Name	Name	Last commit message	Last commit date
parent directory ..
solution	solution
README.md	README.md

Creating a client with LLM

So far, you've seen how to create a server and a client. The client has been able to call the server explicitly to list its tools, resources, and prompts. However, this is not a very practical approach. Your users live in the agentic era and expect to use prompts and communicate with an LLM instead. They do not care whether you use MCP to store your capabilities; they simply expect to interact using natural language. So how do we solve this? The solution is to add an LLM to the client.

Overview

In this lesson we focus on adding an LLM to do your client and show how this provides a much better experience for your user.

Learning Objectives

By the end of this lesson, you will be able to:

Create a client with an LLM.
Seamlessly interact with an MCP server using an LLM.
Provide a better end user experience on the client side.

Approach

Let's try to understand the approach we need to take. Adding an LLM sounds simple, but will we actually do this?

Here's how the client will interact with the server:

Establish connection with server.
List capabilities, prompts, resources and tools, and save down their schema.
Add an LLM and pass the saved capabilities and their schema in a format the LLM understands.
Handle a user prompt by passing it to the LLM together with the tools listed by the client.

Great, now we understand how we can do this at high level, let's try this out in below exercise.

Exercise: Creating a client with an LLM

In this exercise, we will learn to add an LLM to our client.

Authentication using GitHub Personal Access Token

Creating a GitHub token is a straightforward process. Here’s how you can do it:

Go to GitHub Settings – Click on your profile picture in the top right corner and select Settings.
Navigate to Developer Settings – Scroll down and click on Developer Settings.
Select Personal Access Tokens – Click on Fine-grained tokens and then Generate new token.
Configure Your Token – Add a note for reference, set an expiration date, and select the necessary scopes (permissions). In this case be sure to add the Models permission.
Generate and Copy the Token – Click Generate token, and make sure to copy it immediately, as you won’t be able to see it again.

-1- Connect to server

Let's create our client first:

TypeScript

import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { StdioClientTransport } from "@modelcontextprotocol/sdk/client/stdio.js";
import { Transport } from "@modelcontextprotocol/sdk/shared/transport.js";
import OpenAI from "openai";
import { z } from "zod"; // Import zod for schema validation

class MCPClient {
    private openai: OpenAI;
    private client: Client;
    constructor(){
        this.openai = new OpenAI({
            baseURL: "https://models.inference.ai.azure.com", 
            apiKey: process.env.GITHUB_TOKEN,
        });

        this.client = new Client(
            {
                name: "example-client",
                version: "1.0.0"
            },
            {
                capabilities: {
                prompts: {},
                resources: {},
                tools: {}
                }
            }
            );    
    }
}

In the preceding code we've:

Imported the needed libraries
Create a class with two members, client and openai that will help us manage a client and interact with an LLM respectively.
Configured our LLM instance to use GitHub Models by setting baseUrl to point to the inference API.

Python

from mcp import ClientSession, StdioServerParameters, types
from mcp.client.stdio import stdio_client

# Create server parameters for stdio connection
server_params = StdioServerParameters(
    command="mcp",  # Executable
    args=["run", "server.py"],  # Optional command line arguments
    env=None,  # Optional environment variables
)


async def run():
    async with stdio_client(server_params) as (read, write):
        async with ClientSession(
            read, write
        ) as session:
            # Initialize the connection
            await session.initialize()


if __name__ == "__main__":
    import asyncio

    asyncio.run(run())

In the preceding code we've:

Imported the needed libraries for MCP
Created a client

.NET

using Azure;
using Azure.AI.Inference;
using Azure.Identity;
using System.Text.Json;
using ModelContextProtocol.Client;
using System.Text.Json;

var clientTransport = new StdioClientTransport(new()
{
    Name = "Demo Server",
    Command = "/workspaces/mcp-for-beginners/03-GettingStarted/02-client/solution/server/bin/Debug/net8.0/server",
    Arguments = [],
});

await using var mcpClient = await McpClient.CreateAsync(clientTransport);

Java

First, you'll need to add the LangChain4j dependencies to your pom.xml file. Add these dependencies to enable MCP integration and GitHub Models support:

<properties>
    <langchain4j.version>1.0.0-beta3</langchain4j.version>
</properties>

<dependencies>
    <!-- LangChain4j MCP Integration -->
    <dependency>
        <groupId>dev.langchain4j</groupId>
        <artifactId>langchain4j-mcp</artifactId>
        <version>${langchain4j.version}</version>
    </dependency>
    
    <!-- OpenAI Official API Client -->
    <dependency>
        <groupId>dev.langchain4j</groupId>
        <artifactId>langchain4j-open-ai-official</artifactId>
        <version>${langchain4j.version}</version>
    </dependency>
    
    <!-- GitHub Models Support -->
    <dependency>
        <groupId>dev.langchain4j</groupId>
        <artifactId>langchain4j-github-models</artifactId>
        <version>${langchain4j.version}</version>
    </dependency>
    
