Ligue agentes a servidores do Model Context Protocol

O exemplo seguinte mostra como adicionar o servidor MCP do GitHub a uma caixa de ferramentas e ligar a caixa de ferramentas a um agente. Selecione Prompt Agents para usar o SDK Azure AI Projects para criar um agente de prompt do lado do servidor, ou Hosted Agents para usar o Agent Framework FoundryChatClient para construir um agente efémero em processo.

Agentes de comando

import json
from azure.identity import DefaultAzureCredential
from azure.ai.projects import AIProjectClient
from azure.ai.projects.models import PromptAgentDefinition, MCPTool
from openai.types.responses.response_input_param import McpApprovalResponse, ResponseInputParam

# Format: "https://resource_name.ai.azure.com/api/projects/project_name"
PROJECT_ENDPOINT = "your_project_endpoint"
MCP_CONNECTION_NAME = "my-mcp-connection"

# Create clients to call Foundry API
project = AIProjectClient(
    endpoint=PROJECT_ENDPOINT,
    credential=DefaultAzureCredential(),
)
openai = project.get_openai_client()

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

# Create a prompt agent with MCP tool capabilities
agent = project.agents.create_version(
    agent_name="MyAgent7",
    definition=PromptAgentDefinition(
        model="gpt-5-mini",
        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.conversations.create()
print(f"Created conversation (id: {conversation.id})")

# Send initial request that will trigger the MCP tool
response = openai.responses.create(
    conversation=conversation.id,
    input="What is my username in my GitHub profile?",
    extra_body={"agent_reference": {"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" and item.id:
        print("MCP approval requested")
        print(f"  Server: {item.server_label}")
        print(f"  Tool: {getattr(item, 'name', '<unknown>')}")
        print(
            f"  Arguments: {json.dumps(getattr(item, 'arguments', None), indent=2, default=str)}"
        )

        # Approve only after you review the tool call.
        # In production, implement your own approval UX and policy.
        should_approve = (
            input("Approve this MCP tool call? (y/N): ").strip().lower() == "y"
        )
        input_list.append(
            McpApprovalResponse(
                type="mcp_approval_response",
                approve=should_approve,
                approval_request_id=item.id,
            )
        )

# Send the approval response back to continue the agent's work
response = openai.responses.create(
    input=input_list,
    previous_response_id=response.id,
    extra_body={"agent_reference": {"name": agent.name, "type": "agent_reference"}},
)

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

# Clean up resources by deleting the agent version
project.agents.delete_version(agent_name=agent.name, agent_version=agent.version)
print("Agent deleted")

Produção esperada

O exemplo seguinte mostra a saída esperada quando executa a amostra:

Agent created (id: <agent-id>, name: MyAgent7, version: 1)
Created conversation (id: <conversation-id>)
Response: Your GitHub username is "example-username".
Agent deleted

Agentes alojados

Este exemplo utiliza FoundryChatClient do Microsoft Agent Framework, cria um conjunto de ferramentas que contém o servidor MCP do GitHub e, em seguida, anexa o endpoint do conjunto de ferramentas ao seu agente alojado com FoundryToolbox. Instale os pacotes com pip install agent-framework-foundry, defina as variáveis de ambiente FOUNDRY_PROJECT_ENDPOINT e FOUNDRY_MODEL e inicie sessão com az login.

import asyncio

from agent_framework import Agent
from agent_framework.foundry import FoundryChatClient, FoundryToolbox
from azure.ai.projects import AIProjectClient
from azure.ai.projects.models import MCPToolboxTool
from azure.identity import AzureCliCredential

PROJECT_ENDPOINT = "https://<account>.services.ai.azure.com/api/projects/<project>"
MCP_CONNECTION_NAME = "my-mcp-connection"


async def main() -> None:
    credential = AzureCliCredential()

    # 1. Add the GitHub MCP server to a toolbox.
    project = AIProjectClient(endpoint=PROJECT_ENDPOINT, credential=credential)
    server_tool = MCPToolboxTool(
        server_label="api-specs",
        server_url="https://api.githubcopilot.com/mcp",
        require_approval="always",
        project_connection_id=MCP_CONNECTION_NAME,
    )
    toolbox = project.toolboxes.create_version(
        name="mcp-server-toolbox",
        description="Toolbox with the GitHub MCP server",
        tools=[server_tool],
    )

    # 2. The toolbox exposes an MCP-compatible endpoint.
    TOOLBOX_MCP_URL = (
        f"{PROJECT_ENDPOINT}/toolboxes/{toolbox.name}"
        f"/versions/{toolbox.version}/mcp?api-version=v1"
    )

    # 3. Attach the toolbox to the hosted agent as an MCP tool.
,
        timeout=120.0,
    )

    toolbox_tool = FoundryToolbox(credential, url=TOOLBOX_MCP_URL)

agent = Agent(
        client=FoundryChatClient(credential=credential),
        instructions="You are a helpful assistant that uses your MCP tool "
        "to help with Microsoft documentation questions.",
        tools=[toolbox_tool],
    )

    result = await agent.run("What is Microsoft Agent Framework?")
    print(f"Agent: {result.text}")

if __name__ == "__main__":
    asyncio.run(main())

Produção esperada

O agente chama o servidor MCP do Microsoft Learn através do endpoint da caixa de ferramentas e devolve texto fundamentado na documentação:

Agent: Microsoft Agent Framework is an open-source framework for building, orchestrating, and deploying AI agents ...

Para os padrões completos de toolbox com agente hospedado, veja Usar uma caixa de ferramentas com um agente alojado.

Crie um agente com a ferramenta MCP

O exemplo seguinte mostra como adicionar um servidor MCP remoto a uma caixa de ferramentas e ligar a caixa de ferramentas a um agente. Selecione Prompt Agents para usar o SDK Azure AI Projects para criar um agente de prompt do lado do servidor, ou Hosted Agents para usar o Microsoft Agent Framework para construir um agente efémero em processo.

