What does Rami Code Review do during a review?
It fetches review results, walks each finding by priority, fixes each one or lets you dispute with evidence, then commits and pushes changes.

@rami-code-review
基本情報
Rami reviews every pull request for the bugs, logic errors, and risky patterns that AI coding agents commonly leave behind. When it flags something, your agent — Claude Code, Cursor, or Codex — fetches the finding over MCP, fixes it, and pushes; Rami re-reviews until those issues
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"rami": {
"url": "https://rami.reviews/mcp"
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
このサーバーは認証が必要です。ツールの取得にはログインや提供元の認証情報が必要な場合があります。
上のボタンでサーバーのエンドポイントに接続し、ツール一覧を取得できます。
Rami Code Review is an MCP server that reviews pull requests for security vulnerabilities, bugs, and performance issues, then fixes the findings through MCP. It works with Claude Code and Codex, and gives you full control over what merges.
Install the Rami GitHub App on your repository, add the marketplaces for Claude Code or Codex, install the plugin, then run /rami:review on a PR branch. The server walks each finding by priority — blocking, high, medium, low — and applies fixes or accepts disputes until the PR is clean.
It fetches review results, walks each finding by priority, fixes each one or lets you dispute with evidence, then commits and pushes changes.
You need to install the Rami GitHub App on your repository and add the Rami plugin through either the Claude Code or Codex marketplace.
Use the dispute loop built into the same review session by providing evidence for categories like false positive, framework guarantee, intentional design, or duplicate. Accepted disputes drop out so only real issues land in commits.
The Rami GitHub App must be installed on the repository. Install it from [github.com/apps/rami-code-remeow](https://github.com/apps/rami-code-remeow) to resolve this.
The `/rami:review` command repeats its fix-dispute loop until the PR is clean, up to a maximum of 5 iterations per session.

JiCo for Jira & Confluence: local MCP server for Jira Data Center - redacts personal data before the AI model, holds every write for approval
ZeroBeacon.ai — Collision-proof commerce router for AI agents. 1000 MCP tools: commerce, trust, billing, sovereign ID + everyday tools. LIVE.
OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

Design review for UI code, inside your agent. quick_review checks the files you just changed in about ten seconds. review_files returns a 0-100 score and patches. verify_fixes confirms the fixes landed, free. review_url
コメント