    <!-- Spring Boot Starter (optional, for production apps) -->
    <dependency>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-actuator</artifactId>
    </dependency>
</dependencies>

Then create your Java client class:

import dev.langchain4j.mcp.McpToolProvider;
import dev.langchain4j.mcp.client.DefaultMcpClient;
import dev.langchain4j.mcp.client.McpClient;
import dev.langchain4j.mcp.client.transport.McpTransport;
import dev.langchain4j.mcp.client.transport.http.HttpMcpTransport;
import dev.langchain4j.model.chat.ChatLanguageModel;
import dev.langchain4j.model.openaiofficial.OpenAiOfficialChatModel;
import dev.langchain4j.service.AiServices;
import dev.langchain4j.service.tool.ToolProvider;

import java.time.Duration;
import java.util.List;

public class LangChain4jClient {
    
    public static void main(String[] args) throws Exception {        // Configure the LLM to use GitHub Models
        ChatLanguageModel model = OpenAiOfficialChatModel.builder()
                .isGitHubModels(true)
                .apiKey(System.getenv("GITHUB_TOKEN"))
                .timeout(Duration.ofSeconds(60))
                .modelName("gpt-4.1-nano")
                .build();

        // Create MCP transport for connecting to server
        McpTransport transport = new HttpMcpTransport.Builder()
                .sseUrl("http://localhost:8080/sse")
                .timeout(Duration.ofSeconds(60))
                .logRequests(true)
                .logResponses(true)
                .build();

        // Create MCP client
        McpClient mcpClient = new DefaultMcpClient.Builder()
                .transport(transport)
                .build();
    }
}

In the preceding code we've:

Added LangChain4j dependencies: Required for MCP integration, OpenAI official client, and GitHub Models support
Imported the LangChain4j libraries: For MCP integration and OpenAI chat model functionality
Created a ChatLanguageModel: Configured to use GitHub Models with your GitHub token
Set up HTTP transport: Using Server-Sent Events (SSE) to connect to the MCP server
Created an MCP client: That will handle communication with the server
Used LangChain4j's built-in MCP support: Which simplifies integration between LLMs and MCP servers

Rust

This example assumes you have a Rust based MCP server running. If you don't have one, refer back to the 01-first-server lesson to create the server.

Once you have your Rust MCP server, open a terminal and navigate to the same directory as the server. Then run the following command to create a new LLM client project:

mkdir calculator-llmclient
cd calculator-llmclient
cargo init

Add the following dependencies to your Cargo.toml file:

[dependencies]
async-openai = { version = "0.29.0", features = ["byot"] }
rmcp = { version = "0.5.0", features = ["client", "transport-child-process"] }
serde_json = "1.0.141"
tokio = { version = "1.46.1", features = ["rt-multi-thread"] }

Note

There isn't an official Rust library for OpenAI, however, the async-openai crate is a community maintained library that is commonly used.

Open the src/main.rs file and replace its content with the following code:

use async_openai::{Client, config::OpenAIConfig};
use rmcp::{
    RmcpError,
    model::{CallToolRequestParam, ListToolsResult},
    service::{RoleClient, RunningService, ServiceExt},
    transport::{ConfigureCommandExt, TokioChildProcess},
};
use serde_json::{Value, json};
use std::error::Error;
use tokio::process::Command;

#[tokio::main]
async fn main() -> Result<(), Box<dyn Error>> {
    // Initial message
    let mut messages = vec![json!({"role": "user", "content": "What is the sum of 3 and 2?"})];

    // Setup OpenAI client
    let api_key = std::env::var("OPENAI_API_KEY")?;
    let openai_client = Client::with_config(
        OpenAIConfig::new()
            .with_api_base("https://models.github.ai/inference/chat")
            .with_api_key(api_key),
    );

    // Setup MCP client
    let server_dir = std::path::Path::new(env!("CARGO_MANIFEST_DIR"))
        .parent()
        .unwrap()
        .join("calculator-server");

    let mcp_client = ()
        .serve(
            TokioChildProcess::new(Command::new("cargo").configure(|cmd| {
                cmd.arg("run").current_dir(server_dir);
            }))
            .map_err(RmcpError::transport_creation::<TokioChildProcess>)?,
        )
        .await?;

    // TODO: Get MCP tool listing 

    // TODO: LLM conversation with tool calls

    Ok(())
}

This code sets up a basic Rust application that will connect to an MCP server and GitHub Models for LLM interactions.

Important

Make sure to set the OPENAI_API_KEY environment variable with your GitHub token before running the application.

Great, for our next step, let's list the capabilities on the server.

-2- List server capabilities

Now we will connect to the server and ask for its capabilities:

Typescript

In the same class, add the following methods:

async connectToServer(transport: Transport) {
     await this.client.connect(transport);
     this.run();
     console.error("MCPClient started on stdin/stdout");
}

async run() {
    console.log("Asking server for available tools");

    // listing tools
    const toolsResult = await this.client.listTools();
}

In the preceding code we've:

Added code for connecting to the server, connectToServer.
Created a run method responsible for handling our app flow. So far it only lists the tools but we will add more to it shortly.

