CodeHealth MCP Server ensures agents and AI coding assistants write maintainable, production-ready code without introducing technical debt. Using deterministic CodeHealth feedback, it guides agents to spot risks, improve unhealthy code, and refactor toward clear quality targets. Run it locally and keep full control of your workflow while making legacy systems more AI-ready. The result is more reliable AI-generated code, safer refactoring, and greater trust in real engineering workflows.
DiffSense
Cool! is it like SonarQube but as an MCP?
CodeHealth MCP Server by CodeScene
@conduit_design It's CodeScene analysis tools as an MCP, which works in the same space as SonarQube. It can help you do code health reviews, uplifting of unhealthy code and safeguarding AI generated code. Is there a specific use case you're interested in?
CodeHealth MCP Server by CodeScene
@conduit_design Thanks and lot, André!
CodeScene's MCP is based on the Code Health metric. It's the only validated code-level metric with a proven impact in terms of faster (shorter lead times) and better (fewer defects).
Compared to linting aggregators like SonarQube, Code Health works at a higher level. Think of linters like the line-by-line commenting whereas Code Health checks the design and structure of the code to guide agents.
Does that help explaining the difference?
DiffSense
@adam_tornhill_cs SonarQube is not a linter. its a: static code analysis platform that scans source code across 35+ languages to detect bugs, vulnerabilities, code smells, duplication, coverage gaps, and technical debt. My question is. How is code health metric different? Im very into this right now, so im genuinly interested in finding out. Thanks.
CodeHealth MCP Server by CodeScene
@adam_tornhill_cs @conduit_design We have a very in-depth explanation of our CodeHealth metric available here: https://codescene.io/docs/guides/technical/code-health.html#code-health-identifies-factors-known-to-impact-maintenance-costs-and-delivery-risks. There's a lot of overlap between what CodeScene does and what SonarQube does, but our analysis is validated by academic research, viewable here: https://codescene.com/hubfs/web_docs/Business-impact-of-code-quality.pdf. We've also written more about how we fair against SonarQube here: https://codescene.com/blog/6x-improvement-over-sonarqube.
Does this clear up the similarities and differences between the two?
DiffSense
@adam_tornhill_cs @askonmm That article doesnt read well. It bashes sonarqube. the industry standard without proof. It does not go into details on how codeScene is better. what particular thing makes it better? Like show benchmarks. Show examples. For instance do a case study on a popular code repo, and do head to head compare with SonarQube. Im all for trying something better than SonarQube, but prove it. Dont just say it. you know what I mean? Proof is in the pudding as they say. Also some more details into how CodeScene does things. Is it all AI? or is there heuristics, or is there some exotic engines that run this. If its AI, then its only as good as the guardrails it uses. Some insight into these things would be great and bring a lot of credability and lower friction to adoption. Full disclosure. I run SonarCube on local runners with lots of customizations added on top, and its fantastic. Also big fan of Codebeat.io but they kinda dropped of a while ago. Anyways. great space! this is the new battlefield. when AI writes all our code, the output is only as good as whatever keeps it in line. # my 2 cents
Congrats on the launch, Adam. Japan-based founder here, using Claude/Codex heavily.
One Japan-specific thought: this may be especially relevant here because many Japanese teams work in legacy-heavy, review-heavy environments: mixed JP/EN identifiers, Japanese comments/docs, internal conventions, long-lived modules, and approval flows where senior engineers become bottlenecks.
The strongest local angle I’d test first is not just “AI can increase technical debt,” but “give conservative Japanese teams a deterministic quality gate so Claude/Cursor-generated changes can enter review without quietly increasing maintenance risk.”
That could land well for enterprise teams and SIer-style dev environments where speed is attractive, but uncontrolled AI changes are politically and technically hard to trust.
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!
CodeHealth MCP Server by CodeScene
@tajib_smajlovic Thank you so much for your support, our team appreciates it a lot. How reliable has AI-generated code been for you in production so far?
