Cursor Auto-Review MCP Server
An MCP server that automates code reviews through linting, testing, and git diff analysis. It also generates conventional commit messages and detailed pull request descriptions based on file changes and code patterns.
README
Cursor Auto-Review MCP Server
MCP server for automated code review, testing, linting, and commit/PR generation.
Features
Available Tools
- get_diff - Get git diff (staged or working)
- get_recent_commits - Get recent commit messages
- run_tests - Run test suite
- run_lint - Run linter
- generate_commit_and_pr - Generate commit message and PR description ✨ NEW
New Feature: Commit & PR Generation
The generate_commit_and_pr tool analyzes your changed files and automatically generates:
-
Detailed Commit Message with:
- Conventional commit format (feat/fix/refactor/chore)
- Change summary
- File statistics
- Affected areas
- File type breakdown
-
PR Description with:
- Summary: Overview of changes
- Why: Reasons for the changes
- How: Implementation details
- Risks/Rollback: Risk assessment and rollback plan
- Testing Recommendations: Checklist for testing
Usage
Command: /auto-review-commit
When you type /auto-review-commit in Cursor, the AI will:
- Analyze all changed files (working directory by default)
- Generate a detailed commit message
- Generate a comprehensive PR description
- Provide analysis statistics
Example:
/auto-review-commit
Command: /auto-review
The /auto-review command now includes commit and PR generation at the end:
- Get git diff
- Check for linting errors
- Run tests (if available)
- Analyze code quality
- Generate commit message and PR description ✨ NEW
Tool Parameters
generate_commit_and_pr
{
mode?: "staged" | "working" // Default: "working"
}
staged: Analyze staged changes onlyworking: Analyze all working directory changes
Output Format
The tool returns a JSON object with:
{
"commitMessage": "feat(search): improve type safety, add documentation\n\n...",
"prDescription": "## Summary\n\n...",
"analysis": {
"changedFiles": 2,
"totalAdditions": 150,
"totalDeletions": 50,
"affectedAreas": ["app/composables", "app/components"],
"fileTypes": { "ts": 1, "vue": 1 }
}
}
Installation
- Build the project:
npm run build
- The MCP server is configured in
~/.cursor/mcp.json:
{
"mcpServers": {
"cursor-auto-review": {
"command": "node",
"args": ["/path/to/cursor-autoreview-mcp/dist/index.js"]
}
}
}
- Restart Cursor to load the updated MCP server.
How It Works
Commit Message Generation
The tool analyzes:
- File changes (additions, deletions, modifications)
- Code patterns (type improvements, documentation, constants)
- Affected areas and file types
- Change magnitude (refactor vs feature vs fix)
PR Description Generation
The tool creates sections:
- Summary: High-level overview with statistics
- Why: Extracted from code patterns and change analysis
- How: Detailed breakdown of changes made
- Risks/Rollback: Risk assessment based on change scope and affected areas
- Testing Recommendations: Context-aware testing checklist
Examples
Example 1: Type Safety Improvements
Input: Changed files with FilterItem type imports
Output:
- Commit:
refactor(search): improve type safety, extract constants - PR Why: "Improve type safety and reduce potential runtime errors"
- PR How: "Replaced
any[]types with properFilterItem[]types"
Example 2: Documentation Updates
Input: Files with JSDoc comments added
Output:
- Commit:
docs(search): add documentation, improve error handling - PR Why: "Enhance code documentation and maintainability"
- PR How: "Added JSDoc comments to complex functions"
Development
# Build TypeScript
npm run build
# Run in development (if ts-node is available)
npm start
License
ISC
Cursor-auto-review-mcp
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.