CodeHealth MCP Server by CodeScene

Keep AI-generated code healthy and maintainable

Developer Tools

Artificial Intelligence

Vibe coding

Visit WebsiteSee on Product HuntGithub ⧉Twitter ⧉

Very timely launch. A major theme at ICSE 2026 (https://conf.researchr.org/home/icse-2026) was how to add guardrails in agentic workflows. This MCP server is a meaningful step toward making structural code quality a commodity.

I’ve tried it out and was quite happy with how easy it is to use. The installation was quick and the whole setup fells intuitive!

Healthy systems at AI speed that’s a powerful phrase. What’s one practical step teams can take today to move closer to that goal? Clean and nice logo as well. Congratulations!

One thing we found in our research is that AI tends to struggle the most in already complex, low CodeHealth codebases, it doesn’t just generate code, it amplifies existing issues.

We found that there's a 60% higher defect risk when applying AI coding tools to unhealthy Code. Here is a link to our whitepaper that is based on the research paper linked above.

Curious, how are you validating code quality when using AI tools today?

This is clearly needed. Agents are capable of writing excellent code, but left alone they choose not to.

I try to find ways to micromanage quality less and this is the best I’ve seen so far.

Been a CodeScene user for a while, so when the CodeHealth MCP Server dropped I jumped on it immediately and it's been a great addition to my workflow.

As someone who leans heavily into vibe-coding, having real-time CodeHealth feedback baked directly into my AI coding assistant is a game changer. It catches the kind of subtle technical debt that accumulates fast when you're moving quickly and letting the AI do the heavy lifting. Instead of ending up with a pile of "works but nobody should touch this" code, I actually ship things I'm not embarrassed by later.

If you're already a CodeScene user, this is a no-brainer. And if you're new to it this is a great entry point. The deterministic health scoring gives you something concrete to improve toward, which is way more actionable than vague AI suggestions.

A lot of developers have a negative view of AI assisted or generated code, because they tried it out at one point and it created what would be best described as low quality slop, making the job of the developer one of a glorified AI slop cleanup specialist. Nobody likes doing that, so they stopped using AI or formed a very negative view of it. I've been there myself, too.

With the CodeHealth MCP though, you can have a deterministic feedback loop for AI which makes AI self-correct the slop it creates, allowing you to think holistically about your task at hand without having to deal with cleaning up bad AI generated code.

I consider myself a fairly decent software engineer, but not only can the CodeHealth MCP remove the slop cleaning part of my agentic workflow, it also allows me to create better code than I did before, and I think my code pre-AI was already fairly decent, so that's saying something. I truly cannot envision doing agentic programming without CodeHealth MCP anymore. It's either that or I'd much rather write code without AI again.

Do you have similar experiences?

When we developed the CodeHealth MCP we benchmarked raw Claude Code refactoring against MCP-guided refactoring. The result: 2-5x improvement in how many code smells Claude Code could solve. And the type of work changed too, from more low level improvements like renames of variables to guided restructuring of the code.

Agents aren't lazy, they're just flying blind and have no incentive to do better.
Read the full thing here: https://codescene.com/blog/making-legacy-code-ai-ready-benchmarks-on-agentic-refactoring

Hi PH! I'm Adna, Developer Advocate at CodeScene.

I tested Claude, Copilot, and Cursor on the same legacy file and ended up with the same result: all three passed tests and all three made the code worse - and it happened silently, with no signal telling them they had.

The problem isn't the model. It's that agents have no idea which parts of a codebase are already load-bearing and fragile. They write confidently into broken areas because nothing stops them.

With the MCP Server in the loop: same file, same task, 4.82 → 9.1. Iteratively. The agent verified the delta after each step before moving on. That behavioral shift, knowing where not to be reckless, is what actually changed. Server runs locally, is model-agnostic, and finally, no code leaves your machine.

Happy to answer anything - especially if you've hit this problem yourself: how are you currently catching structural degradation in agent-assisted workflows?

The speed of generating code with Claude Code or Cursor is incredible but the "did I just create six months of tech debt in 20 minutes" anxiety is real. Having an opinionated quality gate that doesn't change its mind based on how you phrase the prompt is exactly what you need when the code itself is generated by a probabilistic system. Does it catch structural issues too, like functions that are doing too many things or classes that have grown beyond a reasonable scope? Those are the kinds of problems that AI agents love to create - technically correct code that's architecturally messy.

Deterministic is doing a lot of work here and in the best way possible. In a world of AI-generated everything, having a non-LLM signal for code quality feels underrated. What does the scoring model actually look at — cyclomatic complexity, coupling, something proprietary?

Been using CodeScene for a while to improve code quality and keep things maintainable. Really excited to try the MCP server and see how it can take this further, especially with AI-assisted workflows. Great work on the launch!

I use AI assisted code a lot now. Actually AI writes most of my code now. One thing has become very clear: AI is great at producing a lot of code. But it amplifies the code quality of what is already in the code base. Bad code gets worse. Good code can stay good, but it is very much the responsibility of the developer to keep it good.

The combination of Codescene extension (free) of the Codescene MCP makes this so much easier. The extension will surface potential problems instantly and show you code smells you probably want to adress. The Codescene MCP allows the coding agent to to be aware of problems and get more details and context on how to fix them.

I love the fact that the agent can end each session with asking codescene mcp for a code review so see where it didn't really cleared the bar, and automatically correct itself.

I also use the MCP server to ask about code that I might think is too complex, or where I sense something is wrong, but can't really put words on it. The MCP is so good at evaluating the code quality and give suggestions for improvements.

The more you work with AI assisted coding, the more important this product becomes. I highly recommend it and it is always the first thing that goes into custom instructions for the AI when I start working on a project.

This hits a nerve. When I was CTO scaling an engineering team from 15 to 120 people, code review was already our biggest bottleneck - senior engineers spending 30-40% of their time reviewing junior code. Now multiply that by AI-generated PRs that look clean on the surface but silently introduce coupling and complexity. The fact that CodeHealth MCP runs deterministic checks locally is the right call - you need something that catches structural issues before they compound, not after three sprints of building on top of them. Curious how the feedback loop works in practice: when an agent gets a CodeHealth warning, does it typically self-correct in one pass or does it tend to need multiple iterations to converge on healthy code?