@romanela_p It’s quite reliable in production after a thorough review, but I still think AI-generated code needs the right tooling around it. AI-generated code tends to work well in cleaner parts of the codebase, but in more complex or legacy areas it can introduce issues that are easy to miss. That’s where CodeScene has been helpful for me, by tracking code health and helping catch problems early.
CodeHealth MCP Server by CodeScene
@tajib_smajlovic Hi Tajib, that's really good insighs and also what we've seen from our research. When agents operate on unhealthy code, the defect risk increases by at least 60%. What we also saw that, based on the patterns, the relationship is not linear. Our study included only "problematic" code, on our Code Health scale rating ≥ 7.0.
The research never touched the truly unhealthy code found in many legacy codebases, modules scoring 4, 3, or even 1. In very unhealthy code, breakage may become the default behaviour.
This is the risk we removed with the CodeHealth MCP when enabled in the AI workflow, since the MCP is deterministic and auto-reviews the generated code continuously, flagging any potential code health issues. The agent is then "forced" in to a refactoring loop until all the issues are resolved and the generated code is healthy enough. So the MCP guides the agent to ensure that the code is healthy, free from technical debt and ready for production.
CodeHealth MCP Server by CodeScene
@tajib_smajlovic I'm glad you like the product!
CodeHealth MCP Server by CodeScene
@tajib_smajlovic Great to hear Tajib! Looking forward to hearing your thoughts on the MCP 🙏
CodeHealth MCP Server by CodeScene
@tajib_smajlovic Thanks for the feedback Tajib!
CodeHealth MCP Server by CodeScene
Thank you@tajib_smajlovic !
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.
CodeHealth MCP Server by CodeScene
@mrksbrg Indeed! I'm excited for how far we can take this, and what other tools we could create to further improve software quality.
CodeHealth MCP Server by CodeScene
Insightful! @mrksbrg
CodeHealth MCP Server by CodeScene
@mrksbrg That's good news and I'm glad to hear that it's picked up as an important theme :)
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!
CodeHealth MCP Server by CodeScene
@freyawi We're glad you like it! If you have any feedback on how we could improve things further, we're all ears.
CodeHealth MCP Server by CodeScene
@freyawi Great to hear Freya 🙂
CodeHealth MCP Server by CodeScene
Thank you@freyawi I'm glad to hear!
CodeHealth MCP Server by CodeScene
@freyawi Thanks a lot, Freya! Happy to hear that.
CodeHealth MCP Server by CodeScene
I'm curious how you are actually handling this in practice, what does your workflow look like for reviewing or validating AI-generated code before it hits production?
CodeHealth MCP Server by CodeScene
@stefan_persson1 Everybody has a different development flow, of course, but I personally use it something like this: I create an initial prompt to the AI to work on some task. I've instructed it via `AGENTS.md` to always run code health review after every change, and if it has degraded, fix it on its own. This allows me to focus on the task and not the code quality, which the CodeHealth MCP takes care of. Once I'm done with my task I run the `analyze_change_set` tool to make sure that my feature branch doesn't have any degradation's compared to the master branch, and if there are, I will ask AI to fix those issues using CodeHealth MCP guidance.
This makes sure that the code itself is of perfect quality, but of course it can't understand architectural choices, so the very last review is still made by me - a human - to verify that everything looks good. I can focus on architectural analysis, and no longer have to focus on tedious code health parts, which is very liberating.
Asa.team
This is the right problem to be solving right now. Vibe coding is shipping a lot of code that works but that nobody will be able to maintain in 6 months.
The MCP angle is smart, putting code health signals directly in the context window where the agent can actually act on them rather than as a separate dashboard nobody checks. Does it surface refactor suggestions inline or just flag issues?
CodeHealth MCP Server by CodeScene
@ng_junsheng It flags issues, but with accurate solutions to those issues so the AI has no problem acting on the feedback without needing concrete code examples given to it.