Skillget

Revvy

mcp
Guvenlik Denetimi
Basarisiz
Health Uyari
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 9 GitHub stars
Code Basarisiz
  • rm -rf — Recursive force deletion command in build.sh
Permissions Gecti
  • Permissions — No dangerous permissions requested
Purpose
This MCP server and VS Code extension provides AI-powered, automated code reviews for GitHub and GitLab. It allows teams to define standardized review rules in a YAML file and enforces them on pull/merge requests directly within the editor using major AI backends like Copilot, Claude, and OpenAI.

Security Assessment
The tool interacts with third-party AI APIs (OpenAI, Anthropic) and external Git providers (GitHub, GitLab), meaning it inherently makes external network requests and accesses sensitive source code and potentially Jira tickets. No dangerous system permissions were requested, and no hardcoded secrets were detected. However, the scan flagged a recursive force deletion command (`rm -rf`) inside a build script, which is a minor code safety concern but generally acceptable for build/CI processes. Overall risk is assessed as Medium due to the routine external transmission of proprietary source code to third-party AI services.

Quality Assessment
The project is licensed under the standard MIT license and is actively maintained, with recent repository activity. The major drawback is its extremely low community visibility; having only 9 GitHub stars indicates that the tool has not been broadly tested or vetted by the open-source community.

Verdict
Use with caution: the extension is actively maintained and officially licensed, but you must be comfortable sending your proprietary code to external AI providers and relying on a largely unvetted, low-visibility project.
SUMMARY

Team code review, standardized. Define your team's review rules once in YAML, enforce them on every PR/MR across GitHub & GitLab — right inside VS Code. Works with Copilot, Claude, or OpenAI.

README.md

revvy Logo

VS Code Marketplace License: MIT CI

Code review that knows your rules.

What is it?

Revvy is a VS Code extension that brings structured, AI-powered code review directly into your editor. Instead of generic AI feedback, it enforces a set of rules you define in YAML — tailored to your team's standards, domain, or industry requirements (e.g. safety-critical embedded C/C++, Python, and more).

Why not just use /review or type a prompt?

  • Many developers are not good at writing prompts.
  • Every review requires crafting a new prompt tailored to a specific tech stack or language.
  • AI can't deliver a thorough review without specific rules or best practices — the kind that are usually defined at the company or team level.
  • Rules vary from one developer to another, which is why Revvy uses hardcoded, shared rules stored in a single YAML file that the whole team uses.
  • A clean UI that shows you the exact line of code with an inline comment when an issue or warning is detected.

That's all?

Not quite. Revvy also:

  • Reviews multiple GitHub PRs and GitLab MRs in a single pass using MCP
  • Validates your code against Jira ticket requirements — so nothing slips out of scope
  • Generates integration tests (functional + regression)
  • Provides a Copy as Markdown button that copies all review comments along with a ready-to-use prompt — paste it into your favorite AI assistant (ChatGPT, Claude, Copilot, etc.) to fix every issue in one shot
  • (Coming soon) Auto-comment on PRs/MRs — Revvy posts a comment on the pull/merge request stating it has been reviewed by the tool, with a summary of findings for reviewers and maintainers to see at a glance

It works with the AI backend you already have — GitHub Copilot (no extra key needed), OpenAI GPT-4o, or Anthropic Claude — with automatic fallback.

Why Revvy over other tools?

Revvy Generic AI prompt (Copilot Chat, etc.) Paid review tools
Rule-driven, team-shared standards Yes — YAML profiles in your repo No — prompt varies per developer Partial — cloud-managed rules
Works with your existing AI subscription Yes — Copilot, OpenAI, Anthropic Yes No — separate subscription
Embedded / safety-critical profiles Yes — C/C++, Yocto, MISRA-style rules No No
Multi-repo PR/MR in one pass Yes — GitHub + GitLab via MCP No Partial
Cost Free & open-source Included in your AI plan Paid

Demo

revvy

Quick Start

From the VS Code Marketplace:

Search for Revvy in the VS Code Extensions panel and install it.

From source:

git clone https://github.com/YonK0/revvy.git
cd revvy
npm install
npm run compile
# Press F5 in VS Code to launch the Extension Development Host

Once installed, click the Revvy icon in the Activity Bar. Three example profiles are created automatically on first use (c-embedded, yocto, python).

Writing Rule Profiles

Create .yaml files in .vscode-reviewer/profiles/. Rules are reloaded automatically on save.

profile:
  id: my-team
  label: "My Team Rules"
  version: "1.0.0"
  file_patterns:
    - "**/*.ts"

  rules:
    - id: NO_CONSOLE_LOG
      title: "No console.log in production code"
      category: "coding-standards"
      severity: warning      # error | warning | info
      enabled: true
      description: |
        console.log statements should not be merged to main.
        Use a structured logger instead.

See the bundled profiles in .vscode-reviewer/profiles/ for full examples.

MCP Servers (Optional)

Enables Jira ticket fetching and multi-repo PR/MR review. Copy .vscode/mcp.json and fill in your credentials — tokens are prompted at runtime and never stored on disk.

Server Install Used for
GitHub Docker Fetch PR diffs for multi-repo review
GitLab npm i -g @modelcontextprotocol/server-gitlab Fetch MR diffs
Atlassian pip install mcp-atlassian Fetch Jira ticket requirements

Requirements

  • VS Code 1.96.0+
  • Git in PATH
  • One of: GitHub Copilot subscription or free tier / OpenAI API key / Anthropic API key

Architecture

src/
├── extension.ts      # Entry point — commands, WebView provider, YAML watcher
├── panelProvider.ts  # WebView UI — welcome, loading, results screens
├── reviewer.ts       # Core engine — prompt construction, AI call, response parsing
├── aiBackend.ts      # AI abstraction — Copilot, OpenAI, Anthropic + fallback chain
└── ruleLoader.ts     # YAML loader — file scanning, parsing, live-reload watcher

Contributing

Contributions are welcome — new rule profiles, AI backends, bug fixes, UI improvements. See CONTRIBUTING.md.

Yorumlar (0)

Sonuc bulunamadi