FRENES

Developer tools · MCP server

Open code review: MCP server, setup and security

Open code review is an MCP server published on GitHub that lets an AI agent detect hallucinated dependencies and other defects in AI-generated code. Its repository has 40 stars and its last commit is from April 16, 2026, but it declares no licence.

Last commit 6 months agoNo licence

What Open code review does

According to its repository: “Code quality gate for AI-generated code, detecting hallucinated packages, phantom dependencies, stale APIs and AI-specific defects.”

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. Open code review is listed under Developer tools, a category of 475 servers in the directory, where it ranks #276 by stars.

Topics declared by the repository: ai-generated-code, ci-cd, code-quality, code-review, github-actions, hallucination-detection.

Installing and connecting Open code review

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 Open code review:

  • 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 March 4, 2026, the raye-deng/open-code-review repository has 40 stars and 4 forks, with 2 open issues. It has more stars than 49% of the servers in the directory. Last change 6 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.

StorybookStorybook : 91.4K91.4KFront End ChecklistFront End Checklist : 74.6K74.6KTldrawTldraw : 51.1K51.1KCodebase MemoryCodebase Memory : 47.4K47.4KCCXTCCXT : 44.5K44.5KPostHog MCP ServerPostHog MCP Server : 40.4K40.4KClaude task masterClaude task master : 28.3K28.3KAgent Skills Search ServerAgent Skills Search Server : 26.6K26.6KOpen code reviewOpen code review : 4040
GitHub stars of the most followed servers in the category (log scale); Open code review in orange. Checked October 25, 2026.

Verdict

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

Limitations

  • No commit for 6 months
  • No licence declared
  • Install from source

Avoid if…

  • Company use without the author's agreement

Frequently asked questions

How do I install Open code review?

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

Is Open code review free?

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

Is Open code review 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 raye-deng on GitHub. Check who maintains it before giving it access.

What are the alternatives to Open code review?

In the same category: Radar Kubernetes MCP Server, Repowise, Jscpd, and Apify MCP server. Radar Kubernetes MCP Server and Repowise 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