连接到模型上下文协议服务器（预览版）

使用以下代码示例创建代理并调用函数。 需要最新的预发行版包。 有关详细信息，请参阅 快速入门 。

import os
from dotenv import load_dotenv
from azure.identity import DefaultAzureCredential
from azure.ai.projects import AIProjectClient
from azure.ai.projects.models import PromptAgentDefinition, MCPTool, Tool
from openai.types.responses.response_input_param import McpApprovalResponse, ResponseInputParam


load_dotenv()

endpoint = os.environ["AZURE_AI_PROJECT_ENDPOINT"]

with (
    DefaultAzureCredential() as credential,
    AIProjectClient(endpoint=endpoint, credential=credential) as project_client,
    project_client.get_openai_client() as openai_client,
):

    # [START tool_declaration]
    tool = MCPTool(
        server_label="api-specs",
        server_url="https://api.githubcopilot.com/mcp",
        require_approval="always",
        project_connection_id=os.environ["MCP_PROJECT_CONNECTION_ID"],
    )
    # [END tool_declaration]

    # Create a prompt agent with MCP tool capabilities
    agent = project_client.agents.create_version(
        agent_name="MyAgent7",
        definition=PromptAgentDefinition(
            model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
            instructions="Use MCP tools as needed",
            tools=[tool],
        ),
    )
    print(f"Agent created (id: {agent.id}, name: {agent.name}, version: {agent.version})")

    # Create a conversation to maintain context across multiple interactions
    conversation = openai_client.conversations.create()
    print(f"Created conversation (id: {conversation.id})")

    # Send initial request that will trigger the MCP tool
    response = openai_client.responses.create(
        conversation=conversation.id,
        input="What is my username in Github profile?",
        extra_body={"agent": {"name": agent.name, "type": "agent_reference"}},
    )

    # Process any MCP approval requests that were generated
    input_list: ResponseInputParam = []
    for item in response.output:
        if item.type == "mcp_approval_request":
            if item.server_label == "api-specs" and item.id:
                # Automatically approve the MCP request to allow the agent to proceed
                # In production, you might want to implement more sophisticated approval logic
                input_list.append(
                    McpApprovalResponse(
                        type="mcp_approval_response",
                        approve=True,
                        approval_request_id=item.id,
                    )
                )

    print("Final input:")
    print(input_list)

    # Send the approval response back to continue the agent's work
    # This allows the MCP tool to access the GitHub repository and complete the original request
    response = openai_client.responses.create(
        input=input_list,
        previous_response_id=response.id,
        extra_body={"agent": {"name": agent.name, "type": "agent_reference"}},
    )

    print(f"Response: {response.output_text}")

    # Clean up resources by deleting the agent version
    # This prevents accumulation of unused agent versions in your project
    project_client.agents.delete_version(agent_name=agent.name, agent_version=agent.version)
    print("Agent deleted")

有关 C# 用法的示例，请参阅 GitHub 上 Azure SDK for .NET 存储库中的 Azure.AI.Projects.OpenAI 示例：使用 MCP 工具和代理，以及 使用 MCP 工具与项目连接的代理。