Agentes de comando

O exemplo utiliza métodos síncronos para criar um agente. Para métodos assíncronos, consulte o código exemplo no SDK do Azure para .NET repositório no GitHub.

using System;
using Azure.AI.Projects;
using Azure.AI.Extensions.OpenAI;
using Azure.Identity;

// Format: "https://resource_name.ai.azure.com/api/projects/project_name"
var projectEndpoint = "your_project_endpoint";

// Create project client to call Foundry API
AIProjectClient projectClient = new(
    endpoint: new Uri(projectEndpoint),
    tokenProvider: new DefaultAzureCredential());

// Create Agent with the `MCPTool`. Note that in this scenario 
// GlobalMcpToolCallApprovalPolicy.AlwaysRequireApproval is used,
// which means that any calls to the MCP server must be approved.
DeclarativeAgentDefinition agentDefinition = new(model: "gpt-5-mini")
{
    Instructions = "You are a helpful agent that can use MCP tools to assist users. Use the available MCP tools to answer questions and perform tasks.",
    Tools = { ResponseTool.CreateMcpTool(
        serverLabel: "api-specs",
        serverUri: new Uri("https://gitmcp.io/Azure/azure-rest-api-specs"),
        toolCallApprovalPolicy: new McpToolCallApprovalPolicy(GlobalMcpToolCallApprovalPolicy.AlwaysRequireApproval
    )) }
};
AgentVersion agentVersion = projectClient.AgentAdministrationClient.CreateAgentVersion(
    agentName: "myAgent",
    options: new(agentDefinition));

// If the tool approval is required, the response item is
// of `McpToolCallApprovalRequestItem` type and contains all
// the information about tool call. This example checks that
// the server label is "api-specs" and approves the tool call.
// All other calls are denied because they should not occur for
// the current configuration.
ProjectResponsesClient responseClient = projectClient.ProjectOpenAIClient.GetProjectResponsesClientForAgent(agentVersion.Name);

CreateResponseOptions nextResponseOptions = new([ResponseItem.CreateUserMessageItem("Please summarize the Azure REST API specifications README")]);
ResponseResult latestResponse = null;

while (nextResponseOptions is not null)
{
    latestResponse = responseClient.CreateResponse(nextResponseOptions);
    nextResponseOptions = null;

    foreach (ResponseItem responseItem in latestResponse.OutputItems)
    {
        if (responseItem is McpToolCallApprovalRequestItem mcpToolCall)
        {
            nextResponseOptions = new CreateResponseOptions()
            {
                PreviousResponseId = latestResponse.Id,
            };
            if (string.Equals(mcpToolCall.ServerLabel, "api-specs"))
            {
                Console.WriteLine($"Approval requested for {mcpToolCall.ServerLabel} (tool: {mcpToolCall.ToolName})");
                Console.Write("Approve this MCP tool call? (y/N): ");
                bool approved = string.Equals(Console.ReadLine(), "y", StringComparison.OrdinalIgnoreCase);
                nextResponseOptions.InputItems.Add(ResponseItem.CreateMcpApprovalResponseItem(approvalRequestId: mcpToolCall.Id, approved: approved));
            }
            else
            {
                Console.WriteLine($"Rejecting unknown call {mcpToolCall.ServerLabel}...");
                nextResponseOptions.InputItems.Add(ResponseItem.CreateMcpApprovalResponseItem(approvalRequestId: mcpToolCall.Id, approved: false));
            }
        }
    }
}

// Output the final response from the agent.
Console.WriteLine(latestResponse.GetOutputText());

// Clean up resources by deleting the agent version.
projectClient.AgentAdministrationClient.DeleteAgentVersion(agentName: agentVersion.Name, agentVersion: agentVersion.Version);

Produção esperada

O exemplo seguinte mostra a saída esperada quando executa a amostra:

Approval requested for api-specs...
Response: The Azure REST API specifications repository contains the OpenAPI specifications for Azure services. It is
organized by service and includes guidelines for contributing new specifications. The repository is intended for use by developers building tools and services that interact with Azure APIs.

Agentes alojados

Este exemplo cria a caixa de ferramentas do servidor MCP com o SDK de Projetos de IA do Azure, e depois utiliza a integração com o Microsoft Agent Framework AddFoundryToolboxes para expor as ferramentas da caixa de ferramentas ao seu agente alojado. Defina as AZURE_AI_PROJECT_ENDPOINTvariáveis , AZURE_OPENAI_ENDPOINT, e AZURE_AI_MODEL_DEPLOYMENT_NAME de ambiente, e faça login com az login.

using Azure.AI.AgentServer.Responses;
using Azure.AI.AgentServer.Responses.Models;
using Azure.AI.OpenAI;
using Azure.AI.Projects;
using Azure.AI.Extensions.OpenAI;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Agents.AI.Foundry.Hosting;
using Microsoft.Extensions.DependencyInjection;
using OpenAI.Chat;

string projectEndpoint = Environment.GetEnvironmentVariable("AZURE_AI_PROJECT_ENDPOINT")
    ?? "https://<account>.services.ai.azure.com/api/projects/<project>";
string openAiEndpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT")
    ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
string deploymentName = Environment.GetEnvironmentVariable("AZURE_AI_MODEL_DEPLOYMENT_NAME") ?? "gpt-5-mini";

DefaultAzureCredential credential = new();

// 1. Create the MCP server tool and add it to a toolbox.
AIProjectClient projectClient = new(endpoint: new Uri(projectEndpoint), tokenProvider: credential);
McpTool mcpTool = ResponseTool.CreateMcpTool(
    serverLabel: "api-specs",
    serverUri: new Uri("https://gitmcp.io/Azure/azure-rest-api-specs"),
    toolCallApprovalPolicy: new McpToolCallApprovalPolicy(
        GlobalMcpToolCallApprovalPolicy.AlwaysRequireApproval));