Python

# List available resources
resources = await session.list_resources()
print("LISTING RESOURCES")
for resource in resources:
    print("Resource: ", resource)

# List available tools
tools = await session.list_tools()
print("LISTING TOOLS")
for tool in tools.tools:
    print("Tool: ", tool.name)
    print("Tool", tool.inputSchema["properties"])

Here's what we added:

Listing resources and tools and printed them. For tools we also list inputSchema which we use later.

.NET

async Task<List<ChatCompletionsToolDefinition>> GetMcpTools()
{
    Console.WriteLine("Listing tools");
    var tools = await mcpClient.ListToolsAsync();

    List<ChatCompletionsToolDefinition> toolDefinitions = new List<ChatCompletionsToolDefinition>();

    foreach (var tool in tools)
    {
        Console.WriteLine($"Connected to server with tools: {tool.Name}");
        Console.WriteLine($"Tool description: {tool.Description}");
        Console.WriteLine($"Tool parameters: {tool.JsonSchema}");

        // TODO: convert tool definition from MCP tool to LLm tool     
    }

    return toolDefinitions;
}

In the preceding code we've:

Listed the tools available on the MCP Server
For each tool, listed name, description and its schema. The latter is something we will use to call the tools shortly.

Java

// Create a tool provider that automatically discovers MCP tools
ToolProvider toolProvider = McpToolProvider.builder()
        .mcpClients(List.of(mcpClient))
        .build();

// The MCP tool provider automatically handles:
// - Listing available tools from the MCP server
// - Converting MCP tool schemas to LangChain4j format
// - Managing tool execution and responses

In the preceding code we've:

Created a McpToolProvider that automatically discovers and registers all tools from the MCP server
The tool provider handles the conversion between MCP tool schemas and LangChain4j's tool format internally
This approach abstracts away the manual tool listing and conversion process

Rust

Retrieving tools from the MCP server is done using the list_tools method. In your main function, after setting up the MCP client, add the following code:

// Get MCP tool listing 
let tools = mcp_client.list_tools(Default::default()).await?;

-3- Convert server capabilities to LLM tools

Next step after listing server capabilities is to convert them into a format that the LLM understands. Once we do that, we can provide these capabilities as tools to our LLM.

TypeScript

Add the following code to convert response from MCP Server to a tool format the LLM can use:

openAiToolAdapter(tool: {
    name: string;
    description?: string;
    input_schema: any;
    }) {
    // Create a zod schema based on the input_schema
    const schema = z.object(tool.input_schema);

    return {
        type: "function" as const, // Explicitly set type to "function"
        function: {
        name: tool.name,
        description: tool.description,
        parameters: {
        type: "object",
        properties: tool.input_schema.properties,
        required: tool.input_schema.required,
        },
        },
    };
}

The above code takes a response from the MCP Server and converts that to a tool definition format the LLM can understand.

Let's update the run method next to list server capabilities:

async run() {
    console.log("Asking server for available tools");
    const toolsResult = await this.client.listTools();
    const tools = toolsResult.tools.map((tool) => {
        return this.openAiToolAdapter({
        name: tool.name,
        description: tool.description,
        input_schema: tool.inputSchema,
        });
    });
}

In the preceding code, we've update the run method to map through the result and for each entry call openAiToolAdapter.

Python

First, let's create the following converter function

def convert_to_llm_tool(tool):
    tool_schema = {
        "type": "function",
        "function": {
            "name": tool.name,
            "description": tool.description,
            "type": "function",
            "parameters": {
                "type": "object",
                "properties": tool.inputSchema["properties"]
            }
        }
    }

    return tool_schema

In the function above convert_to_llm_tools we take an MCP tool response and convert it to a format that the LLM can understand.

Next, let's update our client code to leverage this function like so:

functions = []
for tool in tools.tools:
    print("Tool: ", tool.name)
    print("Tool", tool.inputSchema["properties"])
    functions.append(convert_to_llm_tool(tool))

Here, we're adding a call to convert_to_llm_tool to convert the MCP tool response to something we can feed the LLM later.

.NET

Let's add code to convert the MCP tool response to something the LLM can understand

ChatCompletionsToolDefinition ConvertFrom(string name, string description, JsonElement jsonElement)
{ 
    // convert the tool to a function definition
    FunctionDefinition functionDefinition = new FunctionDefinition(name)
    {
        Description = description,
        Parameters = BinaryData.FromObjectAsJson(new
        {
            Type = "object",
            Properties = jsonElement
        },
        new JsonSerializerOptions() { PropertyNamingPolicy = JsonNamingPolicy.CamelCase })
    };

    // create a tool definition
    ChatCompletionsToolDefinition toolDefinition = new ChatCompletionsToolDefinition(functionDefinition);
    return toolDefinition;
}

In the preceding code we've:

Created a function ConvertFrom that takes, name, description and input schema.
Defined functionality that creates a FunctionDefinition that gets passed to a ChatCompletionsDefinition. The latter is something the LLM can understand.

