Skip to main content
Glama
README.md
# Statelessor MCP Server

MCP (Model Context Protocol) server for analyzing .NET and Java projects for stateful code patterns. Integrates with Amazon Q Developer.

## Installation

```bash
npm install -g statelessor-mcp
```

## Quick Start

### 1. Configure Amazon Q

Create or edit `~/.aws/amazonq/mcp-config.json`:

```json
{
  "mcpServers": {
    "statelessor": {
      "command": "npx",
      "args": ["statelessor-mcp"],
      "env": {
        "STATELESSOR_API_URL": "https://statelessor-api.port2aws.pro"
      }
    }
  }
}
```

### 2. Restart Amazon Q in your IDE

### 3. Use in Amazon Q Chat

```
You: Analyze my local project at /path/to/my-dotnet-app

You: Analyze https://github.com/myorg/java-project

You: Explain how to fix Session State issues

You: Generate a bash script for analyzing .NET projects
```

## Available Tools

- **analyze_git_repository** - Analyze Git repos for stateful patterns
- **analyze_local_project** - Analyze local project directories
- **generate_analysis_script** - Generate bash/PowerShell scripts
- **get_project_findings** - Retrieve historical findings
- **explain_remediation** - Get remediation guidance

## Configuration

Environment variables:

- `STATELESSOR_API_URL` - API endpoint (default: http://localhost:3001)
- `STATELESSOR_API_TIMEOUT` - Request timeout in ms (default: 300000)

## Additional details

Read USER_GUIDE.md for more details
Read INTEGRATION.md as well for additional information

## License

MIT

TDQS

A3.5/5.0

Scored across 5 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: analyze_git_repository and analyze_local_project target different source locations, explain_remediation provides guidance, generate_analysis_script creates scripts, and get_project_findings retrieves historical data. No overlap or ambiguity exists between these functions.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern with snake_case naming (e.g., analyze_git_repository, explain_remediation, generate_analysis_script). The naming is predictable and readable throughout the set.

Tool Count5/5

With 5 tools, the server is well-scoped for analyzing stateful code patterns. Each tool serves a unique and necessary function in the workflow, from analysis to remediation and historical retrieval, without being too sparse or bloated.

Completeness4/5

The toolset covers core analysis workflows (git/local analysis, remediation guidance, script generation, and findings retrieval). A minor gap exists in direct remediation actions (e.g., fixing patterns automatically), but agents can work around this using the provided guidance and scripts.