ToolboxVersion toolboxVersion = projectClient.AgentAdministrationClient
    .GetAgentToolboxes().CreateToolboxVersion(
        toolboxName: "mcp-server-toolbox",
        tools: [ProjectsAgentTool.AsProjectTool(mcpTool)],
        description: "Toolbox with the GitHub MCP server");

// Create the hosted agent and register the toolbox integration.
AIAgent agent = projectClient.AsAIAgent(
    model: deploymentName,
    instructions: "You are a helpful assistant with access to the toolbox tools.",
    name: "hosted-toolbox-agent");

var builder = WebApplication.CreateBuilder(args);
builder.Services.AddFoundryResponses(agent);
builder.Services.AddFoundryToolboxes(credential, toolboxVersion.Name);

var app = builder.Build();
app.MapFoundryResponses();
app.Run();

Produção esperada

Quando invocado, o agente hospedado consulta o servidor MCP do Microsoft Learn através do endpoint toolbox para obter excertos de documentação e respostas:

User: How does one create an Azure storage account using the az CLI?

Agent: To create an Azure storage account using the az CLI, run: `az storage account create --name <name> --resource-group <rg> --location <region> --sku Standard_LRS` ...

Para uma integração mantida com o .NET Agent Framework, veja Usar uma caixa de ferramentas com um agente alojado.

Crie um agente usando a ferramenta MCP com autenticação de ligação ao projeto

Neste exemplo, aprendes a autenticar no servidor MCP do GitHub dentro de uma toolbox, depois ligas o endpoint MCP toolbox a um agente. O exemplo utiliza métodos síncronos para criar a caixa de ferramentas e o agente. Para métodos assíncronos, consulte o código exemplo no SDK do Azure para .NET repositório no GitHub.

Estabelecer ligação ao projeto

Antes de analisar a amostra:

1. Inicia sessão no teu perfil no GitHub.
2. Selecione a foto de perfil no canto superior direito.
3. Selecione Definições.
4. No painel esquerdo, selecione Definições de Programador e Tokens de acesso pessoal > Tokens (clássicos).
5. No topo, selecione Gerar novo token, introduza a sua palavra-passe e crie um token que possa ler repositórios públicos.
   • Importante: Guarde o token, ou mantenha a página aberta, pois uma vez fechada, o token não pode ser mostrado novamente.
6. No portal do Azure, abra o Microsoft Foundry.
7. Selecione Gerir no canto superior direito da navegação, selecione Detalhes do Project e depois selecione o separador Recursos Conectados.
8. Criar uma nova ligação do tipo Chaves personalizadas .
9. Atribui um nome e adiciona um par chave-valor.
10. Defina o nome da chave para Authorization e o valor deve ter a forma de Bearer your_github_token.

Exemplo de código para criar o agente

using System;
using Azure.AI.Projects;
using Azure.AI.Extensions.OpenAI;
using Azure.Identity;

// Format: "https://resource_name.ai.azure.com/api/projects/project_name"
var projectEndpoint = "your_project_endpoint";
var mcpConnectionName = "my-mcp-connection";

// Create project client to call Foundry API
AIProjectClient projectClient = new(
    endpoint: new Uri(projectEndpoint),
    tokenProvider: new DefaultAzureCredential());

// 1. Add the GitHub MCP server to a toolbox. Using a toolbox is the recommended
//    way to give agents tools. See /azure/foundry/agents/concepts/toolbox-overview
AgentToolboxes toolboxClient = projectClient.AgentAdministrationClient.GetAgentToolboxes();

McpTool mcpTool = ResponseTool.CreateMcpTool(
    serverLabel: "api-specs",
    serverUri: new Uri("https://api.githubcopilot.com/mcp"),
    toolCallApprovalPolicy: new McpToolCallApprovalPolicy(
        GlobalMcpToolCallApprovalPolicy.AlwaysRequireApproval));
mcpTool.ProjectConnectionId = mcpConnectionName;

ToolboxVersion toolboxVersion = toolboxClient.CreateToolboxVersion(
    toolboxName: "mcp-server-toolbox",
    tools: [ProjectsAgentTool.AsProjectTool(mcpTool)],
    description: "Toolbox with the GitHub MCP server");

// 2. The toolbox exposes an MCP-compatible endpoint.
var toolboxMcpUrl = new Uri(
    $"{projectEndpoint}/toolboxes/{toolboxVersion.Name}" +
    $"/versions/{toolboxVersion.Version}/mcp?api-version=v1");

// 3. Create a remote-tool project connection that points at the toolbox endpoint.
//    Use a user Entra token so the caller's identity is passed through
//    (audience https://ai.azure.com). Create the connection once, for example
//    with the Azure Developer CLI:
//
//    azd ai connection create mcp-server-toolbox-conn \
//      --kind remote-tool \
//      --target "<toolboxMcpUrl>" \
//      --auth-type user-entra-token \
//      --audience https://ai.azure.com
var toolboxConnectionName = "mcp-server-toolbox-conn";

// 4. Attach the toolbox to a prompt agent as an MCP tool. Note that in this scenario
//    GlobalMcpToolCallApprovalPolicy.AlwaysRequireApproval is used, which means that
//    any calls to the toolbox MCP endpoint must be approved.
McpTool toolboxTool = ResponseTool.CreateMcpTool(
    serverLabel: "toolbox",
    serverUri: toolboxMcpUrl,
    toolCallApprovalPolicy: new McpToolCallApprovalPolicy(
        GlobalMcpToolCallApprovalPolicy.AlwaysRequireApproval));
toolboxTool.ProjectConnectionId = toolboxConnectionName;

