feat: allow filtering exposed tools#4
Conversation
Summary of ChangesHello @mKeRix, 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 introduces a new feature that enables granular control over the tools exposed by Model Context Protocol (MCP) servers. Users can now define Highlights
Using Gemini Code AssistThe 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
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 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
|
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #4 +/- ##
==========================================
+ Coverage 52.50% 52.61% +0.10%
==========================================
Files 32 33 +1
Lines 2272 2313 +41
Branches 136 142 +6
==========================================
+ Hits 1193 1217 +24
- Misses 1079 1096 +17 ☔ View full report in Codecov by Sentry. |
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request introduces a valuable feature for filtering tools from MCP servers. The implementation is well-structured, with the core filtering logic correctly isolated in its own file and accompanied by a comprehensive suite of tests. The changes to the configuration schema and types are clear and consistent. I've provided a few suggestions to improve performance and code clarity. Overall, this is a solid contribution.
# 1.0.0 (2025-12-01) ### Features * add config merging ([#5](#5)) ([4d58cb7](4d58cb7)) * add semantic tool search ([#2](#2)) ([cac523b](cac523b)) * allow filtering exposed tools ([#4](#4)) ([bd1d64c](bd1d64c)) * implement code mode ([#1](#1)) ([b3c4646](b3c4646)) * initial commit ([5477138](5477138)) * support oauth2 protected mcp servers ([#3](#3)) ([f5408d1](f5408d1))
# 1.0.0 (2025-12-01) ### Features * add config merging ([#5](#5)) ([4d58cb7](4d58cb7)) * add semantic tool search ([#2](#2)) ([cac523b](cac523b)) * allow filtering exposed tools ([#4](#4)) ([bd1d64c](bd1d64c)) * implement code mode ([#1](#1)) ([b3c4646](b3c4646)) * initial commit ([5477138](5477138)) * support oauth2 protected mcp servers ([#3](#3)) ([f5408d1](f5408d1))
|
🎉 This PR is included in version 1.0.0 🎉 The release is available on: Your semantic-release bot 📦🚀 |
2 participants
This will allow users to filter the tools exposed by an MCP server with include and exclude rules, giving them the option to target what the AI will use even if the underlying MCP server does not offer this functionality.