Best for
- Development teams maintaining medium to large codebases
- Developers wanting to assess code health before refactoring
- Engineering managers needing quantified code risk to plan tech debt cleanup
P
Project Health Auditor
Community
Analyze local repos for code health, complexity, test coverage gaps
- Category
- Dev Tools #432 of 438
- Stars
- ★ 2.8k Very popular
- Transport
- stdio (local process)
- Runtime
- Node.js
- Credentials
- No credential needed
- License
- MIT
- Last commit
21FMRS · D
This server is part of the Claude Code plugin marketplace and provides local code health analysis. Functionality is straightforward, but specific analysis algorithms and tools are not disclosed; actual capabilities need validation.
Strongest · Setup experience 5/20 Weakest · Reliability 3/20
Why each score
- Reliability 3/20
- Only the server.json manifest and a one-line catalog description were supplied; no server source code, tests, or CI evidence exists to verify clean startup, the MCP init/tool-list handshake, or that declared tools match real behavior. Error handling and dependency boundaries are undocumented. Missing evidence is treated as a deduction, so the score is 3.
- Security and permissions 5/20
- The stated purpose is local repository analysis, and no malware, credential theft, or covert exfiltration red-line is visible. However, there is no documentation of least privilege, data boundaries, confirmation for dangerous operations, or external network behavior, so whether data leaves the machine cannot be verified. Permissions and scoping are undisclosed, giving 5.
- Maintenance 5/20
- Repo-level facts show an MIT license and a non-archived repository, and the manifest pins version 1.0.0 with an npm package identifier, indicating at least one published artifact. There is no server-specific evidence of commit history, release notes, dependency updates, or issue responsiveness, and README popularity claims are not treated as evidence. Conservative score: 5.
- Documentation 3/20
- Documentation is limited to a one-line description in the README catalog and the manifest description. There is no install guide, tool parameter reference, authentication notes, limitations, cost disclosure, or troubleshooting section, so users cannot reliably integrate or debug the server. Score: 3.
- Setup experience 5/20
- The manifest declares an npm package over stdio transport, giving a plausible install route, but there is no client configuration example, environment requirements, or verification step, and no executable tests or CI evidence confirm that a connection works after install. Per the static calibration cap, setup is scored 5.
Static review · not runListed 2026-08-07
Read the FMRS scoring method →Fit and risk
What it can accessReads local filesRuns commands or code
Not for
- Scenarios requiring deep security auditing
- Real-time monitoring of production environments
- Analysis of non-local repositories
Required permissions
- Read local repository filesystem
- Analyze code statistics
Risks and side effects
- Potential misclassification of some code patterns as high complexity
- Analysis results depend on local repo state and may become stale
- Analysis of large repositories may be time-consuming
Setup
Before you start
Runtime：Node.js
To install this MCP server:
- Install the CLI globally using npm:
pnpm add -g @intentsolutionsio/ccpi(or use npm). - Run
ccpi install project-health-auditorto install the plugin.
Alternatively, use Claude Code's built-in command: /plugin install project-health-auditor@claude-code-plugins-plus.
Check that it works
Confirm the Project Health Auditor (io.github.jeremylongshore/project-health-auditor) tools appear in your MCP client's tool list, then ask it to run a health analysis on the current directory; a returned analysis proves the stdio server is connected.
Troubleshooting
- Ensure npm package is correctly installed and version matches
- Check that local repository path is correct
- Verify network connectivity if external resources are required
- Inspect MCP server logs to diagnose errors
Things to try
Once connected, you can ask your AI assistant things like:
- Audit this repo for code health and report the most complex files
- Analyze test coverage gaps in the current project
- Scan the local codebase and identify technical debt hot spots
Use cases
Evaluate complexity distribution across a codebase
Identify modules with insufficient test coverage
Locate technical debt hotspots
Supported clients
Claude Desktop
Listed from the project's documentation, not tested by this site.
Overview
Project Health Auditor is an MCP server that analyzes local code repositories for code health, complexity, churn, and test coverage gaps to identify technical debt hotspots. It provides multi-dimensional health analysis to help developers focus on areas needing attention.
Similar servers
Context7
80 · B
Upstash's official server providing up-to-date third-party library docs for AI coding assistants
NPM Sentinel MCP Server
79 · B
AI-powered NPM package analysis MCP server
MartinLoop MCP Server
79 · B
An independent control layer that gives AI coding agents budgets, brakes, and receipts
GitHub MCP Server
76 · B
GitHub's official MCP server for managing repos, issues, PRs, and workflows via natural language
More servers from this repository
Source revision ebea1067983c Data synced 2026-10-12 Read the FMRS scoring method