DeclarativeAgentDefinition agentDefinition = new(model: "gpt-5-mini")
{
    Instructions = "You are a helpful agent that can use MCP tools to assist users. Use the available MCP tools to answer questions and perform tasks.",
    Tools = { toolboxTool }
};
AgentVersion agentVersion = projectClient.AgentAdministrationClient.CreateAgentVersion(
    agentName: "myAgent",
    options: new(agentDefinition));

// If the tool approval is required, the response item is
// of McpToolCallApprovalRequestItem type and contains all
// the information about tool call. This example checks that
// the server label is "toolbox" and approves the tool call.
// All other calls are denied because they shouldn't happen given
// the current configuration.
ProjectResponsesClient responseClient = projectClient.ProjectOpenAIClient.GetProjectResponsesClientForAgent(agentVersion.Name);

CreateResponseOptions nextResponseOptions = new([ResponseItem.CreateUserMessageItem("What is my username in my GitHub profile?")]);
ResponseResult latestResponse = null;

while (nextResponseOptions is not null)
{
    latestResponse = responseClient.CreateResponse(nextResponseOptions);
    nextResponseOptions = null;

    foreach (ResponseItem responseItem in latestResponse.OutputItems)
    {
        if (responseItem is McpToolCallApprovalRequestItem mcpToolCall)
        {
            nextResponseOptions = new()
            {
                PreviousResponseId = latestResponse.Id,
            };
            if (string.Equals(mcpToolCall.ServerLabel, "toolbox"))
            {
                Console.WriteLine($"Approval requested for {mcpToolCall.ServerLabel} (tool: {mcpToolCall.ToolName})");
                Console.Write("Approve this MCP tool call? (y/N): ");
                bool approved = string.Equals(Console.ReadLine(), "y", StringComparison.OrdinalIgnoreCase);
                nextResponseOptions.InputItems.Add(ResponseItem.CreateMcpApprovalResponseItem(approvalRequestId: mcpToolCall.Id, approved: approved));
            }
            else
            {
                Console.WriteLine($"Rejecting unknown call {mcpToolCall.ServerLabel}...");
                nextResponseOptions.InputItems.Add(ResponseItem.CreateMcpApprovalResponseItem(approvalRequestId: mcpToolCall.Id, approved: false));
            }
        }
    }
}

// Output the final response from the agent.
Console.WriteLine(latestResponse.GetOutputText());

// Clean up resources by deleting the agent version.
projectClient.AgentAdministrationClient.DeleteAgentVersion(agentName: agentVersion.Name, agentVersion: agentVersion.Version);

Produção esperada

O exemplo seguinte mostra a saída esperada quando executa a amostra:

Approval requested for toolbox...
Response: Your GitHub username is "example-username".

Crie um agente em TypeScript com a ferramenta MCP

O exemplo seguinte de TypeScript demonstra como adicionar um servidor MCP a uma caixa de ferramentas, ligar a caixa de ferramentas a um agente, enviar pedidos que desencadeiam fluxos de trabalho de aprovação MCP, tratar pedidos de aprovação e limpar recursos. Para uma versão em JavaScript, consulte o código de exemplo no repositório SDK do Azure para JavaScript no GitHub.

import { DefaultAzureCredential } from "@azure/identity";
import { AIProjectClient } from "@azure/ai-projects";
import OpenAI from "openai";
import * as readline from "readline";

// Format: "https://resource_name.ai.azure.com/api/projects/project_name"
const PROJECT_ENDPOINT = "your_project_endpoint";

export async function main(): Promise<void> {
  // Create clients to call Foundry API
  const project = new AIProjectClient(PROJECT_ENDPOINT, new DefaultAzureCredential());
  const openai = project.getOpenAIClient();

  console.log("Creating agent with MCP tool...");

  // 1. Add the Azure REST API specifications MCP server to a toolbox. Using a toolbox is
  //    the recommended way to give agents tools. See /azure/foundry/agents/concepts/toolbox-overview
  const toolbox = await project.toolboxes.createVersion(
    "mcp-server-toolbox",
    [
      {
        type: "mcp",
        server_label: "api-specs",
        server_url: "https://gitmcp.io/Azure/azure-rest-api-specs",
        require_approval: "always",
      },
    ],
    { description: "Toolbox with the Azure REST API specifications MCP server" },
  );

  // 2. The toolbox exposes an MCP-compatible endpoint.
  const toolboxMcpUrl =
    `${PROJECT_ENDPOINT}/toolboxes/${toolbox.name}` +
    `/versions/${toolbox.version}/mcp?api-version=v1`;

  // 3. Create a remote-tool project connection that points at the toolbox endpoint.
  //    Use a user Entra token so the caller's identity is passed through
  //    (audience https://ai.azure.com). Create the connection once, for example
  //    with the Azure Developer CLI:
  //
  //    azd ai connection create mcp-server-toolbox-conn \
  //      --kind remote-tool \
  //      --target "<toolboxMcpUrl>" \
  //      --auth-type user-entra-token \
  //      --audience https://ai.azure.com
  const toolboxConnectionName = "mcp-server-toolbox-conn";

  // 4. Attach the toolbox to a prompt agent as an MCP tool.
  // The toolbox tool requires approval for each operation to ensure user control over external requests.
  const agent = await project.agents.createVersion("agent-mcp", {
    kind: "prompt",
    model: "gpt-5-mini",
    instructions:
      "You are a helpful agent that can use MCP tools to assist users. Use the available MCP tools to answer questions and perform tasks.",
    tools: [
      {
        type: "mcp",
        server_label: "toolbox",
        server_url: toolboxMcpUrl,
        require_approval: "always",
        project_connection_id: toolboxConnectionName,
      },
    ],
  });
  console.log(`Agent created (id: ${agent.id}, name: ${agent.name}, version: ${agent.version})`);

