Specialized Code Review Tools

You deploy this MCP server to gain specialized code review capabilities that leverage established critic methodologies and fixing strategies. It enables a two-step workflow: analyze code with critics to identify issues, then apply targeted fixes with fixed strategies to improve code quality.

How to use

You interact with the MCP server through a compatible client in your development environment. Start a new analysis session to clear context, then request evaluations such as UI/UX reviews, security checks, data handling assessments, or performance considerations. After you obtain the critique results, choose one of the predefined fixer strategies to apply improvements directly to your codebase. This two-step pattern—analyze then fix—helps you focus on high-impact issues and track changes in a structured way.

How to install

Prerequisites you need before installing are Node.js 18.0 or higher and a development environment with VS Code.

Follow these concrete steps to set up the MCP server locally.

# 1) Clone the project with submodules to fetch critic and fixer frameworks
# Use your preferred destination path
git clone --recursive https://github.com/jonels-msft/mcp-review.git
cd mcp-review

# 2) Install dependencies
npm install

Configuration and running the MCP server in VS Code

Configure your editor to run the MCP server as a local (stdio) process so the client can communicate with it. Create a server entry that points to the local server index file.

{
  "mcp": {
    "servers": {
      "mcp_review": {
        "command": "node",
        "args": [
          "/path/to/your/mcp-review/src/index.js"
        ]
      }
    }
  }
}

Notes on using VS Code with WSL

If you run your editor in Windows Subsystem for Linux (WSL), VS Code executes the MCP server inside the Linux environment. Use the same structure as above, but wrap the command to run inside the WSL context.

{
  "mcp": {
    "servers": {
      "mcp_review": {
        "command": "wsl",
        "args": [
          "node",
          "/path/to/your/mcp-review/src/index.js"
        ]
      }
    }
  }
}

Notes on environment variables

The setup may not require additional environment variables for basic operation. If your project or workflow introduces environment parameters, include them in both the global MCP settings and the per-server env mapping.

Troubleshooting and tips

If the MCP server does not start automatically in your editor, ensure the path to your index file is correct and that Node.js is available in the environment. Restart VS Code after configuring the server entry. Check the terminal or output panel for any startup errors and confirm the server reports its status back to the client.

Available tools

review-design

UI and user experience review

review-color

Color usage and accessibility review

review-data-visualization

Charts and data presentation review

review-sql-security

SQL injection and database security review

review-sql-data-integrity

Data validation and constraints review

review-algorithm-performance

Algorithm efficiency analysis

review-algorithm-correctness

Algorithm correctness verification

review-logging-performance

Logging overhead analysis

review-c-memory

C memory management review

review-c-error-handling

C error handling patterns

review-c-portability

Cross-platform C code review

review-general-error-handling

Error handling best practices

review-procedural-error

Procedural error management

review-procedural-data

Data structure and flow analysis

review-procedural-functions

Function design and organization review

review-procedural-flow

Control flow analysis in procedures

review-floating-point

Floating-point precision and associated issues review

review-datetime

Date/time handling correctness review

review-unicode

Unicode and internationalization review

review-sql-standard-compliance

SQL standard compliance analysis

review-posix

POSIX compliance and portability review

review-unix-interface

Unix philosophy and interface review

review-logging-practices

Logging strategy and implementation review

review-terminology

Naming conventions and clarity in code

review-writing

Documentation and comments quality review

review-estimation

Complexity and effort estimation review

review-benchmarking

Performance measurement practices review

review-meson

Meson build system review

review-probability

Statistical and probabilistic code review

review-relational

Database design and relationships review

review-prompting

AI prompt engineering review

review-logicism

Formal logic and reasoning review

review-taylorism

Workflow and efficiency analysis review

fix-comment

Add TODO comments marking issues for later fixing

fix-conservative

Fix only low-risk issues that won’t trigger cascading changes

fix-zealot

Fix one important issue comprehensively, even if major rearrangement is needed