Łączenie agentów z serwerami protokołu kontekstu modelu

W poniższym przykładzie pokazano, jak dodać serwer GitHub MCP do przybornika i dołączyć przybornik do agenta. Wybierz Prompt Agents, aby użyć zestawu SDK Azure AI Projects do utworzenia agenta promptów po stronie serwera, lub Hosted Agents, aby użyć struktury Agent Framework FoundryChatClient do zbudowania efemerycznego agenta działającego w procesie.

Pobudzaj agentów

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")

Oczekiwane dane wyjściowe

W poniższym przykładzie pokazano oczekiwane dane wyjściowe po uruchomieniu przykładu:

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

Hostowani agenci

Ten przykład używa elementu FoundryChatClient z Microsoft Agent Framework, tworzy zestaw narzędzi zawierający serwer GitHub MCP, a następnie dołącza punkt końcowy zestawu narzędzi do hostowanego agenta za pomocą FoundryToolbox. Zainstaluj pakiety za pomocą polecenia pip install agent-framework-foundry, ustaw zmienne środowiskowe FOUNDRY_PROJECT_ENDPOINT i FOUNDRY_MODEL, a następnie zaloguj się za pomocą 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())

Oczekiwane dane wyjściowe

Agent wywołuje serwer Microsoft Learn MCP za pośrednictwem punktu końcowego zestawu narzędzi, a następnie zwraca tekst oparty na dokumentacji:

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

Pełny zestaw wzorców zestawu narzędzi z agentem hostowanym znajduje się w artykule Korzystanie z zestawu narzędzi z agentem hostowanym.

Tworzenie agenta za pomocą narzędzia MCP

W poniższym przykładzie pokazano, jak dodać zdalny serwer MCP do przybornika i dołączyć przybornik do agenta. Wybierz Prompt Agents, aby za pomocą zestawu SDK Azure AI Projects utworzyć po stronie serwera agenta opartego na monicie, lub Hosted Agents, aby za pomocą Microsoft Agent Framework utworzyć tymczasowego agenta działającego w procesie.

Pobudzaj agentów

W przykładzie użyto metod synchronicznych do utworzenia agenta. Aby uzyskać metody asynchroniczne, zobacz kod sample w repozytorium Azure SDK dla .NET w 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);

Oczekiwane dane wyjściowe

W poniższym przykładzie pokazano oczekiwane dane wyjściowe po uruchomieniu przykładu:

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.

Hostowani agenci

Ten przykład tworzy przybornik serwera MCP przy użyciu zestawu Azure AI Projects SDK, a następnie używa integracji Microsoft Agent Framework AddFoundryToolboxes, aby udostępnić narzędzia przybornika hostowanemu agentowi. Ustaw zmienne środowiskowe AZURE_AI_PROJECT_ENDPOINT, AZURE_OPENAI_ENDPOINT i AZURE_AI_MODEL_DEPLOYMENT_NAME, a następnie zaloguj się za pomocą 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();

Oczekiwane dane wyjściowe

Po wywołaniu hostowany agent wysyła zapytanie do serwera Microsoft Learn MCP za pośrednictwem punktu końcowego zestawu narzędzi, aby uzyskać fragmenty dokumentacji i odpowiedzi:

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` ...

Informacje o utrzymywanej integracji platformy .NET Agent Framework znajdziesz w artykule Korzystanie z przybornika z hostowanym agentem.

Tworzenie agenta przy użyciu narzędzia MCP z uwierzytelnianiem połączenia projektu

W tym przykładzie dowiesz się, jak uwierzytelniać się na serwerze GitHub MCP wewnątrz przybornika, a następnie dołączyć punkt końcowy MCP przybornika do agenta. W przykładzie użyto metod synchronicznych do utworzenia przybornika i agenta. Aby uzyskać metody asynchroniczne, zobacz kod sample w repozytorium Azure SDK dla .NET w GitHub.

Konfigurowanie połączenia projektu

Przed uruchomieniem przykładu:

1. Zaloguj się do profilu GitHub.
2. Wybierz obraz profilu w prawym górnym rogu.
3. Wybierz pozycję Ustawienia.
4. W panelu po lewej stronie wybierz pozycję Ustawienia dewelopera i Osobiste tokeny dostępu Tokeny > (wersja klasyczna).
5. W górnej części wybierz pozycję Generuj nowy token, wprowadź hasło i utwórz token, który może odczytywać repozytoria publiczne.
   • Ważne: Zapisz token lub pozostaw stronę otwartą tak, jak po zamknięciu strony nie można wyświetlić tokenu ponownie.
6. W portalu Azure otwórz Microsoft Foundry.
7. Wybierz pozycję Zarządzaj w prawym górnym obszarze nawigacji, wybierz pozycję Szczegóły projektu, a następnie wybierz kartę Połączone zasoby.
8. Utwórz nowe połączenie typu Klucze niestandardowe.
9. Nadaj mu nazwę i dodaj parę wartości klucza.
10. Ustaw nazwę klucza na Authorization , a wartość powinna mieć postać Bearer your_github_token.