  // Create a conversation thread to maintain context across multiple interactions
  console.log("\nCreating conversation...");
  const conversation = await openai.conversations.create();
  console.log(`Created conversation (id: ${conversation.id})`);

  // Send initial request that will trigger the MCP tool to access Azure REST API specs
  // This will generate an approval request since requireApproval="always"
  console.log("\nSending request that will trigger MCP approval...");
  const response = await openai.responses.create(
    {
      conversation: conversation.id,
      input: "Please summarize the Azure REST API specifications Readme",
    },
    {
      body: { agent_reference: { name: agent.name, type: "agent_reference" } },
    },
  );

  // Process any MCP approval requests that were generated
  // When requireApproval="always", the agent will request permission before accessing external resources
  const inputList: OpenAI.Responses.ResponseInputItem.McpApprovalResponse[] = [];

  const rl = readline.createInterface({ input: process.stdin, output: process.stdout });
  const ask = (q: string) => new Promise<string>((resolve) => rl.question(q, resolve));
  for (const item of response.output) {
    if (item.type === "mcp_approval_request") {
      if (item.server_label === "toolbox" && item.id) {
        console.log(`\nReceived MCP approval request (id: ${item.id})`);
        console.log(`  Server: ${item.server_label}`);
        console.log(`  Tool: ${item.name}`);

        // Approve only after you review the tool call.
        // In production, implement your own approval UX and policy.
        const answer = (await ask("Approve this MCP tool call? (y/N): ")).trim().toLowerCase();
        const approve = answer === "y";
        inputList.push({
          type: "mcp_approval_response",
          approval_request_id: item.id,
          approve,
        });
      }
    }
  }

  rl.close();

  console.log(`\nProcessing ${inputList.length} approval request(s)`);
  console.log("Final input:");
  console.log(JSON.stringify(inputList, null, 2));

  // 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
  console.log("\nSending approval response...");
  const finalResponse = await openai.responses.create(
    {
      input: inputList,
      previous_response_id: response.id,
    },
    {
      body: { agent_reference: { name: agent.name, type: "agent_reference" } },
    },
  );

  console.log(`\nResponse: ${finalResponse.output_text}`);

  // Clean up resources by deleting the agent version and conversation
  // This prevents accumulation of unused resources in your project
  console.log("\nCleaning up resources...");
  await openai.conversations.delete(conversation.id);
  console.log("Conversation deleted");

  await project.agents.deleteVersion(agent.name, agent.version);
  console.log("Agent deleted");

  console.log("\nMCP sample completed!");
}

main().catch((err) => {
  console.error("The sample encountered an error:", err);
});

Produção esperada

O exemplo seguinte mostra a saída esperada quando executa a amostra:

Creating agent with MCP tool...
Agent created (id: <agent-id>, name: agent-mcp, version: 1)

Creating conversation...
Created conversation (id: <conversation-id>)

Sending request that will trigger MCP approval...

Received MCP approval request (id: <approval-request-id>)
  Server: api-specs
  Tool: get-readme

Processing 1 approval request(s)
Final input:
[
  {
    "type": "mcp_approval_response",
    "approval_request_id": "<approval-request-id>",
    "approve": true
  }
]

Sending approval response...

Response: The Azure REST API specifications repository contains the OpenAPI specifications for Azure services. It is organized by service and includes guidelines for contributing new specifications. The repository is intended for use by developers building tools and services that interact with Azure APIs.

Cleaning up resources...
Conversation deleted
Agent deleted

MCP sample completed!

Crie um agente usando a ferramenta MCP com autenticação de ligação ao projeto

O exemplo seguinte de TypeScript demonstra como adicionar um servidor MCP autenticado a uma caixa de ferramentas, ligar o endpoint MCP toolbox a um agente, enviar pedidos que desencadeiam fluxos de trabalho de aprovação MCP, gerir pedidos de aprovação e limpar recursos. Para uma versão em JavaScript, consulte o código de exemplo no repositório SDK do Azure para JavaScript no GitHub.

import { DefaultAzureCredential } from "@azure/identity";
import { AIProjectClient } from "@azure/ai-projects";
import OpenAI from "openai";
import * as readline from "readline";

// Format: "https://resource_name.ai.azure.com/api/projects/project_name"
const PROJECT_ENDPOINT = "your_project_endpoint";
const MCP_CONNECTION_NAME = "my-mcp-connection";

export async function main(): Promise<void> {
  // Create clients to call Foundry API
  const project = new AIProjectClient(PROJECT_ENDPOINT, new DefaultAzureCredential());
  const openai = project.getOpenAIClient();

  console.log("Creating agent with MCP tool using project connection...");

  // 1. Add the GitHub MCP server to a toolbox with project connection authentication.
  // The project connection should have Authorization header configured with "Bearer <GitHub PAT token>"
  // Token can be created at https://github.com/settings/personal-access-tokens/new
  const toolbox = await project.toolboxes.createVersion(
    "mcp-server-toolbox",
    [
      {
        type: "mcp",
        server_label: "api-specs",
        server_url: "https://api.githubcopilot.com/mcp",
        require_approval: "always",
        project_connection_id: MCP_CONNECTION_NAME,
      },
    ],
    { description: "Toolbox with the GitHub MCP server" },
  );

  // 2. The toolbox exposes an MCP-compatible endpoint.
  const toolboxMcpUrl =
    `${PROJECT_ENDPOINT}/toolboxes/${toolbox.name}` +
    `/versions/${toolbox.version}/mcp?api-version=v1`;

