StdioClientTransport
SseClientTransport
StreamClientTransport
image-20250419133222108

image-20250419140628291
TransportStdioServer 添加 Tool ：
後面講解 Tool ，這裏先跳過。
[McpServerToolType]
public class EchoTool
{
    [McpServerTool, Description("Echoes the message back to the client.")]
    public static string Echo(string message) => $"hello {message}";
}
然後創建 MCP Server 服務，並使用 WithStdioServerTransport() 暴露接口能力。
using Microsoft.Extensions.DependencyInjection;
using Microsoft.Extensions.Hosting;
using Microsoft.Extensions.Logging;
using TransportStdioServer;
var builder = Host.CreateApplicationBuilder(args);
builder.Services.AddMcpServer()
    .WithStdioServerTransport()
    .WithTools();
builder.Logging.AddConsole(options =>
{
    options.LogToStandardErrorThreshold = LogLevel.Trace;
});
await builder.Build().RunAsync();

C# 編寫 Client 時，需要通過命令行參數導入 .exe 文件，示例如下：
using Microsoft.Extensions.Configuration;
using Microsoft.Extensions.Hosting;
using ModelContextProtocol.Client;
using ModelContextProtocol.Protocol.Transport;
var builder = Host.CreateApplicationBuilder(args);
builder.Configuration
    .AddEnvironmentVariables()
    .AddUserSecrets();
var clientTransport = new StdioClientTransport(new()
{
    Name = "Demo Server",
    // 要使用絕對路徑，這裏筆者省略了
    Command = "E:/../../TransportStdioServer.exe"
});
await using var mcpClient = await McpClientFactory.CreateAsync(clientTransport);
var tools = await mcpClient.ListToolsAsync();
foreach (var tool in tools)
{
    Console.WriteLine($"Connected to server with tools: {tool.Name}");
}
啓動 TransportStdioClient，控制枱會打印 TransportStdioServer 中的所有 Mcp tool。
image-20250419140917673
StdioClientTransport 原理是基於命令行參數啓動 TransportStdioServer，StdioClient 會將命令行參數拼接起來，然後以子進程方式啓動 MCP Server，命令行示例：
cmd.exe/c E:/../TransportStdioServer.exe
StdioClientTransport 核心代碼啓動子進程：
image-20250419135453777
SSE

SSE Server 需提供兩個端點：
/sse（GET請求）：建立長連接，接收服務器推送的事件流。
/messages（POST請求）：客户端發送請求至該端點。
image-20250419142510347
在 TransportSseServer 實現簡單的 EchoTool。
[McpServerToolType]
public sealed class EchoTool
{
    [McpServerTool, Description("Echoes the input back to the client.")]
    public static string Echo(string message)
    {
        return "hello " + message;
    }
}
配置 MCP Server 支持 SSE：
using TransportSseServer.Tools;
var builder = WebApplication.CreateBuilder(args);
builder.Services.AddMcpServer()
    .WithHttpTransport()
    .WithTools()
    .WithTools();
var app = builder.Build();
app.MapMcp();
app.Run("http://0.0.0.0:5000");
TransportSseClient 實現客户端連接 Mcp Server，其代碼非常簡單，連接到 MCP Server 後將對方支持的 Tool 列出來。
using Microsoft.Extensions.Logging;
using Microsoft.Extensions.Logging.Abstractions;
using ModelContextProtocol.Client;
using ModelContextProtocol.Protocol.Transport;
var defaultOptions = new McpClientOptions
{
    ClientInfo = new() { Name = "IntegrationTestClient", Version = "1.0.0" }
};
var defaultConfig = new SseClientTransportOptions
{
    Endpoint = new Uri($"http://localhost:5000/sse"),
    Name = "Everything",
};
// Create client and run tests
await using var client = await McpClientFactory.CreateAsync(
    new SseClientTransport(defaultConfig),
    defaultOptions,
    loggerFactory: NullLoggerFactory.Instance);
var tools = await client.ListToolsAsync();
foreach (var tool in tools)
{
    Console.WriteLine($"Connected to server with tools: {tool.Name}");
}
Streamable

