FRENES

Data science and visualization · MCP server

Code guardian: MCP server, setup and security

Code guardian is an MCP server published on GitHub that lets an AI agent analyze code complexity and generate automated refactoring plans for hotspots. Its repository has 9 stars and its last commit is from December 25, 2025, but it declares no licence.

Last commit 10 months agoNo licence

What Code guardian does

According to its repository: “Code refactoring engine: code analysis, hotspot detection, complexity metrics, persistent memory and automated refactoring plans.”

The Model Context Protocol (MCP) is a standard plug between an AI agent and an outside service: once the server is connected, its tools show up in the agent, which decides when to call them. Code guardian is listed under Data science and visualization, a category of 48 servers in the directory, where it ranks #40 by stars.

Topics declared by the repository: ai-tools, claude-code, code-quality, code-refactoring, technical-debt.

Installing and connecting Code guardian

No package or remote server is declared in the official MCP registry: you install it from source, following the repository README.

It works with any MCP-compatible client (Claude Desktop, Claude Code, Cursor, VS Code, Codex and most recent agents). You add one entry to the client's MCP configuration: server name, start command or URL, environment variables. Project language: TypeScript.

Security: what to check

Connecting an MCP server means installing software that talks straight to your agent: it runs with your rights and the model trusts its tool descriptions. The risk therefore depends on what it can touch and how far its code can be trusted.

Points found for Code guardian:

  • No licence: without a licence the code is not legally reusable, even if it is public. Avoid it in a company setting without the author's agreement.

Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.

Project activity and maintenance

Created on December 4, 2025, the phuongrealmax/code-guardian repository has 9 stars and 3 forks, with 0 open issues. It has more stars than 24% of the servers in the directory. Last change 10 months ago.

Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.

Agent Native AnalyticsAgent Native Analytics : 7.5K7.5KGoogle Ads + Meta Ads + SEO/Google Ads + Meta Ads + SEO/ : 5.9K5.9KAsk JevAsk Jev : 5.2K5.2KVizro MCPVizro MCP : 3.8K3.8KShipSwiftShipSwift : 3.2K3.2KMarkdownify MCPMarkdownify MCP : 3K3KSemioticSemiotic : 2.7K2.7KPaperBananaPaperBanana : 2.4K2.4KCode guardianCode guardian : 99
GitHub stars of the most followed servers in the category (log scale); Code guardian in orange. Checked October 25, 2026.

Verdict

Code guardian is still a modest project: read its code and compare it with the alternatives before using it.

Limitations

  • No commit for 10 months
  • No licence declared
  • Few visible users
  • Install from source

Avoid if…

  • Company use without the author's agreement

Frequently asked questions

How do I install Code guardian?

No package is declared in the MCP registry: clone the phuongrealmax/code-guardian repository, follow its README, then declare the start command in your client's MCP configuration.

Is Code guardian free?

The code is public but has no declared licence: it is not formally free to reuse.

Is Code guardian safe?

Points to watch: no licence. Give it minimum rights and approve sensitive actions.

Is it an official server?

Nothing says so: it is a project published by phuongrealmax on GitHub. Check who maintains it before giving it access.

What are the alternatives to Code guardian?

In the same category: Vizro MCP, Agent Native Analytics, Semiotic, and Google Ads + Meta Ads + SEO/GEO MCP. Vizro MCP and Agent Native Analytics score higher on our grid.

Related articles

Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score