Let's see how we can update some existing code to take advantage of this function above:

async Task<List<ChatCompletionsToolDefinition>> GetMcpTools()
{
    Console.WriteLine("Listing tools");
    var tools = await mcpClient.ListToolsAsync();

    List<ChatCompletionsToolDefinition> toolDefinitions = new List<ChatCompletionsToolDefinition>();

    foreach (var tool in tools)
    {
        Console.WriteLine($"Connected to server with tools: {tool.Name}");
        Console.WriteLine($"Tool description: {tool.Description}");
        Console.WriteLine($"Tool parameters: {tool.JsonSchema}");

        JsonElement propertiesElement;
        tool.JsonSchema.TryGetProperty("properties", out propertiesElement);

        var def = ConvertFrom(tool.Name, tool.Description, propertiesElement);
        Console.WriteLine($"Tool definition: {def}");
        toolDefinitions.Add(def);

        Console.WriteLine($"Properties: {propertiesElement}");        
    }

    return toolDefinitions;
}
```    In the preceding code, we've:

- Update the function to convert the MCP tool response to an LLm tool. Let's highlight the code we added:

    ```csharp
    JsonElement propertiesElement;
    tool.JsonSchema.TryGetProperty("properties", out propertiesElement);

    var def = ConvertFrom(tool.Name, tool.Description, propertiesElement);
    Console.WriteLine($"Tool definition: {def}");
    toolDefinitions.Add(def);
    ```

    The input schema is part of the tool response but on the "properties" attribute, so we need to extract. Furthermore, we now call `ConvertFrom` with the tool details. Now we've done the heavy lifting, let's see how it call comes together as we handle a user prompt next.

Java

// Create a Bot interface for natural language interaction
public interface Bot {
    String chat(String prompt);
}

// Configure the AI service with LLM and MCP tools
Bot bot = AiServices.builder(Bot.class)
        .chatLanguageModel(model)
        .toolProvider(toolProvider)
        .build();

In the preceding code we've:

Defined a simple Bot interface for natural language interactions
Used LangChain4j's AiServices to automatically bind the LLM with the MCP tool provider
The framework automatically handles tool schema conversion and function calling behind the scenes
This approach eliminates manual tool conversion - LangChain4j handles all the complexity of converting MCP tools to LLM-compatible format

Rust

To convert the MCP tool response to a format that the LLM can understand, we will add a helper function that formats the tools listing. Add the following code to your main.rs file below the main function. This will be called when making requests to the LLM:

async fn format_tools(tools: &ListToolsResult) -> Result<Vec<Value>, Box<dyn Error>> {
    let tools_json = serde_json::to_value(tools)?;
    let Some(tools_array) = tools_json.get("tools").and_then(|t| t.as_array()) else {
        return Ok(vec![]);
    };

    let formatted_tools = tools_array
        .iter()
        .filter_map(|tool| {
            let name = tool.get("name")?.as_str()?;
            let description = tool.get("description")?.as_str()?;
            let schema = tool.get("inputSchema")?;

            Some(json!({
                "type": "function",
                "function": {
                    "name": name,
                    "description": description,
                    "parameters": {
                        "type": "object",
                        "properties": schema.get("properties").unwrap_or(&json!({})),
                        "required": schema.get("required").unwrap_or(&json!([]))
                    }
                }
            }))
        })
        .collect();

    Ok(formatted_tools)
}

Great, we're not set up to handle any user requests, so let's tackle that next.

-4- Handle user prompt request

In this part of the code, we will handle user requests.

TypeScript

Add a method that will be used to call our LLM:

async callTools(
    tool_calls: OpenAI.Chat.Completions.ChatCompletionMessageToolCall[],
    toolResults: any[]
) {
    for (const tool_call of tool_calls) {
    const toolName = tool_call.function.name;
    const args = tool_call.function.arguments;

    console.log(`Calling tool ${toolName} with args ${JSON.stringify(args)}`);


    // 2. Call the server's tool 
    const toolResult = await this.client.callTool({
        name: toolName,
        arguments: JSON.parse(args),
    });

    console.log("Tool result: ", toolResult);

    // 3. Do something with the result
    // TODO  

    }
}

In the preceding code we:

Added a method callTools.

The method takes an LLM response and checks to see what tools have been called, if any:

for (const tool_call of tool_calls) {
const toolName = tool_call.function.name;
const args = tool_call.function.arguments;

console.log(`Calling tool ${toolName} with args ${JSON.stringify(args)}`);

// call tool
}

Calls a tool, if LLM indicates it should be called:

// 2. Call the server's tool 
const toolResult = await this.client.callTool({
    name: toolName,
    arguments: JSON.parse(args),
});

console.log("Tool result: ", toolResult);

// 3. Do something with the result
// TODO

Update the run method to include calls to the LLM and calling callTools:

// 1. Create messages that's input for the LLM
const prompt = "What is the sum of 2 and 3?"

const messages: OpenAI.Chat.Completions.ChatCompletionMessageParam[] = [
        {
            role: "user",
            content: prompt,
        },
    ];