var echoTool = tools.First(x => x.Name == "Echo");
var result = await client.CallToolAsync("Echo", new Dictionary
{
    { "message","痴者工良"}
});
foreach (var item in result.Content)
{
    Console.WriteLine($"type: {item.Type},text: {item.Text}");
}
讓我們再回顧 MCP Server 是怎麼提供 Tool 的。
首先服務端需要定義 Tool 類和函數。
[McpServerToolType]
public sealed class EchoTool
{
    [McpServerTool, Description("Echoes the input back to the client.")]
    public static string Echo(string message)
    {
        return "hello " + message;
    }
}
Mcp server 可以通過以下兩種方式暴露 tool。
// 直接指定 Tool 類
builder.Services
    .AddMcpServer()
    .WithHttpTransport()
    .WithTools()
    .WithTools();
// 掃描程序集
builder.Services
    .AddMcpServer()
    .WithHttpTransport()
    .WithStdioServerTransport()
    .WithToolsFromAssembly();
Client 識別服務端的 Tool 列表時，可以使用 McpClientTool.ProtocolTool.InputSchema 獲取 tool 的輸入參數格式：
image-20250419152644657
其內容格式示例如下：
Annotations: null
Description: "Echoes the input back to the client."
Name: "Echo"
InputSchema: "{"title":"Echo","description":"Echoes the input back to the client.","type":"object","properties":{"message":{"type":"string"}},"required":["message"]}"
[McpServerToolType] 用於將包含應該作為ModelContextProtocol.Server.McpServerTools公開的方法的類型屬性化。
[McpServerTool]用於指示應該將方法視為 ModelContextProtocol.Server.McpServerTool。
[Description] 則用於添加註釋。
依賴注入
在實現 Tool 函數時，服務端是可以通過函數實現依賴注入的。
參考示例項目 InjectServer、InjectClient。
image-20250419160655239
添加一個服務類並註冊到容器中。
public class MyService
{
    public string Echo(string message)
    {
        return "hello " + message;
    }
}
builder.Services.AddScoped();
在 Tool 函數中注入該服務：
[McpServerToolType]
public sealed class MyTool
{
    [McpServerTool, Description("Echoes the input back to the client.")]
    public static string Echo(MyService myService, string message)
    {
        return myService.Echo(message);
    }
}

maps_direction_bicycling
maps_direction_driving
maps_direction_transit_integrated
maps_direction_walking
maps_distance
maps_geo
maps_regeocode
maps_ip_location
maps_around_search
maps_search_detail
maps_text_search
maps_weather

"McpServers": {
    "amap-amap-sse": {
      "url": "https://mcp.amap.com/sse?key={在高德官網上申請的key}"
    }
  },
  "AIModel": {
    "ModelId": "gpt-4o",
    "DeploymentName": "gpt-4o",
    "Endpoint": "https://openai.com/",
    "Key": "aaaaaaaa"
  }
image-20250419170432902
導入配置並創建日誌：
var configuration = new ConfigurationBuilder()
    .AddJsonFile("appsettings.json")
    .AddJsonFile("appsettings.Development.json")
    .Build();
using ILoggerFactory factory = LoggerFactory.Create(builder => builder.AddConsole());

var defaultOptions = new McpClientOptions
{
    ClientInfo = new() { Name = "地圖規劃", Version = "1.0.0" }
};
var defaultConfig = new SseClientTransportOptions
{
    Endpoint = new Uri(configuration["McpServers:amap-amap-sse:url"]!),
    Name = "amap-amap-sse",
};
await using var client = await McpClientFactory.CreateAsync(
    new SseClientTransport(defaultConfig),
    defaultOptions,
    loggerFactory: factory);
var tools = await client.ListToolsAsync();
foreach (var tool in tools)
{
    Console.WriteLine($"Connected to server with tools: {tool.Name}");
}
image-20250419170702770

var aiModel = configuration.GetSection("AIModel");
var builder = Kernel.CreateBuilder()
    .AddAzureOpenAIChatCompletion(
    deploymentName: aiModel["ModelId"],
    endpoint: aiModel["Endpoint"],
    apiKey: aiModel["Key"]);
builder.Services.AddLogging(s =>
{
    s.AddConsole();
});
Kernel kernel = builder.Build();
// 這裏將 mcp 轉換為 functaion call
kernel.Plugins.AddFromFunctions("amap", tools.Select(aiFunction => aiFunction.AsKernelFunction()));
var chatCompletionService = kernel.GetRequiredService();
OpenAIPromptExecutionSettings openAIPromptExecutionSettings = new()
{
    Temperature = 0,
    FunctionChoiceBehavior = FunctionChoiceBehavior.Auto(options: new() { RetainArgumentTypes = true })
};
image-20250419170714853
第三步：對話交互
編寫控制枱與用户對話交互。
var history = new ChatHistory();
string? userInput;
do
{
    Console.Write("用户提問 > ");
    userInput = Console.ReadLine();
    history.AddUserMessage(userInput!);
    var result = await chatCompletionService.GetChatMessageContentAsync(
        history,
        executionSettings: openAIPromptExecutionSettings,
        kernel: kernel);
    Console.WriteLine("AI 回答 > " + result);
    history.AddMessage(result.Role, result.Content ?? string.Empty);
} while (userInput is not null);
image-20250419170840789