  // 3. Create a remote-tool project connection that points at the toolbox endpoint.
  //    Use a user Entra token so the caller's identity is passed through
  //    (audience https://ai.azure.com). Create the connection once, for example
  //    with the Azure Developer CLI:
  //
  //    azd ai connection create mcp-server-toolbox-conn \
  //      --kind remote-tool \
  //      --target "<toolboxMcpUrl>" \
  //      --auth-type user-entra-token \
  //      --audience https://ai.azure.com
  const toolboxConnectionName = "mcp-server-toolbox-conn";

  // 4. Attach the toolbox to a prompt agent as an MCP tool.
  const agent = await project.agents.createVersion("agent-mcp-connection-auth", {
    kind: "prompt",
    model: "gpt-5-mini",
    instructions: "Use MCP tools as needed",
    tools: [
      {
        type: "mcp",
        server_label: "toolbox",
        server_url: toolboxMcpUrl,
        require_approval: "always",
        project_connection_id: toolboxConnectionName,
      },
    ],
  });
  console.log(`Agent created (id: ${agent.id}, name: ${agent.name}, version: ${agent.version})`);

  // Create a conversation thread to maintain context across multiple interactions
  console.log("\nCreating conversation...");
  const conversation = await openai.conversations.create();
  console.log(`Created conversation (id: ${conversation.id})`);

  // Send initial request that will trigger the MCP tool
  console.log("\nSending request that will trigger MCP approval...");
  const response = await openai.responses.create(
    {
      conversation: conversation.id,
      input: "What is my username in my GitHub profile?",
    },
    {
      body: { agent_reference: { name: agent.name, type: "agent_reference" } },
    },
  );

  // Process any MCP approval requests that were generated
  const inputList: OpenAI.Responses.ResponseInputItem.McpApprovalResponse[] = [];

  const rl = readline.createInterface({ input: process.stdin, output: process.stdout });
  const ask = (q: string) => new Promise<string>((resolve) => rl.question(q, resolve));
  for (const item of response.output) {
    if (item.type === "mcp_approval_request") {
      if (item.server_label === "toolbox" && item.id) {
        console.log(`\nReceived MCP approval request (id: ${item.id})`);
        console.log(`  Server: ${item.server_label}`);
        console.log(`  Tool: ${item.name}`);

        // Approve only after you review the tool call.
        // In production, implement your own approval UX and policy.
        const answer = (await ask("Approve this MCP tool call? (y/N): ")).trim().toLowerCase();
        const approve = answer === "y";
        inputList.push({
          type: "mcp_approval_response",
          approval_request_id: item.id,
          approve,
        });
      }
    }
  }

  rl.close();

  console.log(`\nProcessing ${inputList.length} approval request(s)`);
  console.log("Final input:");
  console.log(JSON.stringify(inputList, null, 2));

  // 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
  console.log("\nSending approval response...");
  const finalResponse = await openai.responses.create(
    {
      input: inputList,
      previous_response_id: response.id,
    },
    {
      body: { agent_reference: { name: agent.name, type: "agent_reference" } },
    },
  );

  console.log(`\nResponse: ${finalResponse.output_text}`);

  // Clean up resources by deleting the agent version and conversation
  // This prevents accumulation of unused resources in your project
  console.log("\nCleaning up resources...");
  await openai.conversations.delete(conversation.id);
  console.log("Conversation deleted");

  await project.agents.deleteVersion(agent.name, agent.version);
  console.log("Agent deleted");

  console.log("\nMCP with project connection sample completed!");
}

main().catch((err) => {
  console.error("The sample encountered an error:", err);
});

Produção esperada

O exemplo seguinte mostra a saída esperada quando executa a amostra:

Creating agent with MCP tool using project connection...
Agent created (id: <agent-id>, name: agent-mcp-connection-auth, version: 1)
Creating conversation...
Created conversation (id: <conversation-id>)
Sending request that will trigger MCP approval...
Received MCP approval request (id: <approval-request-id>)
  Server: toolbox
  Tool: get-github-username
Processing 1 approval request(s)
Final input:
[
  {
    "type": "mcp_approval_response",
    "approval_request_id": "<approval-request-id>",
    "approve": true
  }
]
Sending approval response...
Response: Your GitHub username is "example-username".
Cleaning up resources...
Conversation deleted
Agent deleted
MCP with project connection sample completed!

Use ferramentas MCP num agente Java

Adicione a dependência ao seu pom.xml:

<dependency>
    <groupId>com.azure</groupId>
    <artifactId>azure-ai-agents</artifactId>
    <version>2.2.0</version>
</dependency>

Crie um agente com a ferramenta MCP

import com.azure.ai.agents.AgentsClient;
import com.azure.ai.agents.AgentsClientBuilder;
import com.azure.ai.agents.ResponsesClient;
import com.azure.ai.agents.models.AgentReference;
import com.azure.ai.agents.models.AgentVersionDetails;
import com.azure.ai.agents.models.AzureCreateResponseOptions;
import com.azure.ai.agents.models.McpTool;
import com.azure.ai.agents.models.PromptAgentDefinition;
import com.azure.identity.DefaultAzureCredentialBuilder;
import com.openai.models.responses.Response;
import com.openai.models.responses.ResponseCreateParams;

import java.util.Collections;

public class McpToolExample {
    public static void main(String[] args) {
        // Format: "https://resource_name.ai.azure.com/api/projects/project_name"
        String projectEndpoint = "your_project_endpoint";
        // Create the toolbox out-of-band by using Python, REST, the Foundry portal, C#, or TypeScript.
        String toolboxMcpUrl = projectEndpoint + "/toolboxes/mcp-server-toolbox/versions/1/mcp?api-version=v1";
        String toolboxConnectionName = "mcp-server-toolbox-conn";

        AgentsClientBuilder builder = new AgentsClientBuilder()
            .credential(new DefaultAzureCredentialBuilder().build())
            .endpoint(projectEndpoint);

