Community.Mcp.DotNet 0.1.0-beta.2.1

This is a prerelease version of Community.Mcp.DotNet.

{
  "servers": {
    "Community.Mcp.DotNet": {
      "type": "stdio",
      "command": "dnx",
      "args": ["Community.Mcp.DotNet@0.1.0-beta.2.1", "--yes"]
    }
  }
}

This package contains an MCP Server. The server can be used in VS Code by copying the generated JSON to your VS Code workspace's .vscode/mcp.json settings file.

dotnet tool install --global Community.Mcp.DotNet --version 0.1.0-beta.2.1

This package contains a .NET tool you can call from the shell/command line.

dotnet new tool-manifest
                    

                            if you are setting up this repo

dotnet tool install --local Community.Mcp.DotNet --version 0.1.0-beta.2.1

This package contains a .NET tool you can call from the shell/command line.

#tool dotnet:?package=Community.Mcp.DotNet&version=0.1.0-beta.2.1&prerelease

The NuGet Team does not provide support for this client. Please contact its maintainers for support.

nuke :add-package Community.Mcp.DotNet --version 0.1.0-beta.2.1

The NuGet Team does not provide support for this client. Please contact its maintainers for support.

.NET MCP Server

Give your AI assistant superpowers for .NET development! This MCP server connects GitHub Copilot, Claude, and other AI assistants directly to the .NET SDK, enabling them to create projects, manage packages, run builds, and more—all through natural language.

Quick Install

Click to install in your preferred environment:

Note: Quick install requires .NET 10 SDK (launching November 2025). See manual installation for .NET 9 support.

What is This?

The .NET MCP Server is a bridge that connects AI assistants to the .NET SDK using the Model Context Protocol. Think of it as giving your AI assistant a direct line to dotnet commands, but with intelligence and context.

graph LR
    A[AI Assistant<br/>Copilot/Claude] -->|Natural Language| B[.NET MCP Server]
    B -->|dotnet commands| C[.NET SDK]
    C -->|Results| B
    B -->|Structured Response| A
    
    style A fill:#e1f5ff
    style B fill:#fff4e6
    style C fill:#e8f5e9

Why Use It?

🚀 Faster Development

Instead of remembering exact dotnet commands and syntax, just ask:

"Create a new web API project with Entity Framework"
"Add the Serilog package and configure structured logging"
"Update all my NuGet packages to the latest versions"

🧠 Smarter AI Assistance

Your AI assistant gets direct access to:

All installed .NET templates and their parameters
NuGet package search and metadata
Framework version information (including LTS status)
Your solution and project structure

🎯 Why Not Just Let the AI Call `dotnet` Directly?

The .NET MCP Server provides context and intelligence that raw CLI execution cannot:

1. Template Discovery & Validation

With MCP: AI knows exactly which templates are installed (console, webapi, blazor, etc.) and their parameters
Without MCP: AI guesses template names and parameters, often getting them wrong

2. Framework Intelligence

With MCP: AI knows which .NET versions are installed, which are LTS, and can recommend appropriately
Without MCP: AI suggests net8.0 when you only have net9.0 installed, leading to errors

3. Rich Tool Descriptions

With MCP: Each tool has detailed parameter descriptions and constraints (e.g., "configuration must be Debug or Release")
Without MCP: AI constructs commands from general knowledge, missing version-specific changes

4. Parameter Information

With MCP: AI sees template parameters like --use-controllers, --auth, framework options
Without MCP: AI doesn't know what optional parameters exist for each template

5. Package Search Integration

With MCP: AI can search NuGet.org to find exact package names and versions
Without MCP: AI guesses package names, often suggesting outdated or incorrect ones

6. Structured Error Handling

With MCP: Errors are parsed and returned in structured format the AI can understand
Without MCP: AI gets raw stderr output and may misinterpret errors

7. MCP Resources

MCP Resources provide read-only access to structured metadata about your .NET environment:

dotnet://sdk-info - Information about installed .NET SDKs (versions and paths)
dotnet://runtime-info - Information about installed .NET runtimes (versions and types)
dotnet://templates - Complete catalog of installed .NET templates with metadata
dotnet://frameworks - Information about supported .NET frameworks (TFMs) including LTS status

This enables AI assistants to:

Answer questions without executing commands ("What .NET versions do I have installed?")
Provide context-aware suggestions based on your actual environment
Access structured JSON data more efficiently than parsing CLI output
Reference official .NET metadata for accurate recommendations

