Cursor Reviewer MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Cursor Reviewer MCP review the new authentication module in src/auth.js"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
cursor-reviewer-mcp
MCPサーバー「cursor-reviewer」。Claude Code から cursor.review または codex.review ツールを呼び出し、Cursor CLI(GPT‑5)または Codex CLI でレビューを実行し、レビューJSONのみを返します。仕様は 1.specs/spec.md(v3)に準拠しています。
概要
ツール名:
cursor.review,codex.review入力:
targets,reference,review_request,timeout_ms(オプション),policy(予約・null固定)実装: Node.js + TypeScript + MCP SDK(
@modelcontextprotocol/sdk)Cursor実行:
cursor-agent -p --model gpt-5 --output-format json "<プロンプト>"Codex実行:
codex exec "<プロンプト>"出力: 各CLIの出力からレビューJSONのみを抽出し返却
監査:
reviews/YYYYMMDD-HHMMSS.jsonにレビューJSONを保存
Related MCP server: Review MCP Server
ディレクトリ構成
.
├─ bin/
│ └─ cursor-reviewer-mcp # 実行バイナリ(ビルド済みdistを起動)
├─ src/
│ ├─ server.ts # MCPサーバー本体(stdio)
│ ├─ cursor.ts # Cursor CLI 呼び出し・再試行・パース
│ ├─ codex.ts # Codex CLI 呼び出し・再試行・パース
│ ├─ prompt/
│ │ └─ template.txt # 共有プロンプトテンプレート
│ └─ schemas/
│ ├─ cursor.review.input.schema.json
│ └─ codex.review.input.schema.json
├─ reviews/.gitkeep # 監査ログ出力先(JSON)
├─ .cursor/cli.json # Cursor CLI の権限制御(Read-only)
├─ .claude/agents/build-and-iterate.md # サブエージェント定義テンプレ
├─ package.json
├─ tsconfig.json
├─ .gitignore
└─ README.mdセットアップ
Node.js 22 LTS を用意(推奨)
nvm利用時:nvm use(本リポジトリは.nvmrcで 22 を指定)
依存インストール(任意のパッケージマネージャ)
npm iビルド
npm run build実行(MCPサーバーとして stdio で起動)
./bin/cursor-reviewer-mcpClaude Code への登録例(プロジェクトスコープ)
claude mcp add --scope project cursor-reviewer $(pwd)/bin/cursor-reviewer-mcp環境変数
通常は不要です。
cursor-agentやcodexが既にローカル設定済みであれば、環境変数は不要です。特殊な環境(CI 等)で
cursor-agentが環境変数経由の認証を要求する場合のみ、CURSOR_API_KEYを設定してください。Codex CLI のパスを明示する場合は
REVIEWER_MCP_CODEX_BIN、追加フラグはREVIEWER_MCP_CODEX_FLAGSを設定します(シェル風の記法で引用可、例:--model "gpt 4" --quiet)。スキーマを差し替える場合は
REVIEWER_MCP_SCHEMA_DIR(ディレクトリを指定)、または個別にREVIEWER_MCP_CURSOR_SCHEMA_PATH/REVIEWER_MCP_CODEX_SCHEMA_PATHを指定します。JSON以外の出力を許容する場合のみ
REVIEWER_MCP_ALLOW_PLAINTEXT_FALLBACK=1を設定します(デフォルトは厳格にJSONのみ)。
ツール仕様(要点)
入力スキーマは
src/schemas/*.review.input.schema.jsonに定義。targets[].pathが存在しない場合はエラーを返却。CursorはトップレベルJSONの
resultからレビューJSONを抽出、Codexは標準出力から直接抽出(失敗時1回だけ再実行)。各実行のレビューJSONは
reviews/にタイムスタンプ名で保存。
注意
このリポジトリにはSDK等の依存は含まれていません。
npm iで取得してください。Cursor CLI(
cursor-agent)および Codex CLI(codex)がPATHに存在する必要があります。
ライセンス
本リポジトリは MIT License です。詳細は
LICENSEを参照してください。
Available Tools
2 toolscodex.reviewRun review via Codex CLIC
Review deliverables via Codex CLI and return review JSON only.
Inputs: targets (required), reference (required), review_request (required), previous_reviews, +2 more.
cursor.reviewRun review via Cursor (GPT‑5)C
Review deliverables via Cursor CLI (GPT‑5) and return review JSON only.
Inputs: targets (required), reference (required), review_request (required), previous_reviews, +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: codex.review uses Codex CLI, while cursor.review uses Cursor CLI with GPT-5. There is no overlap in functionality as each targets a different review system, making misselection unlikely.
Both tools follow a consistent naming pattern: they use a prefix (codex or cursor) followed by a dot and the action 'review'. This pattern is uniform across all tools, making them predictable and easy to identify.
With only 2 tools, the server feels thin for a 'Cursor Reviewer' domain, as it lacks operations like listing reviews, updating reviews, or handling review feedback. The count is too low to support comprehensive review workflows.
The tool surface is severely incomplete for a review system; it only provides review creation via two CLI methods, missing essential CRUD operations such as retrieving, updating, deleting reviews, or managing review-related data. This will likely cause agent failures in broader tasks.
Maintenance
Related MCP Connectors
AI code review for GitHub PRs with an MCP autofix loop for Claude Code and Cursor
Approved test intent, reviewed Playwright automation and run evidence, inside your editor.
Multi-brand AI code review for Claude: up to 12 reviewers and a judge, no install.
Run accessibility, contrast, and design token audits and file QA issues from your AI coding tool.
Related MCP Servers
- -licenseCqualityNot gradedmaintenanceEnables comprehensive GitHub PR reviews through Cursor's AI by fetching PR diffs, running static analysis tools (ESLint, Prettier, TypeScript, Semgrep), executing tests, and generating detailed code review reports with inline comments.92,530 npm1-
- AlicenseAqualityDmaintenanceEnables Claude to perform thorough code reviews by integrating with Codex and Gemini CLIs to provide senior-level feedback on code quality, security, performance, and best practices. Supports reviewing code snippets, individual files, or entire directories with automatic detection of available review tools.4696 npmMIT
- AlicenseBqualityDmaintenanceEnables AI assistants to perform code reviews by providing access to staged files, git diffs, and repository file content. It allows users to evaluate changes and context within any local git repository before committing or pushing.31 npmISC
- AlicenseNot gradedqualityDmaintenanceEnables AI-powered code review and improvement, including analysis, refactoring suggestions, and automatic test generation, with an optional agentic loop for iterative refinement.MIT