        AgentsClient agentsClient = builder.buildAgentsClient();
        ResponsesClient responsesClient = builder.buildResponsesClient();

        // Attach the toolbox MCP endpoint with server label, URL, connection, and approval mode.
        McpTool mcpTool = new McpTool("toolbox")
            .setServerUrl(toolboxMcpUrl)
            .setProjectConnectionId(toolboxConnectionName)
            .setRequireApproval("always");

        // Create agent with MCP tool
        PromptAgentDefinition agentDefinition = new PromptAgentDefinition("gpt-5-mini")
            .setInstructions("You are a helpful assistant that can use MCP tools.")
            .setTools(Collections.singletonList(mcpTool));

        AgentVersionDetails agent = agentsClient.createAgentVersion("mcp-agent", agentDefinition);
        System.out.printf("Agent created: %s (version %s)%n", agent.getName(), agent.getVersion());

        // Create a response
        AgentReference agentReference = new AgentReference(agent.getName())
            .setVersion(agent.getVersion());

        Response response = responsesClient.createAzureResponse(
            new AzureCreateResponseOptions().setAgentReference(agentReference),
            ResponseCreateParams.builder()
                .input("Summarize the Azure REST API specifications"));

        System.out.println("Response: " + response.output());

        // Clean up
        agentsClient.deleteAgentVersion(agent.getName(), agent.getVersion());
    }
}

Produção esperada

Agent created: mcp-agent (version 1)
Response: [ResponseOutputItem containing MCP tool results ...]

Utilize a ferramenta de MCP com a API REST

Os exemplos seguintes mostram como criar um agente com a ferramenta MCP e chamá-lo usando a API Responses. Se a resposta incluir um item de saída com type definido para mcp_approval_request, envie um pedido de seguimento que inclua um mcp_approval_response item.

Pré-requisitos

Defina estas variáveis de ambiente:

• FOUNDRY_PROJECT_ENDPOINT: URL do endpoint do seu projeto.
• FOUNDRY_MODEL_DEPLOYMENT_NAME: O nome do seu modelo de implantação.
• AGENT_TOKEN: Um token de autenticação para a Foundry.
• MCP_PROJECT_CONNECTION_NAME (opcional): O nome da sua ligação ao projeto MCP.

Obtenha um token de acesso:

export AGENT_TOKEN=$(az account get-access-token --scope "https://ai.azure.com/.default" --query accessToken -o tsv)

Se o servidor MCP dentro da toolbox não exigir autenticação, omita project_connection_id da definição da ferramenta da toolbox. A ferramenta MCP do agente continua a usar project_connection_id para a ligação da ferramenta remota ao endpoint da caixa de ferramentas.

1. Criar uma caixa de ferramentas com o servidor MCP

A forma recomendada de adicionar um servidor MCP é através de uma caixa de ferramentas e depois ligar a caixa de ferramentas ao seu agente como uma ferramenta MCP. Veja O que é uma caixa de ferramentas?

curl -X POST "$FOUNDRY_PROJECT_ENDPOINT/toolboxes/mcp-server-toolbox/versions?api-version=v1" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AGENT_TOKEN" \
  -d '{
    "description": "Toolbox with the Azure REST API specifications MCP server",
    "tools": [
      {
        "type": "mcp",
        "server_label": "api-specs",
        "server_url": "https://gitmcp.io/Azure/azure-rest-api-specs",
        "require_approval": "never"
      }
    ]
  }'

A caixa de ferramentas expõe um endpoint compatível com MCP em $FOUNDRY_PROJECT_ENDPOINT/toolboxes/mcp-server-toolbox/versions/<version>/mcp?api-version=v1, onde <version> é a versão devolvida pela chamada anterior.

2. Criar uma ligação a uma ferramenta remota na caixa de ferramentas

Crie uma ligação remota a um projeto de ferramenta que aponte para o endpoint da caixa de ferramentas. Use um token Entra do utilizador para que a identidade do chamador seja transmitida (audiência https://ai.azure.com):

azd ai connection create mcp-server-toolbox-conn \
  --kind remote-tool \
  --target "$FOUNDRY_PROJECT_ENDPOINT/toolboxes/mcp-server-toolbox/versions/<version>/mcp?api-version=v1" \
  --auth-type user-entra-token \
  --audience https://ai.azure.com

3. Criar um agente MCP

curl -X POST "$FOUNDRY_PROJECT_ENDPOINT/agents?api-version=v1" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AGENT_TOKEN" \
  -d '{
    "name": "<AGENT_NAME>-mcp",
    "description": "MCP agent",
    "definition": {
      "kind": "prompt",
      "model": "'$FOUNDRY_MODEL_DEPLOYMENT_NAME'",
      "instructions": "You are a helpful agent that can use MCP tools to assist users. Use the available MCP tools to answer questions and perform tasks.",
      "tools": [
        {
          "type": "mcp",
          "server_label": "toolbox",
          "server_url": "'$FOUNDRY_PROJECT_ENDPOINT'/toolboxes/mcp-server-toolbox/versions/<version>/mcp?api-version=v1",
          "require_approval": "always",
          "project_connection_id": "mcp-server-toolbox-conn"
        }
      ]
    }
  }'

Para usar um servidor MCP autenticado dentro da caixa de ferramentas, adicione "project_connection_id": "'$MCP_PROJECT_CONNECTION_NAME'" à definição da ferramenta da caixa de ferramentas. Alterar server_url para o endpoint do servidor autenticado (por exemplo, https://api.githubcopilot.com/mcp).

4. Criar uma resposta

curl -X POST "$FOUNDRY_PROJECT_ENDPOINT/openai/v1/responses" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AGENT_TOKEN" \
  -d '{
    "agent": {"type": "agent_reference", "name": "<AGENT_NAME>-mcp"},
    "input": "Please summarize the Azure REST API specifications Readme"
  }'

Se a resposta incluir um item de saída com type definido para mcp_approval_request, copie o item id do pedido de aprovação como APPROVAL_REQUEST_ID. Também copie a resposta do nível superior id como PREVIOUS_RESPONSE_ID.