Example: Using resources for context-aware assistance

❌ Without Resources:
User: "What .NET versions do I have?"
AI: Executes dotnet --list-sdks and parses output
User: "Which is LTS?"
AI: Executes dotnet --info and tries to parse support info

✅ With Resources:
User: "What .NET versions do I have?"
AI: Reads dotnet://sdk/list resource (no execution needed)
    Returns: .NET 8.0 (LTS), .NET 9.0 (STS), .NET 10.0 (STS)
User: "Which is LTS?"
AI: Already knows from resource metadata - .NET 8.0

Example: Creating a Blazor project with authentication

❌ Without MCP:
AI: "I'll run: dotnet new blazor --auth Individual"
Result: Error - template 'blazor' doesn't support --auth parameter

✅ With MCP:
AI: Queries dotnet_template_info for 'blazor'
    Sees available parameters: --interactivity, --use-program-main, --empty
    Uses dotnet_template_search to find authentication templates
AI: "I'll create a Blazor Web App with authentication using the correct template..."
Result: Success - uses 'blazor' template with proper authentication configuration

✨ Consistent Results

The MCP server uses official .NET SDK APIs and CLI commands, ensuring:

Accurate template information from the Template Engine
Reliable command execution
Proper error handling and validation

🔒 Secure by Design

Runs locally on your machine
No data sent to external servers
You control what commands execute
Standard .NET security model applies

How It Works

sequenceDiagram
    participant User
    participant AI as AI Assistant
    participant MCP as .NET MCP Server
    participant SDK as .NET SDK

    User->>AI: "Create a console app called MyApp"
    AI->>MCP: dotnet_project_new(template: "console", name: "MyApp")
    MCP->>SDK: dotnet new console -n MyApp
    SDK-->>MCP: Project created successfully
    MCP-->>AI: Structured result with output
    AI-->>User: "I've created a new console app called MyApp"

The .NET MCP Server acts as an intelligent middleware that:

Translates natural language requests into structured .NET SDK operations
Validates parameters using official SDK metadata (templates, frameworks, packages)
Executes commands safely with proper error handling
Returns structured results that AI assistants can understand and explain

Installation

Requirements

For Quick Install: .NET 10 SDK (launching November 2025)
For Manual Install: .NET 9.0 SDK or later
Visual Studio Code, Visual Studio 2022 (v17.13+), or Claude Desktop

Option 1: Quick Install (Recommended)

Use the install badges at the top of this page to automatically configure the MCP server in your environment. The server will be downloaded from NuGet.org on first use.

Option 2: Manual Configuration

Follow the instructions below for your specific development environment:

Visual Studio Code

Using Quick Install (recommended - .NET 10 required):

Click the VS Code Install badge at the top of this page
Or manually add via Command Palette:
- Press Ctrl+Shift+P (or Cmd+Shift+P on macOS)
- Run "GitHub Copilot: Add MCP Server"
- Enter:
  - Name: dotnet
  - Type: stdio
  - Command: dnx
  - Arguments: Community.Mcp.DotNet@0.1.0-* --yes

Manual Configuration (for .NET 9 or source builds):

Edit your VS Code settings (Ctrl+, or Cmd+,, search for "mcp"):

{
  "github.copilot.chat.mcp.servers": {
    "dotnet": {
      "type": "stdio",
      "command": "dotnet",
      "args": ["run", "--project", "/path/to/dotnet-mcp/DotNetMcp/DotNetMcp.csproj"]
    }
  }
}

📖 Full VS Code MCP documentation

Visual Studio 2022

Requirements: Visual Studio 2022 version 17.13 or later

Using Quick Install (recommended - .NET 10 required):

Click the Visual Studio Install badge at the top of this page
Or manually add via Options:
- Go to Tools > Options > GitHub Copilot > MCP Servers
- Click Add
- Enter:
  - Name: dotnet
  - Type: stdio
  - Command: dnx
  - Arguments: Community.Mcp.DotNet@0.1.0-* --yes

Manual Configuration (for .NET 9 or source builds):

Go to Tools > Options > GitHub Copilot > MCP Servers
Click Add
Enter:
- Name: dotnet
- Type: stdio
- Command: dotnet
- Arguments: run --project C:\path\to\dotnet-mcp\DotNetMcp\DotNetMcp.csproj

📖 Full Visual Studio MCP documentation

Claude Desktop

Using DNX (recommended - .NET 10 required):

macOS: Edit ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "dotnet": {
      "command": "dnx",
      "args": ["Community.Mcp.DotNet@1.0.0", "--yes"]
    }
  }
}