console.log("Querying LLM: ", messages[0].content);

// 2. Calling the LLM
let response = this.openai.chat.completions.create({
    model: "gpt-4.1-mini",
    max_tokens: 1000,
    messages,
    tools: tools,
});    

let results: any[] = [];

// 3. Go through the LLM response,for each choice, check if it has tool calls 
(await response).choices.map(async (choice: { message: any; }) => {
    const message = choice.message;
    if (message.tool_calls) {
        console.log("Making tool call")
        await this.callTools(message.tool_calls, results);
    }
});

Great, let's list the code in full:

import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { StdioClientTransport } from "@modelcontextprotocol/sdk/client/stdio.js";
import { Transport } from "@modelcontextprotocol/sdk/shared/transport.js";
import OpenAI from "openai";
import { z } from "zod"; // Import zod for schema validation

class MyClient {
    private openai: OpenAI;
    private client: Client;
    constructor(){
        this.openai = new OpenAI({
            baseURL: "https://models.inference.ai.azure.com", // might need to change to this url in the future: https://models.github.ai/inference
            apiKey: process.env.GITHUB_TOKEN,
        });

        this.client = new Client(
            {
                name: "example-client",
                version: "1.0.0"
            },
            {
                capabilities: {
                prompts: {},
                resources: {},
                tools: {}
                }
            }
            );    
    }

    async connectToServer(transport: Transport) {
        await this.client.connect(transport);
        this.run();
        console.error("MCPClient started on stdin/stdout");
    }

    openAiToolAdapter(tool: {
        name: string;
        description?: string;
        input_schema: any;
          }) {
          // Create a zod schema based on the input_schema
          const schema = z.object(tool.input_schema);
      
          return {
            type: "function" as const, // Explicitly set type to "function"
            function: {
              name: tool.name,
              description: tool.description,
              parameters: {
              type: "object",
              properties: tool.input_schema.properties,
              required: tool.input_schema.required,
              },
            },
          };
    }
    
    async callTools(
        tool_calls: OpenAI.Chat.Completions.ChatCompletionMessageToolCall[],
        toolResults: any[]
      ) {
        for (const tool_call of tool_calls) {
          const toolName = tool_call.function.name;
          const args = tool_call.function.arguments;
    
          console.log(`Calling tool ${toolName} with args ${JSON.stringify(args)}`);
    
    
          // 2. Call the server's tool 
          const toolResult = await this.client.callTool({
            name: toolName,
            arguments: JSON.parse(args),
          });
    
          console.log("Tool result: ", toolResult);
    
          // 3. Do something with the result
          // TODO  
    
         }
    }

    async run() {
        console.log("Asking server for available tools");
        const toolsResult = await this.client.listTools();
        const tools = toolsResult.tools.map((tool) => {
            return this.openAiToolAdapter({
              name: tool.name,
              description: tool.description,
              input_schema: tool.inputSchema,
            });
        });

        const prompt = "What is the sum of 2 and 3?";
    
        const messages: OpenAI.Chat.Completions.ChatCompletionMessageParam[] = [
            {
                role: "user",
                content: prompt,
            },
        ];

        console.log("Querying LLM: ", messages[0].content);
        let response = this.openai.chat.completions.create({
            model: "gpt-4.1-mini",
            max_tokens: 1000,
            messages,
            tools: tools,
        });    

        let results: any[] = [];
    
        // 1. Go through the LLM response,for each choice, check if it has tool calls 
        (await response).choices.map(async (choice: { message: any; }) => {
          const message = choice.message;
          if (message.tool_calls) {
              console.log("Making tool call")
              await this.callTools(message.tool_calls, results);
          }
        });
    }
    
}

let client = new MyClient();
 const transport = new StdioClientTransport({
            command: "node",
            args: ["./build/index.js"]
        });

client.connectToServer(transport);

Python

Let's add some imports needed to call an LLM

# llm
import os
from azure.ai.inference import ChatCompletionsClient
from azure.ai.inference.models import SystemMessage, UserMessage
from azure.core.credentials import AzureKeyCredential
import json

Next, let's add the function that will call the LLM:

# llm

def call_llm(prompt, functions):
    token = os.environ["GITHUB_TOKEN"]
    endpoint = "https://models.inference.ai.azure.com"

    model_name = "gpt-4o"

    client = ChatCompletionsClient(
        endpoint=endpoint,
        credential=AzureKeyCredential(token),
    )

    print("CALLING LLM")
    response = client.complete(
        messages=[
            {
            "role": "system",
            "content": "You are a helpful assistant.",
            },
            {
            "role": "user",
            "content": prompt,
            },
        ],
        model=model_name,
