_history(
...     client, thread_id, turn_context
... )

send_chat_history_messages

Send Azure AI Foundry chat history messages to the MCP platform.

This method accepts a sequence of Azure AI Foundry ThreadMessage objects, converts them to ChatHistoryMessage format, and sends them to the MCP platform for real-time threat protection.

async send_chat_history_messages(turn_context: TurnContext, messages: Sequence[ThreadMessage], tool_options: ToolOptions | None = None) -> OperationResult

Parameters

Name	Description
turn_context Required	TurnContext TurnContext from the Agents SDK containing conversation info.
messages Required	Sequence[<xref:azure.ai.agents.models._patch.ThreadMessage>] Sequence of Azure AI Foundry ThreadMessage objects to send.
tool_options	ToolOptions \| None Optional configuration for the request. Default value: None

Returns

Type	Description
OperationResult	OperationResult indicating success or failure.

Exceptions

Type	Description
ValueError	If turn_context or messages is None.

Examples


>>> service = McpToolRegistrationService()
>>> messages = await agents_client.messages.list(thread_id=thread_id)
>>> result = await service.send_chat_history_messages(
...     turn_context, list(messages)
... )
>>> if result.succeeded:
...     print("Chat history sent successfully")