Windows: Edit %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "dotnet": {
      "command": "dnx",
      "args": ["Community.Mcp.DotNet@1.0.0", "--yes"]
    }
  }
}

Manual Configuration (for .NET 9 or source builds):

macOS:

{
  "mcpServers": {
    "dotnet": {
      "command": "dotnet",
      "args": ["run", "--project", "/path/to/dotnet-mcp/DotNetMcp/DotNetMcp.csproj"]
    }
  }
}

Windows:

{
  "mcpServers": {
    "dotnet": {
      "command": "dotnet",
      "args": ["run", "--project", "C:\\path\\to\\dotnet-mcp\\DotNetMcp\\DotNetMcp.csproj"]
    }
  }
}

Usage Examples

Once configured, you can use natural language with your AI assistant:

Quick Start - Single Project

User: "Create a new web API project called WeatherService"

AI: I'll create a new web API project for you...

dotnet new webapi -n WeatherService

The project has been created successfully in the WeatherService directory.

Complex Application - Microservices with Aspire

User: "Create a server-side web app and minimal API, orchestrated by .NET Aspire, with unit tests for the API using xunit. Use slnx format for the solution."

AI: I'll create a complete microservices solution with .NET Aspire orchestration...

# Create solution with new XML format
dotnet new sln -n MyMicroservices --use-slnx

# Create .NET Aspire AppHost for orchestration
dotnet new aspire-apphost -n MyMicroservices.AppHost

# Create web app
dotnet new webapp -n MyMicroservices.Web

# Create minimal API
dotnet new webapi -n MyMicroservices.Api --use-minimal-apis

# Create test project
dotnet new xunit -n MyMicroservices.Api.Tests

# Add projects to solution
dotnet sln add MyMicroservices.AppHost/MyMicroservices.AppHost.csproj
dotnet sln add MyMicroservices.Web/MyMicroservices.Web.csproj
dotnet sln add MyMicroservices.Api/MyMicroservices.Api.csproj
dotnet sln add MyMicroservices.Api.Tests/MyMicroservices.Api.Tests.csproj

# Add project references for tests
dotnet add MyMicroservices.Api.Tests/MyMicroservices.Api.Tests.csproj reference MyMicroservices.Api/MyMicroservices.Api.csproj

Solution created with 4 projects: AppHost for orchestration, Web app, API, and unit tests. Ready to run with dotnet run --project MyMicroservices.AppHost.

Database-Driven Application

User: "Add Entity Framework Core with SQL Server to my API project, and create a NuGet package for my data models"

AI: I'll add EF Core with SQL Server and configure package creation...

# Add Entity Framework packages
dotnet add package Microsoft.EntityFrameworkCore
dotnet add package Microsoft.EntityFrameworkCore.SqlServer
dotnet add package Microsoft.EntityFrameworkCore.Design

# Create a data models class library
dotnet new classlib -n MyMicroservices.Models

# Configure for NuGet packaging
dotnet pack MyMicroservices.Models/MyMicroservices.Models.csproj -c Release

Entity Framework Core with SQL Server provider added. Created a separate Models project that can be packaged and shared.

Multi-Target Testing Strategy

User: "Add integration tests using NUnit that target both .NET 8 and .NET 9, and configure them to run with code coverage"

AI: I'll set up multi-targeted integration tests with coverage...

# Create NUnit test project
dotnet new nunit -n MyMicroservices.IntegrationTests

# Update project to multi-target (edit .csproj)
# <TargetFrameworks>net8.0;net9.0</TargetFrameworks>

# Add integration test packages
dotnet add MyMicroservices.IntegrationTests package Microsoft.AspNetCore.Mvc.Testing
dotnet add MyMicroservices.IntegrationTests package coverlet.collector

# Run tests with coverage for both frameworks
dotnet test --collect:"XPlat Code Coverage"

Integration test project created with multi-targeting. Tests will run on both .NET 8 and .NET 9 with code coverage enabled.

Exploring and Discovering

User: "What templates are available for creating cloud-native applications?"

AI: Let me search for cloud-native related templates...

dotnet new search aspire
dotnet new search dapr
dotnet new search azure

Found templates:

aspire - .NET Aspire Application
aspire-apphost - .NET Aspire App Host
aspire-servicedefaults - .NET Aspire Service Defaults
dapr - Dapr application templates
Various Azure Functions and Container Apps templates

Each template is designed for cloud-native microservices and distributed applications.