        tools = functions,
        # Optional parameters
        temperature=1.,
        max_tokens=1000,
        top_p=1.    
    )

    response_message = response.choices[0].message
    
    functions_to_call = []

    if response_message.tool_calls:
        for tool_call in response_message.tool_calls:
            print("TOOL: ", tool_call)
            name = tool_call.function.name
            args = json.loads(tool_call.function.arguments)
            functions_to_call.append({ "name": name, "args": args })

    return functions_to_call

In the preceding code we've:

Passed our functions, that we found on the MCP server and converted, to the LLM.
Then we called the LLM with said functions.
Then, we're inspecting the result to see what functions we should call, if any.
Finally, we pass an array of functions to call.

Final step, let's update our main code:

prompt = "Add 2 to 20"

# ask LLM what tools to all, if any
functions_to_call = call_llm(prompt, functions)

# call suggested functions
for f in functions_to_call:
    result = await session.call_tool(f["name"], arguments=f["args"])
    print("TOOLS result: ", result.content)

There, that was the final step, in the code above we're:

Calling an MCP tool via call_tool using a function that the LLM thought we should call based on our prompt.
Printing the result of the tool call to the MCP Server.

.NET

Let's show some code for doing an LLM prompt request:

var tools = await GetMcpTools();

for (int i = 0; i < tools.Count; i++)
{
    var tool = tools[i];
    Console.WriteLine($"MCP Tools def: {i}: {tool}");
}

// 0. Define the chat history and the user message
var userMessage = "add 2 and 4";

chatHistory.Add(new ChatRequestUserMessage(userMessage));

// 1. Define tools
ChatCompletionsToolDefinition def = CreateToolDefinition();


// 2. Define options, including the tools
var options = new ChatCompletionsOptions(chatHistory)
{
    Model = "gpt-4.1-mini",
    Tools = { tools[0] }
};

// 3. Call the model  

ChatCompletions? response = await client.CompleteAsync(options);
var content = response.Content;

In the preceding code we've:

Fetched tools from the MCP server, var tools = await GetMcpTools().
Defined a user prompt userMessage.
Constructor an options object specifying model and tools.
Made a request towards the LLM.

One last step, let's see if the LLM thinks we should call a function:

// 4. Check if the response contains a function call
ChatCompletionsToolCall? calls = response.ToolCalls.FirstOrDefault();
for (int i = 0; i < response.ToolCalls.Count; i++)
{
    var call = response.ToolCalls[i];
    Console.WriteLine($"Tool call {i}: {call.Name} with arguments {call.Arguments}");
    //Tool call 0: add with arguments {"a":2,"b":4}

    var dict = JsonSerializer.Deserialize<Dictionary<string, object>>(call.Arguments);
    var result = await mcpClient.CallToolAsync(
        call.Name,
        dict!,
        cancellationToken: CancellationToken.None
    );

    Console.WriteLine(result.Content.First(c => c.Type == "text").Text);

}

In the preceding code we've:

Looped through a list of function calls.
For each tool call, parse out name and arguments and call the tool on the MCP server using the MCP client. Finally we print the results.

Here's the code in full:

using Azure;
using Azure.AI.Inference;
using Azure.Identity;
using System.Text.Json;
using ModelContextProtocol.Client;
using ModelContextProtocol.Protocol;

var endpoint = "https://models.inference.ai.azure.com";
var token = Environment.GetEnvironmentVariable("GITHUB_TOKEN"); // Your GitHub Access Token
var client = new ChatCompletionsClient(new Uri(endpoint), new AzureKeyCredential(token));
var chatHistory = new List<ChatRequestMessage>
{
    new ChatRequestSystemMessage("You are a helpful assistant that knows about AI")
};

var clientTransport = new StdioClientTransport(new()
{
    Name = "Demo Server",
    Command = "/workspaces/mcp-for-beginners/03-GettingStarted/02-client/solution/server/bin/Debug/net8.0/server",
    Arguments = [],
});

Console.WriteLine("Setting up stdio transport");

await using var mcpClient = await McpClient.CreateAsync(clientTransport);

ChatCompletionsToolDefinition ConvertFrom(string name, string description, JsonElement jsonElement)
{ 
    // convert the tool to a function definition
    FunctionDefinition functionDefinition = new FunctionDefinition(name)
    {
        Description = description,
        Parameters = BinaryData.FromObjectAsJson(new
        {
            Type = "object",
            Properties = jsonElement
        },
        new JsonSerializerOptions() { PropertyNamingPolicy = JsonNamingPolicy.CamelCase })
    };

    // create a tool definition
    ChatCompletionsToolDefinition toolDefinition = new ChatCompletionsToolDefinition(functionDefinition);
    return toolDefinition;
}



async Task<List<ChatCompletionsToolDefinition>> GetMcpTools()
{
    Console.WriteLine("Listing tools");
    var tools = await mcpClient.ListToolsAsync();

    List<ChatCompletionsToolDefinition> toolDefinitions = new List<ChatCompletionsToolDefinition>();

    foreach (var tool in tools)
    {
        Console.WriteLine($"Connected to server with tools: {tool.Name}");
        Console.WriteLine($"Tool description: {tool.Description}");
        Console.WriteLine($"Tool parameters: {tool.JsonSchema}");

        JsonElement propertiesElement;
        tool.JsonSchema.TryGetProperty("properties", out propertiesElement);

        var def = ConvertFrom(tool.Name, tool.Description, propertiesElement);
