RoselineMCP

Expose Roslyn code analysis as an MCP server so AI assistants can analyze and fix C# quality issues directly.

Table of Contents

• The Problem
• The Solution
• Features
• Tech Stack
• Getting Started
• Available Tools
• Architecture
• Project Structure
• Roadmap
• Contributing
• License
• Acknowledgments

The Problem

C# codebases accumulate quality issues silently -- inconsistent naming, missing nullable annotations, unused usings, suboptimal patterns. Manual code reviews catch some, but Roslyn analyzers can catch them all automatically. The problem: setting up and running analyzers across large codebases is tedious, and the results are not easily actionable from an AI assistant workflow.

The Solution

RoselineMCP exposes Roslyn analysis as an MCP server so AI assistants can analyze and fix C# code quality issues directly. Connect it to Claude Desktop or any MCP-compatible client and get comprehensive diagnostics, automated fixes, and reviewable patches -- all without leaving your AI workflow.

// In your Claude Desktop config, just add:
{
  "mcpServers": {
    "roseline": {
      "command": "roseline-mcp"
    }
  }
}
// Then ask Claude: "Analyze my solution at /path/to/MySolution.sln"

Features

• Comprehensive Code Analysis -- Analyze entire C# solutions for code quality issues, potential bugs, and style violations
• Automated Code Fixes -- Apply automated fixes for hundreds of diagnostic rules from Roslyn and Roslynator
• Unified Diff Generation -- Generate reviewable patches before applying changes
• Flexible Filtering -- Filter diagnostics by severity, ID, file patterns, and project names
• Safe Operations -- All operations use temporary workspaces to prevent accidental modifications
• MCP Protocol Support -- Full integration with the Model Context Protocol for AI assistant usage
• Docker Support -- Run without any SDK installation via Docker
• NuGet Global Tool -- Install with a single dotnet tool install command

Tech Stack

Getting Started

Prerequisites

• NuGet global tool: .NET 10.0 SDK or later
• Docker: Docker Desktop or Docker Engine
• Build from source: .NET 10.0 SDK + MSBuild (included with Visual Studio or .NET SDK)
• MCP client: Claude Desktop or any MCP-compatible client

Installation

Option 1 -- NuGet Global Tool (recommended)

Requires .NET 10.0 SDK or later.

dotnet tool install -g RoselineMCP

After installation, the roseline-mcp command is available globally.

Claude Desktop configuration (NuGet global tool)

Add to your Claude Desktop configuration file (claude_desktop_config.json):

{
  "mcpServers": {
    "roseline": {
      "command": "roseline-mcp"
    }
  }
}

Config file location:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json

Option 2 -- Docker

No SDK required. Works on any platform with Docker installed.

docker run -i --rm phmatray/roseline-mcp:latest

Claude Desktop configuration (Docker)

{
  "mcpServers": {
    "roseline": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "phmatray/roseline-mcp:latest"
      ]
    }
  }
}

Note: The -i flag is required for stdio transport. The --rm flag removes the container after the session ends.

Option 3 -- Build from Source

git clone https://github.com/Atypical-Consulting/RoselineMCP.git
cd RoselineMCP
dotnet build
dotnet test

Claude Desktop configuration (build from source)

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

Available Tools

1. AnalyzeSolution

Analyzes an entire C# solution for diagnostics.

analyzeSolution({
  pathOrGit: "/path/to/solution.sln",
  includePattern: "*.Core",     // Optional: Include only matching projects
  excludePattern: "*.Tests",    // Optional: Exclude matching projects
  severity: "warning",           // Optional: Minimum severity (error|warning|info)
  maxDiagnostics: 100           // Optional: Maximum diagnostics to return
})

2. ListDiagnostics

Gets detailed diagnostics for a specific project.

listDiagnostics({
  project: "MyProject.csproj",
  ids: ["CS0168", "CS0219"],    // Optional: Filter by diagnostic IDs
  files: ["**/Controllers/*"],   // Optional: Filter by file patterns
  max: 50                        // Optional: Maximum results
})

3. ApplyFixes

Applies automated code fixes for specified diagnostics.

applyFixes({
  project: "MyProject.csproj",
  ids: ["CS0168", "RCS1001"],   // Diagnostic IDs to fix
  previewOnly: true              // Optional: Generate patch without applying
})

4. CreatePatch

Generates a unified diff between two text versions.

createPatch({
  before: "original code",
  after: "modified code",
  fileName: "Example.cs"         // Optional: For display in diff
})

Supported Analyzers

RoselineMCP includes support for:

• Roslyn Analyzers -- Built-in C# compiler diagnostics
• Roslynator -- 500+ analyzers, refactorings, and fixes for C#
• StyleCop Analyzers -- Code style and consistency rules
• Custom Analyzers -- Any Roslyn-based analyzer in your solution

Examples

Analyzing a Solution

# Using with an MCP client
mcp call analyzeSolution '{
  "pathOrGit": "/Users/dev/MyProject/MyProject.sln",
  "severity": "warning",
  "maxDiagnostics": 50
}'

Response:

{
  "solution": "MyProject.sln",
  "projects": 5,
  "diagnosticSummary": {
    "error": 2,
    "warning": 15,
    "info": 28
  },
  "topDiagnostics": [
    {
      "id": "CS0168",
      "severity": "warning",
      "message": "The variable 'ex' is declared but never used",
      "file": "Program.cs",
      "line": 42
    }
  ]
}

Applying Fixes

mcp call applyFixes '{
  "project": "MyProject.Core.csproj",
  "ids": ["CS0168", "RCS1001"],
  "previewOnly": true
}'

Response includes a unified diff patch showing all changes that would be applied.

Configuration

Environment Variables

• ROSELINE_LOG_LEVEL: Set logging level (Debug, Information, Warning, Error)
• ASPNETCORE_ENVIRONMENT: Set environment (Development, Production)

appsettings.json

Configure logging and other settings:

{
  "Logging": {
    "LogLevel": {
      "Default": "Information",
      "RoselineMCP": "Debug"
    }
  }
}

Architecture

RoselineMCP uses stdio transport — this is an intentional design decision. The server runs as a local process launched by the MCP client (Claude Desktop, AI agents), communicates over stdin/stdout, and exits when the client disconnects. This makes it perfectly suited for distribution as a NuGet global tool (dotnet tool install -g RoselineMCP) or Docker image — no port binding, no HTTP server, no infrastructure to manage.