"test://static/resource/{README.txt}"

builder.Services.AddMcpServer()
        .WithListResourceTemplatesHandler(async (ctx, ct) =>
        {
            return new ListResourceTemplatesResult
            {
                ResourceTemplates =
                [
                    new ResourceTemplate { Name = "Static Resource", Description = "A static resource with a numeric ID", UriTemplate = "test://static/resource/{id}" }
                ]
            };
        });
對於地址固定的 Resource，可以通過這種方式暴露出去，比如有個使用必讀的文件，只需要固定暴露地址。
builder.Services.AddMcpServer()
		.WithListResourcesHandler(async (ctx, ct) =>
        {
            await Task.CompletedTask;
            var readmeResource = new Resource
            {
                Uri = "test://static/resource/README.txt",
                Name = "Resource README.txt",
                MimeType = "application/octet-stream",
                Description = Convert.ToBase64String(Encoding.UTF8.GetBytes("這是一個必讀文件"))
            };
            return new ListResourcesResult
            {
                Resources = new List
                {
                    readmeResource
                }
            };
        })
Client 讀取資源模板和靜態資源列表：
var defaultOptions = new McpClientOptions
{
    ClientInfo = new() { Name = "ResourceClient", Version = "1.0.0" }
};
var defaultConfig = new SseClientTransportOptions
{
    Endpoint = new Uri($"http://localhost:5000/sse"),
    Name = "Everything",
};
// Create client and run tests
await using var client = await McpClientFactory.CreateAsync(
    new SseClientTransport(defaultConfig),
    defaultOptions,
    loggerFactory: NullLoggerFactory.Instance);
var resourceTemplates = await client.ListResourceTemplatesAsync();
var resources = await client.ListResourcesAsync();
foreach (var template in resourceTemplates)
{
    Console.WriteLine($"Connected to server with resource templates: {template.Name}");
}
foreach (var resource in resources)
{
    Console.WriteLine($"Connected to server with resources: {resource.Name}");
}
那麼，客户端如果從 MCP 服務器讀取資源只需要將 Resource Uri 傳遞即可。
var readmeResource = await client.ReadResourceAsync(resources.First().Uri);
這裏只介紹了 MCP Server 提供 Resource Uri，那麼當 Client 要獲取某個 Resource Uri 的內容時，MCP Server 要怎麼處理呢？
ModelContextProtocol CSharp 目前提供了兩種實現：
TextResourceContents
BlobResourceContents
比如説，當 Client 訪問 test://static/resource/README.txt 時，可以將 README.txt 文件直接以文本的形式返回：
    .WithReadResourceHandler(async (ctx, ct) =>
    {
        var uri = ctx.Params?.Uri;
        if (uri is null || !uri.StartsWith("test://static/resource/"))
        {
            throw new NotSupportedException($"Unknown resource: {uri}");
        }
        if(uri == "test://static/resource/README.txt")
        {
            var readmeResource = new Resource
            {
                Uri = "test://static/resource/README.txt",
                Name = "Resource README.txt",
                MimeType = "application/octet-stream",
                Description = "這是一個必讀文件"
            };
            return new ReadResourceResult
            {
                Contents = [new TextResourceContents
                {
                    Text = File.ReadAllText("README.txt"),
                    MimeType = readmeResource.MimeType,
                    Uri = readmeResource.Uri,
                }]
            };
        }
    })
image-20250419201835608
如果 Client 訪問了其它 Resource，則以二進制的形式返回：
    .WithReadResourceHandler(async (ctx, ct) =>
    {
        var uri = ctx.Params?.Uri;
        if (uri is null || !uri.StartsWith("test://static/resource/"))
        {
            throw new NotSupportedException($"Unknown resource: {uri}");
        }
        int index = int.Parse(uri["test://static/resource/".Length..]) - 1;
        if (index < 0 || index >= ResourceGenerator.Resources.Count)
        {
            throw new NotSupportedException($"Unknown resource: {uri}");
        }
        var resource = ResourceGenerator.Resources[index];
        return new ReadResourceResult
        {
            Contents = [new TextResourceContents
                {
                    Text = resource.Description!,
                    MimeType = resource.MimeType,
                    Uri = resource.Uri,
                }]
        };
    })