        Console.WriteLine($"Tool definition: {def}");
        toolDefinitions.Add(def);

        Console.WriteLine($"Properties: {propertiesElement}");        
    }

    return toolDefinitions;
}

// 1. List tools on mcp server

var tools = await GetMcpTools();
for (int i = 0; i < tools.Count; i++)
{
    var tool = tools[i];
    Console.WriteLine($"MCP Tools def: {i}: {tool}");
}

// 2. Define the chat history and the user message
var userMessage = "add 2 and 4";

chatHistory.Add(new ChatRequestUserMessage(userMessage));


// 3. Define options, including the tools
var options = new ChatCompletionsOptions(chatHistory)
{
    Model = "gpt-4.1-mini",
    Tools = { tools[0] }
};

// 4. Call the model  

ChatCompletions? response = await client.CompleteAsync(options);
var content = response.Content;

// 5. Check if the response contains a function call
ChatCompletionsToolCall? calls = response.ToolCalls.FirstOrDefault();
for (int i = 0; i < response.ToolCalls.Count; i++)
{
    var call = response.ToolCalls[i];
    Console.WriteLine($"Tool call {i}: {call.Name} with arguments {call.Arguments}");
    //Tool call 0: add with arguments {"a":2,"b":4}

    var dict = JsonSerializer.Deserialize<Dictionary<string, object>>(call.Arguments);
    var result = await mcpClient.CallToolAsync(
        call.Name,
        dict!,
        cancellationToken: CancellationToken.None
    );

    Console.WriteLine(result.Content.OfType<TextContentBlock>().First().Text);

}

// 5. Print the generic response
Console.WriteLine($"Assistant response: {content}");

Java

try {
    // Execute natural language requests that automatically use MCP tools
    String response = bot.chat("Calculate the sum of 24.5 and 17.3 using the calculator service");
    System.out.println(response);

    response = bot.chat("What's the square root of 144?");
    System.out.println(response);

    response = bot.chat("Show me the help for the calculator service");
    System.out.println(response);
} finally {
    mcpClient.close();
}

In the preceding code we've:

Used simple natural language prompts to interact with the MCP server tools
The LangChain4j framework automatically handles:
- Converting user prompts to tool calls when needed
- Calling the appropriate MCP tools based on the LLM's decision
- Managing the conversation flow between the LLM and MCP server
The bot.chat() method returns natural language responses that may include results from MCP tool executions
This approach provides a seamless user experience where users don't need to know about the underlying MCP implementation

Complete code example:

public class LangChain4jClient {
    
    public static void main(String[] args) throws Exception {        ChatLanguageModel model = OpenAiOfficialChatModel.builder()
                .isGitHubModels(true)
                .apiKey(System.getenv("GITHUB_TOKEN"))
                .timeout(Duration.ofSeconds(60))
                .modelName("gpt-4.1-nano")
                .timeout(Duration.ofSeconds(60))
                .build();

        McpTransport transport = new HttpMcpTransport.Builder()
                .sseUrl("http://localhost:8080/sse")
                .timeout(Duration.ofSeconds(60))
                .logRequests(true)
                .logResponses(true)
                .build();

        McpClient mcpClient = new DefaultMcpClient.Builder()
                .transport(transport)
                .build();

        ToolProvider toolProvider = McpToolProvider.builder()
                .mcpClients(List.of(mcpClient))
                .build();

        Bot bot = AiServices.builder(Bot.class)
                .chatLanguageModel(model)
                .toolProvider(toolProvider)
                .build();

        try {
            String response = bot.chat("Calculate the sum of 24.5 and 17.3 using the calculator service");
            System.out.println(response);

            response = bot.chat("What's the square root of 144?");
            System.out.println(response);

            response = bot.chat("Show me the help for the calculator service");
            System.out.println(response);
        } finally {
            mcpClient.close();
        }
    }
}

Rust

Here is where the majority of the work happens. We will call the LLM with the initial user prompt, then process the response to see if any tools need to be called. If so, we will call those tools and continue the conversation with the LLM until no more tool calls are needed and we have a final response.

We will be making multiple calls to the LLM, so let's define a function that will handle the LLM call. Add the following function to your main.rs file:

async fn call_llm(
    client: &Client<OpenAIConfig>,
    messages: &[Value],
    tools: &ListToolsResult,
) -> Result<Value, Box<dyn Error>> {
    let response = client
        .completions()
        .create_byot(json!({
            "messages": messages,
            "model": "openai/gpt-4.1",
            "tools": format_tools(tools).await?,
        }))
        .await?;
    Ok(response)
}

This function takes the LLM client, a list of messages (including the user prompt), tools from the MCP server, and sends a request to the LLM, returning the response.

The response from the LLM will contain an array of choices. We will need to process the result to see if any tool_calls are present. This let's us know the LLM is requesting a specific tool should be called with arguments. Add the following code to the bottom of your main.rs file to define a function to handle the LLM response:

async fn process_llm_response(
    llm_response: &Value,
    mcp_client: &RunningService<RoleClient, ()>,
    openai_client: &Client<OpenAIConfig>,
    mcp_tools: &ListToolsResult,
    messages: &mut Vec<Value>,
) -> Result<(), Box<dyn Error>> {
    let Some(message) = llm_response
        .get("choices")
        .and_then(|c| c.as_array())
        .and_then(|choices| choices.first())
        .and_then(|choice| choice.get("message"))
    else {
        return Ok(());
    };

    // Print content if available
    if let Some(content) = message.get("content").and_then(|c| c.as_str()) {
        println!("🤖 {}", content);
    }

    // Handle tool calls
    if let Some(tool_calls) = message.get("tool_calls").and_then(|tc| tc.as_array()) {
        messages.push(message.clone()); // Add assistant message

        // Execute each tool call
        for tool_call in tool_calls {
            let (tool_id, name, args) = extract_tool_call_info(tool_call)?;
            println!("⚡ Calling tool: {}", name);

            let result = mcp_client
                .call_tool(CallToolRequestParam {
                    name: name.into(),
                    arguments: serde_json::from_str::<Value>(&args)?.as_object().cloned(),
                })
                .await?;

            // Add tool result to messages
            messages.push(json!({
                "role": "tool",
                "tool_call_id": tool_id,
                "content": serde_json::to_string_pretty(&result)?
            }));
        }

        // Continue conversation with tool results
        let response = call_llm(openai_client, messages, mcp_tools).await?;
        Box::pin(process_llm_response(
            &response,
            mcp_client,
            openai_client,
            mcp_tools,
            messages,
        ))
        .await?;
    }
    Ok(())
}

If tool_calls are present, it extracts the tool information, calls the MCP server with the tool request, and adds the results to the conversation messages. It then continues the conversation with the LLM and the messages are updated with the assistant's response and tool call results.

To extract tool call information that the LLM returns for MCP calls, we will add another helper function to extract everything needed to make the call. Add the following code to the bottom of your main.rs file:

fn extract_tool_call_info(tool_call: &Value) -> Result<(String, String, String), Box<dyn Error>> {
    let tool_id = tool_call
        .get("id")
        .and_then(|id| id.as_str())
        .unwrap_or("")
        .to_string();
    let function = tool_call.get("function").ok_or("Missing function")?;
    let name = function
        .get("name")
        .and_then(|n| n.as_str())
        .unwrap_or("")
        .to_string();
    let args = function
        .get("arguments")
        .and_then(|a| a.as_str())
        .unwrap_or("{}")
        .to_string();
    Ok((tool_id, name, args))
}

With all the pieces in place, we can now handle the initial user prompt and call the LLM. Update your main function to include the following code:

// LLM conversation with tool calls
let response = call_llm(&openai_client, &messages, &tools).await?;
process_llm_response(
    &response,
    &mcp_client,
    &openai_client,
    &tools,
    &mut messages,
)
.await?;

This will query the LLM with the initial user prompt asking for the sum of two numbers, and it will process the response to dynamically handle tool calls.

Great, you did it!

Assignment

Take the code from the exercise and build out the server with some more tools. Then create a client with an LLM, like in the exercise, and test it out with different prompts to make sure all your server tools gets called dynamically. This way of building a client means the end user will have a great user experience as they're able to use prompts, instead of exact client commands, and be oblivious to any MCP server being called.

Solution

Key Takeaways

Adding an LLM to your client provides a better way for users to interact with MCP Servers.
You need to convert the MCP Server response to something the LLM can understand.

Samples

Additional Resources

What's Next

Next: Consuming a server using Visual Studio Code

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

README.md

Creating a client with LLM

Overview

Learning Objectives

Approach

Exercise: Creating a client with an LLM

Authentication using GitHub Personal Access Token

-1- Connect to server

TypeScript

Python

.NET

Java

Rust

-2- List server capabilities

Typescript

Python

.NET

Java

Rust

-3- Convert server capabilities to LLM tools

TypeScript

Python

.NET

Java

Rust

-4- Handle user prompt request

TypeScript

Python

.NET

Java

Rust

Assignment

Solution

Key Takeaways

Samples

Additional Resources

What's Next

FilesExpand file tree

03-llm-client

Directory actions

More options

Directory actions

More options

Latest commit

History

03-llm-client

Folders and files

parent directory

README.md

Creating a client with LLM

Overview

Learning Objectives

Approach

Exercise: Creating a client with an LLM

Authentication using GitHub Personal Access Token

-1- Connect to server

TypeScript

Python

.NET

Java

Rust

-2- List server capabilities

Typescript

Python

.NET

Java

Rust

-3- Convert server capabilities to LLM tools

TypeScript

Python

.NET

Java

Rust

-4- Handle user prompt request

TypeScript

Python

.NET

Java

Rust

Assignment

Solution

Key Takeaways

Samples

Additional Resources

What's Next