fix: security vulnerability in server

[Shironex]

• update @modelcontextprotocol/sdk to latest version to adress high security vulnerability

[coderabbitai]

Important

Review skipped

Auto reviews are disabled on base/target branches other than the default branch.

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

---

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

• X
• Mastodon
• Reddit
• LinkedIn

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[gemini-code-assist]

Summary of Changes

Hello @Shironex, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request is crucial for enhancing the server's security posture. It resolves a reported high-severity vulnerability by upgrading a core SDK dependency to its latest patched version. This ensures that the server benefits from the most recent security fixes and maintains a robust and secure operational environment.

Highlights

• Security Update: Addresses a high-severity security vulnerability in the server by updating the @modelcontextprotocol/sdk dependency.
• Dependency Version Bump: The @modelcontextprotocol/sdk package has been updated from version "1.25.1" to "1.25.2" in the server's dependencies.
• Dependency Lock File Adjustments: The package-lock.json file has been updated to reflect the new SDK version and includes several modifications to peer dependency flags for various packages, ensuring consistent dependency resolution.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request updates the @modelcontextprotocol/sdk dependency to version 1.25.2 to address a security vulnerability. The change in apps/server/package.json is correct. However, the package-lock.json file contains a significant number of changes unrelated to this dependency update, primarily toggling the peer flag for many packages. This churn makes the PR difficult to review and could indicate inconsistencies in the development environment. I've added a comment with suggestions on how to minimize lockfile changes in the future and enforce a consistent npm version across the project.

[gemini-code-assist]

While the update to @modelcontextprotocol/sdk is correct, this package-lock.json file includes a large number of changes to peer: true flags across many dependencies, which seem unrelated to the SDK update. This kind of churn often happens when npm install is run with a different version of npm than what was used to generate the original lockfile.

This makes the pull request noisy and harder to review, and can sometimes introduce unintended side effects.

To improve maintainability and consistency, I suggest the following:

• For simple dependency updates, prefer using npm update @modelcontextprotocol/sdk which will minimally modify the lockfile.
• Consider adding an npm version to the engines field in the root package.json to ensure all developers are using the same version of the package manager. For example:

  "engines": {
    "node": ">=22.0.0 <23.0.0",
    "npm": ">=10.0.0"
  }

This will help prevent this kind of lockfile churn in the future.