MCP SeriesGenerator
A .NET server for generating and validating vehicle serial numbers.
This is a repository for testing with Model Context Protocol
Instructions for executing the project
Running with docker:
1. Access the root directory folder in the terminal, example:
cd mcp_seriesgenerator
2. Container execution:
docker-compose up -d
3. Then run the below powershell script command, the docker.ps1 file is located in the root directory (The script will copy the files from the docker container to your local machine)
powershell -ExecutionPolicy ByPass -File docker.ps1
Running with Claude desktop app:
1. Open Claude desktop app for configuration
2. Menu - File - Settings - Developer - Edit Config
3. Open config file in location: \user\AppData\Roaming\Claude\claude_desktop_config.json (Save the file, and restart Claude for Desktop)
{
"mcpServers": {
"serialNumberGenerator": {
"command": "dotnet",
"args": [
"run",
"--project",
"C:\\ABSOLUTE\\PATH\\TO\\PROJECT",
"--no-build"
]
}
}
}
4. Look for the "Search & Tools" icon, type something like Upload Vehicle and insert the file with the serial numbers. Example:
series.txt
1313MEXXXA7989-1
0708BRAXXC4014-3
1414ARGXXA5834-9
1213ASMXXC8348-2
0202ARGXXC2614-E
0606BRAXXA6466-8
0606MEXXXA3820-4
5. More information in: https://modelcontextprotocol.io/quickstart/server
Tests with Mcp Server without client applications:
1. The Model Context Protocol (MCP) allows servers to expose tools that can be invoked externally in a standardized way.
1.1. First, it is necessary to configure the Mcp Server and its tools that will be exposed in the application. Here we configure with StdioServerTransport:
//class src/McpSeriesGenerator.App/Program.cs
builder.Services.AddMcpServer()
.WithStdioServerTransport()
.WithTools<VehicleTool>();
builder.Services.AddScoped<VehicleTool>();
1.2. In the project, there are resources created for the Mcp Server tool. Among some of them, we have, for example, ReturnsIfTheSerialNumberIsValid.
//class src/McpSeriesGenerator.App/McpServer/VehicleTool.cs
[McpServerTool(Name = "ReturnsIfTheSerialNumberIsValid"), Description("Validate serial number with check digit.")]
public string ReturnsIfTheSerialNumberIsValid(
[Description("Enter a serial number with check digit")] string SerialNumber)
{
if (string.IsNullOrWhiteSpace(SerialNumber))
{
return "Serial number cannot be empty.";
}
var vehicle = Vehicle.Create(SerialNumber);
if (vehicle.VehicleSerialNumber.ValidateCheckDigit())
{
return "This serial number is valid";
}
return "This serial number is invalid";
}
2. In the integration test project, there is communication via StdioServerTransport for real simulation of an integration between client application and Mcp Server.
2.1. In the following code, in the constructor method, a process instance is created to run the Mcp Server project externally from the integration test project.
//class test/McpSeriesGenerator.Integration/McpServer/ProcessFixture.cs
public ProcessFixture()
{
string appDll = Path.Combine(AppContext.BaseDirectory, "McpSeriesGenerator.App.dll");
_process = new Process
{
StartInfo = new ProcessStartInfo
{
FileName = "dotnet",
Arguments = $"\"{appDll}\"",
RedirectStandardInput = true,
RedirectStandardOutput = true,
RedirectStandardError = true,
UseShellExecute = false,
CreateNoWindow = true
}
};
_process.Start();
if (_process == null)
{
throw new InvalidOperationException("Failed to start MCP server process");
}
}
2.2. Example test method with the ReturnsIfTheSerialNumberIsValid tool:
//class test/McpSeriesGenerator.Integration/McpServer/VehicleToolTest.cs
public async Task MCPServer_ShouldResponseToReturnsIfTheSerialNumberIsValid()
{
Assert.NotNull(_fixture._process);
_ = Task.Run(async () =>
{
string? err;
while ((err = await _fixture._process.StandardError.ReadLineAsync()) != null)
Console.WriteLine("[STDERR] " + err);
});
var jsonString = JsonSerializer.Serialize(new
{
jsonrpc = "2.0",
id = 1,
method = "tools/call",
@params = new
{
name = "ReturnsIfTheSerialNumberIsValid",
arguments = new { SerialNumber = "0202ARGXXC2614-E" }
}
});
await _fixture._process.StandardInput.WriteLineAsync(jsonString);
await _fixture._process.StandardInput.FlushAsync();
if (_fixture._process.StandardOutput.Peek() > 0)
{
var responseOut = await _fixture._process.StandardOutput.ReadLineAsync();
Assert.True(!string.IsNullOrWhiteSpace(responseOut));
Assert.Contains("jsonrpc", responseOut);
JsonNode? node = JsonNode.Parse(responseOut);
Assert.NotNull(node);
Assert.NotNull(node?["result"]);
Assert.NotNull(node?["result"]?["isError"]);
Assert.True(bool.TryParse(node?["result"]?["isError"]?.ToString(), out bool isError));
Assert.False(isError);
}
}
Technologies and tools used:
相關伺服器
Scout Monitoring MCP
贊助Put performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
贊助Access financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
Directus
This server enables AI assistants and other MCP clients to interact with Directus instances programmatically.
My MCP Server
A remote MCP server deployable on Cloudflare Workers without authentication.
@blockrun/mcp
Access 30+ AI models in Claude Code with zero API keys. One wallet, pay-per-request.
Gemini MCP
An MCP server that orchestrates Google Gemini and Claude Code models via the OpenRouter API.
MCP Image Generator
An MCP server for generating images using Together AI or Replicate models.
MCP Neurolora
An intelligent server for code analysis, collection, and documentation generation using the OpenAI API.
Unity MCP
Perform actions in the Unity Editor for game development using AI clients.
Dify Server
Integrates the Dify AI API to generate Ant Design business component code. Supports text, image inputs, and streaming responses.
APIWeaver
A universal bridge to convert any web API into an MCP server, supporting multiple transport types.
Mermaid MCP Server
Converts Mermaid diagrams to PNG or SVG images.