5. Enviar uma resposta de aprovação

Se a ferramenta MCP exigir aprovação, envie um pedido de seguimento:

curl -X POST "$FOUNDRY_PROJECT_ENDPOINT/openai/v1/responses" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AGENT_TOKEN" \
  -d '{
    "previous_response_id": "'$PREVIOUS_RESPONSE_ID'",
    "input": [
      {
        "type": "mcp_approval_response",
        "approval_request_id": "'$APPROVAL_REQUEST_ID'",
        "approve": true
      }
    ]
  }'

6. Limpar os recursos

Eliminar o agente:

curl -X DELETE "$FOUNDRY_PROJECT_ENDPOINT/agents/<AGENT_NAME>-mcp?api-version=v1" \
  -H "Authorization: Bearer $AGENT_TOKEN"

from time import sleep
from azure.identity import DefaultAzureCredential
from azure.ai.projects import AIProjectClient

PROJECT_ENDPOINT = "your_project_endpoint"
AGENT_NAME = "your_mcp_agent_name"

project = AIProjectClient(
    endpoint=PROJECT_ENDPOINT,
    credential=DefaultAzureCredential(),
)
openai = project.get_openai_client()

# Start a background response. It returns immediately with status "queued".
response = openai.responses.create(
    extra_body={
        "agent_reference": {
            "name": AGENT_NAME,
            "type": "agent_reference",
        }
    },
    input="Run the long-running task and summarize the result.",
    background=True,
)

# Poll the response ID until the MCP tool call completes.
while response.status in ("queued", "in_progress"):
    sleep(5)
    response = openai.responses.retrieve(response.id)

print(response.output_text)

using Azure.Identity;
using Azure.AI.Projects;

var projectEndpoint = "your_project_endpoint";
var agentName = "your_mcp_agent_name";

AIProjectClient projectClient = new(
    endpoint: new Uri(projectEndpoint),
    tokenProvider: new DefaultAzureCredential());

ProjectResponsesClient responsesClient
    = projectClient.ProjectOpenAIClient.GetProjectResponsesClientForAgent(agentName);

// Start a background response. It returns immediately with status "queued".
ResponseResult response = await responsesClient.CreateResponseAsync(
    new CreateResponseOptions
    {
        InputItems = { ResponseItem.CreateUserMessageItem(
            "Run the long-running task and summarize the result.") },
        Background = true,
    });

// Poll the response ID until the MCP tool call completes.
while (response.Status is "queued" or "in_progress")
{
    await Task.Delay(5000);
    response = await responsesClient.RetrieveResponseAsync(response.Id);
}
Console.WriteLine(response.GetOutputText());

import { DefaultAzureCredential } from "@azure/identity";
import { AIProjectClient } from "@azure/ai-projects";

const PROJECT_ENDPOINT = "your_project_endpoint";
const AGENT_NAME = "your_mcp_agent_name";

const project = new AIProjectClient(PROJECT_ENDPOINT, new DefaultAzureCredential());
const openai = project.getOpenAIClient();

// Start a background response. It returns immediately with status "queued".
let response = await openai.responses.create(
  {
    input: "Run the long-running task and summarize the result.",
    background: true,
  },
  { body: { agent_reference: { name: AGENT_NAME, type: "agent_reference" } } },
);

// Poll the response ID until the MCP tool call completes.
while (response.status === "queued" || response.status === "in_progress") {
  await new Promise((r) => setTimeout(r, 5000));
  response = await openai.responses.retrieve(response.id);
}
console.log(response.output_text);

import com.azure.ai.agents.*;
import com.azure.ai.agents.models.AgentReference;
import com.azure.ai.agents.models.AzureCreateResponseOptions;
import com.azure.identity.DefaultAzureCredentialBuilder;
import com.openai.models.responses.Response;
import com.openai.models.responses.ResponseCreateParams;

String projectEndpoint = "your_project_endpoint";
String agentName = "your_mcp_agent_name";

AgentsClientBuilder builder = new AgentsClientBuilder()
    .credential(new DefaultAzureCredentialBuilder().build())
    .endpoint(projectEndpoint);
ResponsesClient responsesClient = builder.buildResponsesClient();

AgentReference agentRef = new AgentReference(agentName);

// Start a background response. It returns immediately with status "queued".
Response response = responsesClient.createAzureResponse(
    new AzureCreateResponseOptions()
        .setAgentReference(agentRef)
        .setBackground(true),
    ResponseCreateParams.builder()
        .input("Run the long-running task and summarize the result."));

// Poll the response ID until the MCP tool call completes.
while (response.status().equals("queued") || response.status().equals("in_progress")) {
    Thread.sleep(5000);
    response = responsesClient.getAzureResponse(response.id());
}
System.out.println(response.output());

Criar uma resposta em segundo plano. O pedido retorna imediatamente com uma resposta id e um status de queued:

curl -X POST "$FOUNDRY_PROJECT_ENDPOINT/openai/v1/responses" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AGENT_TOKEN" \
  -d '{
    "agent": {"type": "agent_reference", "name": "<AGENT_NAME>-mcp"},
    "input": "Run the long-running task and summarize the result.",
    "background": true
  }'

Copie a resposta id do resultado e consulte-a repetidamente até que status seja completed:

curl "$FOUNDRY_PROJECT_ENDPOINT/openai/v1/responses/$RESPONSE_ID" \
  -H "Authorization: Bearer $AGENT_TOKEN"

Quando status é completed, o output array contém o resultado da chamada da ferramenta MCP e a mensagem final do assistente.