Provides integration with Git through cloning repositories and managing submodules to access critic frameworks for code review.
Supports cloning repositories from GitHub to access the critic frameworks used for code analysis and reviews.
Integrates with npm for package management, dependency installation and running scripts for server operation.
Offers specialized code review capabilities for React components through the review-design critic tool.
Provides specialized review capabilities for Unicode and internationalization issues through the review-unicode critic tool.
Specialized Code Review Tools for Copilot
A Model Context Protocol (MCP) server that provides specialized code review capabilities using established critic methodologies and fixing strategies.
Example Usage
The workflow has two steps in your VS Code agent chat:
- Analysis: Use a critic tool to analyze code and identify issues
- Fix: Apply a fixer strategy to address the identified problems
Step 1: Analyze Code
Start a new chat to clear context, then write a request like:
Step 2: Apply Fixes
Choose one:
Features
- 36+ Specialized Critics: Each critic focuses on specific aspects of code quality
- 3 Fixing Strategies: Methods for addressing critic findings
- Explicit Invocation: Users explicitly choose which critic or fixer to apply to their code
- Established Methodologies: Uses frameworks from the ai-review repository
- Two-Step Workflow: Analysis first, then apply fixing strategy
Setup
Prerequisites
- Node.js 18.0 or higher
- VS Code with GitHub Copilot extension
Installation
- Clone with submodules to get critic frameworks:
- Install dependencies:
VS Code Configuration
Add the MCP server to your VS Code settings:
- Open VS Code settings (JSON):
- Press
Ctrl+Shift+P
(Windows/Linux) orCmd+Shift+P
(Mac) to open the command palette - Type "Preferences: Open User Settings (JSON)" and select it
- This opens your
settings.json
file
- Press
- Add the following to the
mcp.servers
section (create the section if it doesn't exist):
When using WSL, VS Code executes the server inside the Linux environment:
If Node.js is not in your WSL PATH (e.g., when using NVM), specify the full path:
Important: Replace /path/to/your/mcp-review/
with the actual path where you cloned this repository (use Unix-style paths for WSL).
After adding the configuration, restart VS Code. VS Code will invoke the server automatically when you use the review tools in Copilot chat.
Available MCP Tools
The server loads all critic methodologies from the ai-review/critic
directory and fixer strategies from the ai-review/fixer
directory.
Critic MCP Tools
All critics follow the naming pattern review-<critic-name>
and are organized by category:
Design & UI Critics
review-design
- UI and user experience reviewreview-color
- Color usage and accessibilityreview-data-visualization
- Charts and data presentation
Security Critics
review-sql-security
- SQL injection and database securityreview-sql-data-integrity
- Data validation and constraints
Performance Critics
review-algorithm-performance
- Algorithm efficiency analysisreview-algorithm-correctness
- Algorithm correctness verificationreview-logging-performance
- Logging overhead analysis
Memory & Resource Management
review-c-memory
- C memory management reviewreview-c-error-handling
- C error handling patternsreview-c-portability
- Cross-platform C code
Error Handling
review-general-error-handling
- Error handling best practicesreview-procedural-error
- Procedural error management
Data & Logic
review-procedural-data
- Data structure and flow analysisreview-procedural-functions
- Function design and organizationreview-procedural-flow
- Control flow analysisreview-floating-point
- Numerical precision and floating-point issuesreview-datetime
- Date/time handling correctnessreview-unicode
- Unicode and internationalization
Standards & Compliance
review-sql-standard-compliance
- SQL standard adherencereview-posix
- POSIX compliance and portabilityreview-unix-interface
- Unix philosophy and interfaces
Development Practices
review-logging-practices
- Logging strategy and implementationreview-terminology
- Naming conventions and clarityreview-writing
- Documentation and commentsreview-estimation
- Complexity and effort estimationreview-benchmarking
- Performance measurement practices
Specialized Critics
review-meson
- Meson build system reviewreview-probability
- Statistical and probabilistic codereview-relational
- Database design and relationshipsreview-prompting
- AI prompt engineeringreview-logicism
- Formal logic and reasoningreview-taylorism
- Workflow and efficiency analysis
Fixer MCP Tools
Three fixer strategies are available:
fix-comment
- Add TODO comments marking issues for later fixingfix-conservative
- Fix only clear-cut, low-risk issues that won't require cascading changesfix-zealot
- Pick one important issue and fix it comprehensively, even if it requires major reorganization
Development
Testing
npm test
- Run all test suitesnpm run test:mcp
- Run MCP protocol validationnpm run test:comprehensive
- Run comprehensive feature tests
Utilities
npm run status
- Display server capabilities and statusnpm run check
- Check VS Code integration readiness
Manual Testing
To debug, you can run the server manually:
npm start
- Run the server in standalone modenpm run dev
- Run in development mode with auto-restart
Project Structure
Credit
Critic frameworks provided by the ai-review repository by Joe Nelson.
A specialized code review service that provides 36+ critics for different programming aspects and 3 fixing strategies to automatically address identified issues in a two-step workflow.
Related MCP Servers
- -securityFlicense-qualityProvides code completion, bug fixing, and test generation for multiple programming languages, integrating with the Mistral Codestral API to enhance code development processes.Last updated -2TypeScript
- -securityFlicense-qualityA code review tool for Cursor IDE that uses OpenAI's GPT models to provide intelligent code analysis and suggestions.Last updated -2Python
- AsecurityFlicenseAqualityAnalyzes codebases using Repomix and LLMs to provide structured code reviews with specific issues and recommendations, supporting multiple LLM providers including OpenAI, Anthropic, and Gemini.Last updated -220JavaScript
- -securityFlicense-qualityA local server that provides powerful code analysis and search capabilities for software projects, helping AI assistants and development tools understand codebases for tasks like code generation and refactoring.Last updated -2Python