Modernization Workflow

User: "Update all packages to latest versions, format all code to match our editorconfig rules, then build and run tests"

AI: I'll update packages, format code, build, and test...

# Update all packages to latest compatible versions
dotnet package update

# Format all code according to .editorconfig
dotnet format

# Clean and rebuild
dotnet clean
dotnet build -c Release

# Run all tests
dotnet test --logger "console;verbosity=detailed"

All packages updated to latest versions. Code formatted consistently across solution. Build succeeded with 0 warnings. All 156 tests passed.

Available Tools

The server provides comprehensive .NET development capabilities through MCP tools and resources:

MCP Resources (Read-Only Context)

The server exposes read-only resources that provide efficient access to .NET environment metadata:

dotnet://sdk-info - Information about installed .NET SDKs (versions and paths)
dotnet://runtime-info - Information about installed .NET runtimes (versions and types)
dotnet://templates - Complete catalog of installed .NET templates with metadata
dotnet://frameworks - Information about supported .NET frameworks (TFMs) including LTS status

Resources provide structured JSON data and are more efficient than tool calls for frequently accessed read-only information.

Tools - Templates & Frameworks

dotnet_template_list - List all installed .NET templates with metadata
dotnet_template_search - Search for templates by name or description
dotnet_template_info - Get detailed template information and parameters
dotnet_template_clear_cache - Clear template cache to force reload from disk
dotnet_framework_info - Get .NET framework version information and LTS status

Tools - Project Management

dotnet_project_new - Create new .NET projects from templates
dotnet_project_restore - Restore project dependencies
dotnet_project_build - Build .NET projects
dotnet_project_run - Build and run .NET projects
dotnet_project_test - Run unit tests
dotnet_project_publish - Publish projects for deployment
dotnet_project_clean - Clean build outputs
dotnet_pack_create - Create NuGet packages from projects
dotnet_watch_run - Run with file watching and hot reload
dotnet_watch_test - Run tests with auto-restart on file changes
dotnet_watch_build - Build with auto-rebuild on file changes

Tools - Package Management

dotnet_package_add - Add NuGet package references
dotnet_package_remove - Remove NuGet package references
dotnet_package_search - Search for NuGet packages on nuget.org
dotnet_package_update - Update NuGet packages to newer versions
dotnet_package_list - List package references (including outdated/deprecated)
dotnet_reference_add - Add project-to-project references
dotnet_reference_remove - Remove project-to-project references
dotnet_reference_list - List project references

Tools - Solution Management

dotnet_solution_create - Create new solution files (.sln or .slnx format)
dotnet_solution_add - Add projects to a solution
dotnet_solution_list - List projects in a solution
dotnet_solution_remove - Remove projects from a solution

Tools - Code Quality

dotnet_format - Format code according to .editorconfig and style rules

Tools - Utilities

dotnet_nuget_locals - Manage NuGet local caches (list, clear)

Tools - SDK Information

dotnet_sdk_version - Get .NET SDK version
dotnet_sdk_info - Get detailed SDK and runtime information
dotnet_sdk_list - List installed SDKs
dotnet_runtime_list - List installed runtimes

Tools - Help

dotnet_help - Get help for any dotnet command

Building from Source

For development or contributing:

git clone https://github.com/jongalloway/dotnet-mcp.git
cd dotnet-mcp/DotNetMcp
dotnet build

Run the server:

dotnet run

The server communicates via stdio transport and is designed to be invoked by MCP clients.

Project Structure

dotnet-mcp/
├── DotNetMcp/                      # Main MCP server project
│   ├── DotNetMcp.csproj            # Project file with NuGet dependencies
│   ├── Program.cs                  # MCP server setup and hosting
│   ├── DotNetCliTools.cs           # MCP tool implementations (44 tools)
│   ├── DotNetResources.cs          # MCP resource implementations (SDK, runtime, templates, frameworks)
│   ├── DotNetCommandExecutor.cs    # Command execution helper with logging
│   ├── DotNetSdkConstants.cs       # Strongly-typed SDK constants (TFMs, configurations, runtimes)
│   ├── TemplateEngineHelper.cs     # Template Engine integration with caching
│   └── FrameworkHelper.cs          # Framework validation and metadata helpers
├── DotNetMcp.Tests/                # Unit test project
│   ├── DotNetMcp.Tests.csproj      # Test project file (xUnit, FluentAssertions, Moq)
│   ├── FrameworkHelperTests.cs     # Tests for framework validation and metadata
│   └── DotNetSdkConstantsTests.cs  # Tests for SDK constants validation
├── doc/
│   └── sdk-integration.md          # SDK integration architecture documentation
├── .github/
│   ├── copilot-instructions.md     # Development guidelines for GitHub Copilot
│   ├── dependabot.yml              # Automated dependency updates
│   └── workflows/
│       └── build.yml               # CI/CD build and test workflow
├── DotNetMcp.slnx                  # Solution file (XML-based .slnx format)
├── LICENSE                         # MIT License
└── README.md                       # This file

