TechDebtMCP
MCP server for analyzing and managing technical debt in codebases via the Model Context Protocol
claude mcp add --transport stdio pierrejanineh-techdebtmcp npx -y tech-debt-mcp@latest
How to use
Tech Debt MCP is a multi-language MCP server designed to analyze technical debt across projects and provide actionable insights. It supports a wide range of languages (JavaScript, Python, Java, Swift, Kotlin, Objective-C, C/C++, C#, Go, Rust, Ruby, PHP, and more) and exposes a set of tools to scan entire projects, individual files, and to produce high-value metrics such as SQALE ratings. Typical workflows include analyzing a whole repository to surface debt hotspots, filtering results by language or severity, and generating summaries that help prioritize remediation efforts. The server can be integrated with MCP-compatible editors and tools (e.g., GitHub Copilot integrations) to surface debt signals directly in your development workflow. Tools available include analyze_project, analyze_file, get_debt_summary, and get_sqale_metrics, each tailored to provide structured debt signals and recommendations.
How to install
Prerequisites:
- Node.js (v14+ recommended) and npm
- Internet access to fetch the MCP server package
Installation steps:
-
Ensure Node.js and npm are installed. Verify with: node -v npm -v
-
Run the MCP server using npx (no local installation required): npx -y tech-debt-mcp@latest
-
(Optional) If you want to run development mode locally, you can clone the repository and install dependencies, then start in development mode as described in the project README (e.g., npm install followed by npm run dev).
-
To integrate with clients, use the MCP configuration snippet: { "mcpServers": { "tech-debt-mcp": { "command": "npx", "args": ["-y", "tech-debt-mcp@latest"] } } }
Additional notes
Notes and tips:
- The server is published as an npm package named tech-debt-mcp; use npx tech-debt-mcp@latest to run without a local install.
- You can customize analysis by language, severity, and categories using the available tool parameters (e.g., analyze_project with path, languages, severity).
- Ensure the executing environment has access to your project files and any required language tooling that may be needed for static analysis (e.g., language servers, linters).
- For IDE integrations, you can use the provided MCP JSON snippets to point editors at tech-debt-mcp and query results directly from within your editor or workflow.
- If you encounter network or permission errors with npx, ensure npm is configured to access the registry and that your environment permits executing binary scripts.
Related MCP Servers
mcp-gm
wanna develop an app ❓
arbor
Graph-native code intelligence that replaces embedding-based RAG with deterministic program understanding.
archmcp
archmcp - MCP Architectural Snapshot Server and Knowledge Graph
local -gateway
Aggregate multiple MCP servers into a single endpoint with web UI, OAuth 2.1, and profile-based tool management
openapi-to
Transform OpenAPI specifications into production-ready MCP servers with AI-powered evaluation and enhancement. Leverages LLMs to analyze, improve, and generate Model Context Protocol implementations from your existing API documentation.
MCP-Client -Project-using-NodeJS
A minimal Model Context Protocol (MCP) implementation built with Node.js and TypeScript. This project demonstrates client–server communication over stdio, structured message handling, and local data access, developed with VS Code and GitHub Copilot to explore modern AI tool integration workflows.