tech-debt-master
A CLI tool that automates technical debt discovery, triage, and resolution. `tdm` transforms technical debt management into a proactive, automated process that works seamlessly with your existing development tools through MCP integration.
claude mcp add --transport stdio nikiforovall-tech-debt-master dotnet run --project src/TechDebtMaster.Cli -- index <repository-path> \ --env REPOMIX_PATH="path to repomix if not in PATH" \ --env TELEMETRY_ENABLED="true/false (optional)" \ --env AZURE_OPENAI_API_KEY="Azure OpenAI API key (if required by your setup)"
How to use
TechDebtMaster is a command-line tool that analyzes software repositories to identify and manage technical debt using AI-powered analysis through Microsoft Semantic Kernel and integration with repomix. The CLI exposes commands to index a repository (extracting file summaries and structure) and analyze the repository to surface potential debt areas. Use the index command to prepare data from a local or remote repository, then run analyze to get AI-generated insights and actionable recommendations. The tool leverages Spectre.Console for a polished CLI experience and supports dependency injection for modular extensibility. To run, use the .NET CLI as demonstrated in the installation and usage sections, and invoke subcommands like index and analyze against the target repository path.
How to install
Prerequisites:
- .NET 9.0 SDK
- repomix installed and available in PATH
- Azure OpenAI API access (via EPAM AI Proxy or direct Azure OpenAI)
Installation steps:
- Install or clone the repository containing TechDebtMaster.Cli.
- Build and install the CLI tool:
dotnet cake --target pack
dotnet tool install --global --add-source ./Artefacts TechDebtMaster.Cli --prerelease
- Verify installation by listing the tool or running a help command:
TechDebtMaster.Cli --help
If you prefer to run directly from source without packaging:
# Navigate to repository and run from source (example)
dotnet run --project src/TechDebtMaster.Cli -- --help
Additional notes
Tips and notes:
- Ensure repomix is installed and available in your PATH since TechDebtMaster relies on it for repository indexing.
- The AI analysis requires access to Azure OpenAI (or EPAM AI Proxy) and may incur costs depending on usage.
- If running from source, you can pass a repository path to the index command to index local repos or remote paths as supported by your environment.
- Environment variables can be used to customize API keys and paths; adjust AZURE_OPENAI_API_KEY and REPOMIX_PATH as needed.
- The CLI is designed to be extended; if you add new analysis modules, consider updating the DI container and command surface accordingly.
Related MCP Servers
ai-trader
Backtrader-powered backtesting framework for algorithmic trading, featuring 20+ strategies, multi-market support, CLI tools, and an integrated MCP server for professional traders.
sonarqube
SonarQube MCP Server
skillz
An MCP server for loading skills (shim for non-claude clients).
agentql
Model Context Protocol server that integrates AgentQL's data extraction capabilities.
mcp -js
MCP server that exposes YepCode processes as callable tools for AI platforms. Securely connect AI assistants to your YepCode workflows, APIs, and automations.
zerodha
Zerodha MCP Server & Client - AI Agent (w/Agno & w/Google ADK)