Technology Stack

Protocol: Model Context Protocol (MCP)
SDK: MCP SDK for .NET v0.4.0-preview.2
Runtime: .NET 9.0 (target framework)
Transport: stdio (standard input/output)
NuGet Packages:
- Microsoft.TemplateEngine.Abstractions & Edge - Template metadata
- Microsoft.Build.Utilities.Core & Microsoft.Build - Project validation

Documentation

📖 SDK Integration Details - Technical architecture and SDK usage
📖 Advanced Topics - Performance, logging, and security details
📖 Model Context Protocol - Official MCP specification
📖 MCP C# SDK Docs - SDK documentation

Contributing

Contributions are welcome! This is a community-maintained project.

Ways to contribute:

🐛 Report bugs or request features via GitHub Issues
💡 Submit pull requests for new tools or improvements
📝 Improve documentation
⭐ Star the repo to show support

Development setup:

Fork the repository
Clone your fork
Create a feature branch
Make your changes
Test thoroughly
Submit a pull request

See .github/copilot-instructions.md for development guidelines.

Troubleshooting

"dnx not found"

Cause: .NET 10 SDK not installed
Solution: Install .NET 10 SDK or use manual configuration with dotnet run

"No templates found"

Cause: .NET SDK templates not installed
Solution: Run dotnet new --install to install default templates

"Server not responding"

Cause: Server crashed or failed to start
Solution: Check logs in your MCP client, ensure .NET SDK is in PATH

Need Help?

📖 Check the documentation
💬 Open a GitHub Issue
🔍 Search existing issues

License

MIT License - see LICENSE file for details.

Product	Compatible and additional computed target framework versions.
.NET	net9.0 is compatible. net9.0-android was computed. net9.0-browser was computed. net9.0-ios was computed. net9.0-maccatalyst was computed. net9.0-macos was computed. net9.0-tvos was computed. net9.0-windows was computed. net10.0 was computed. net10.0-android was computed. net10.0-browser was computed. net10.0-ios was computed. net10.0-maccatalyst was computed. net10.0-macos was computed. net10.0-tvos was computed. net10.0-windows was computed.

Product

.NET

Compatible target framework(s)

Included target framework(s) (in package)

Learn more about Target Frameworks and .NET Standard.

This package has no dependencies.

Version	Downloads	Last Updated
0.1.0-beta.2.1	58	10/25/2025
0.1.0-beta.2	47	10/25/2025
0.1.0-beta.1.5	48	10/25/2025
0.1.0-beta.1	55	10/24/2025
0.1.0-alpha.10	117	10/21/2025

Community.Mcp.DotNet 0.1.0-beta.2.1

.NET MCP Server

Quick Install

What is This?

Why Use It?

🚀 Faster Development

🧠 Smarter AI Assistance

🎯 Why Not Just Let the AI Call dotnet Directly?

1. Template Discovery & Validation

2. Framework Intelligence

3. Rich Tool Descriptions

4. Parameter Information

5. Package Search Integration

6. Structured Error Handling

7. MCP Resources

✨ Consistent Results

🔒 Secure by Design

How It Works

Installation

Requirements

Option 1: Quick Install (Recommended)

Option 2: Manual Configuration

Visual Studio Code

Visual Studio 2022

Claude Desktop

Usage Examples

Quick Start - Single Project

Complex Application - Microservices with Aspire

Database-Driven Application

Multi-Target Testing Strategy

Exploring and Discovering

Modernization Workflow

Available Tools

MCP Resources (Read-Only Context)

Tools - Templates & Frameworks

Tools - Project Management

Tools - Package Management

Tools - Solution Management

Tools - Code Quality

Tools - Utilities

Tools - SDK Information

Tools - Help

Building from Source

Project Structure

Technology Stack

Documentation

Contributing

Troubleshooting

"dnx not found"

"No templates found"

"Server not responding"

Need Help?

License

🎯 Why Not Just Let the AI Call `dotnet` Directly?