Przykładowy kod umożliwiający utworzenie agenta

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);

Oczekiwane dane wyjściowe

W poniższym przykładzie pokazano oczekiwane dane wyjściowe po uruchomieniu przykładu:

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

Tworzenie agenta w języku TypeScript za pomocą narzędzia MCP

W poniższym przykładzie języka TypeScript pokazano, jak dodać serwer MCP do przybornika, dołączyć przybornik do agenta, wysłać żądania wyzwalające przepływy pracy zatwierdzania MCP, obsługiwać żądania zatwierdzenia i czyścić zasoby. Aby uzyskać wersję języka JavaScript, zobacz kod sample w repozytorium Azure SDK dla języka JavaScript w 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);
});

Oczekiwane dane wyjściowe

W poniższym przykładzie pokazano oczekiwane dane wyjściowe po uruchomieniu przykładu:

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!

Tworzenie agenta przy użyciu narzędzia MCP z uwierzytelnianiem połączenia projektu

W poniższym przykładzie języka TypeScript pokazano, jak dodać uwierzytelniony serwer MCP do przybornika, dołączyć punkt końcowy MCP przybornika do agenta, wysłać żądania wyzwalające przepływy pracy zatwierdzania MCP, obsługiwać żądania zatwierdzenia i czyścić zasoby. Aby uzyskać wersję języka JavaScript, zobacz kod sample w repozytorium Azure SDK dla języka JavaScript w 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);
});

Oczekiwane dane wyjściowe

W poniższym przykładzie pokazano oczekiwane dane wyjściowe po uruchomieniu przykładu:

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!

Korzystanie z narzędzi MCP w agencie Java

Dodaj zależność do elementu pom.xml:

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

Tworzenie agenta za pomocą narzędzia 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());
    }
}

Oczekiwane dane wyjściowe

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

Używanie narzędzia MCP z interfejsem API REST

W poniższych przykładach pokazano, jak utworzyć agenta za pomocą narzędzia MCP i wywołać go przy użyciu interfejsu API odpowiedzi. Jeśli odpowiedź zawiera element wyjściowy z type ustawionym na mcp_approval_request, wyślij żądanie uzupełniające zawierające element mcp_approval_response.

Wymagania wstępne

Ustaw następujące zmienne środowiskowe:

• FOUNDRY_PROJECT_ENDPOINT: adres URL punktu końcowego projektu.
• FOUNDRY_MODEL_DEPLOYMENT_NAME: Nazwa wdrożenia modelu.
• AGENT_TOKEN: token elementu nośnego dla rozwiązania Foundry.
• MCP_PROJECT_CONNECTION_NAME (opcjonalnie): Nazwa połączenia projektu MCP.

Uzyskiwanie tokenu dostępu:

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

Jeśli serwer MCP w przyborniku nie wymaga uwierzytelniania, pomiń project_connection_id w definicji narzędzia przybornika. Narzędzie MCP agenta nadal używa project_connection_id do połączenia z narzędziem zdalnym do punktu końcowego zestawu narzędzi.

1. Utwórz zestaw narzędzi za pomocą serwera MCP

Zalecanym sposobem dodania serwera MCP jest użycie przybornika, a następnie dołączenie przybornika do agenta jako narzędzia MCP. Zobacz Czym jest zestaw narzędzi?

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"
      }
    ]
  }'

Zestaw narzędzi udostępnia punkt końcowy zgodny z MCP pod adresem $FOUNDRY_PROJECT_ENDPOINT/toolboxes/mcp-server-toolbox/versions/<version>/mcp?api-version=v1, gdzie <version> oznacza wersję zwróconą przez poprzednie wywołanie.

2. Utwórz połączenie ze zdalnym narzędziem w przyborniku

Utwórz połączenie projektu remote-tool skierowane do punktu końcowego toolbox. Użyj tokenu użytkownika Entra, aby tożsamość wywołującego została przekazana (grupa odbiorców 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. Tworzenie agenta 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"
        }
      ]
    }
  }'

Aby użyć uwierzytelnionego serwera MCP w ramach przybornika, dodaj element "project_connection_id": "'$MCP_PROJECT_CONNECTION_NAME'" do definicji narzędzia w przyborniku. Zmień server_url na uwierzytelniony punkt końcowy serwera (na przykład https://api.githubcopilot.com/mcp).

4. Tworzenie odpowiedzi

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"
  }'

Jeśli odpowiedź zawiera element wyjściowy z ustawioną type wartością mcp_approval_request, skopiuj element id żądania zatwierdzenia jako APPROVAL_REQUEST_ID. Skopiuj również odpowiedź id najwyższego poziomu jako PREVIOUS_RESPONSE_ID.

5. Wyślij odpowiedź na zatwierdzenie

Jeśli narzędzie MCP wymaga zatwierdzenia, wyślij żądanie kontynuacji:

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. Czyszczenie zasobów

Usuń agenta:

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());

Utwórz odpowiedź w tle. Żądanie natychmiast zwraca odpowiedź id i status o wartości 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
  }'

Skopiuj odpowiedź id z wyniku, a następnie sonduj ją aż do status wartości completed:

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

Gdy status ma wartość completed, tablica output zawiera wynik wywołania narzędzia MCP i końcową wiadomość asystenta.