Automated PR reviews and status checks, providing tools to analyze pull requests, add review comments, and update status checks.
Click on "Install 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., "@codesentry-mcp analyze the repo at ./src for security vulnerabilities and code quality"
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.
AI-Powered Code Review Assistant using Model Context Protocol
CodeSentry is an intelligent code review assistant that integrates with AI systems through the Model Context Protocol (MCP). It provides comprehensive analysis of your codebase, identifying security vulnerabilities, performance bottlenecks, code quality issues, and documentation gaps.
🔒 Security Analysis - Detect OWASP Top 10 vulnerabilities and security anti-patterns
⚡ Performance Analysis - Identify bottlenecks and optimization opportunities
🎯 Code Quality - Find code smells, complexity issues, and maintainability problems
📚 Documentation Review - Check for missing or outdated documentation
🤖 AI Integration - Natural language explanations and suggestions
🔗 GitHub Integration - Automated PR reviews and status checks
🧪 Live Testing - Built-in MCP client for immediate feedback
Related MCP server: Argus MCP
Node.js 18+
Git
An AI assistant that supports MCP (Claude, etc.)
# Clone the repository
git clone https://github.com/ayushgundecha/codesentry-mcp.git
cd codesentry-mcp
# Install dependencies
npm install
# Build the project
npm run build
# Test the server
npm run devAdd to Claude Desktop (macOS):
{
"mcpServers": {
"codesentry": {
"command": "node",
"args": ["/path/to/codesentry-mcp/dist/index.js"],
"env": {}
}
}
}Test the connection:
Ask Claude: "Use the ping tool to test CodeSentry"Analyze a repository:
Ask Claude: "Use CodeSentry to analyze the repository at /path/to/your/project"codesentry-mcp/
├── src/
│ ├── analyzers/ # Analysis engines (security, performance, quality)
│ ├── integrations/ # External service integrations (Git, GitHub, AI)
│ ├── mcp/ # MCP protocol implementation
│ ├── utils/ # Utility functions and helpers
│ └── types/ # TypeScript type definitions
├── tests/ # Test suites
├── docs/ # Documentation
└── examples/ # Usage examplesnpm run dev # Start development server
npm run build # Build for production
npm run test # Run test suite
npm run lint # Lint code
npm run format # Format code with Prettieranalyze_repository - Comprehensive repository analysis
analyze_file - Single file analysis
scan_security - Security vulnerability scan
check_dependencies - Dependency audit
explain_code - Natural language code explanations
suggest_improvements - AI-powered refactoring suggestions
generate_tests - Test case recommendations
analyze_pr - Pull request analysis
comment_suggestion - Add review comments
update_status - Update PR status checks
{
"security": [
{
"type": "SQL_INJECTION",
"severity": "HIGH",
"file": "src/user.ts",
"line": 42,
"description": "Potential SQL injection vulnerability",
"suggestion": "Use parameterized queries",
"fix": "await prisma.user.findMany({ where: { id: userId } })"
}
],
"performance": [
{
"type": "ALGORITHM_COMPLEXITY",
"severity": "MEDIUM",
"file": "src/sort.ts",
"line": 15,
"complexity": "O(n²)",
"suggestion": "Use Array.sort() for better performance",
"estimatedImpact": "90% improvement"
}
]
}We welcome contributions! Please see our Contributing Guide for details.
Fork the repository
Create a feature branch (git checkout -b feature/amazing-feature)
Commit your changes (git commit -m 'Add amazing feature')
Push to the branch (git push origin feature/amazing-feature)
Open a Pull Request
This project is licensed under the MIT License - see the LICENSE file for details.
Model Context Protocol by Anthropic
TypeScript ESLint for code analysis patterns
Simple Git for Git integration
📧 Email: your-email@example.com
Analyze a git repository for security, performance, and quality issues
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Path to the repository to analyze | |
| config | No | Analysis configuration options |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description provides no behavioral details such as whether the analysis is read-only, what permissions are needed, whether it has side effects, or what output is returned. With no annotations, the agent lacks critical information about the tool's runtime behavior, leaving a significant transparency gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence that efficiently conveys the tool's purpose with no unnecessary words or redundancy. It is optimally concise and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has a nested config object with multiple toggles and no output schema, yet the description is minimal. It does not explain how to use the config parameter, what the tool returns, or any behavioral constraints. This is insufficient for an agent to invoke the tool correctly in varied scenarios.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Although the schema has 100% coverage, the description adds no explanation of the 'config' parameter or its options. The description lists security, performance, and quality, but the schema also includes 'enableDocumentation', which is not mentioned, creating a mismatch. The description adds little beyond the schema's property names and types.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool analyzes a git repository for security, performance, and quality issues. It uses a specific verb and resource, and is unambiguous. The only sibling tool is 'ping', which serves a different purpose, so there is no confusion.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context by stating what the tool does, but it does not explicitly say when to use it or provide alternatives. Since the only sibling is 'ping', the intended use is reasonably obvious, yet there is no formal guidance on when to choose this tool over others.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Test connectivity to the CodeSentry server
| Name | Required | Description | Default |
|---|---|---|---|
| message | No | Optional message to echo back |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the transparency burden. It implies a safe, non-destructive connectivity check but does not disclose return values, error behavior, or side effects. For a simple ping, this is adequate but minimal.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
One sentence, front-loaded with the action, and zero waste. The description and schema together provide the necessary information without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple connectivity test with one optional parameter, the description is sufficient. No output schema exists, so the return format is not explained, but a ping tool's purpose implies a simple success/failure response. Minor gap in not mentioning the echo behavior explicitly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%: the 'message' parameter is fully described in the schema as 'Optional message to echo back'. The description adds no additional parameter meaning, so the baseline of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Test connectivity to the CodeSentry server' uses a specific verb ('test') and a clear resource ('CodeSentry server'). It fully distinguishes from the sibling tool 'analyze_repository', which is about analysis, not connectivity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The usage is implied: use it to verify server availability. No explicit alternatives or exclusions are mentioned. With only one sibling, the purpose distinction is clear, but there is no direct comparison or when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.0analyze_repositorypingThe two tools serve entirely different purposes: one checks connectivity and the other performs repository analysis. There is no overlap or ambiguity in their intended use.
Both tool names are imperative verbs, but 'ping' is a bare verb while 'analyze_repository' follows a verb_noun pattern. This is a minor deviation from a fully uniform naming convention.
With only two tools, the server feels minimal. For a repository analysis service, one might expect additional tools for managing or retrieving results, but the count is not unreasonable for a simple utility.
The core analysis functionality is present, but there are no supporting operations such as listing previous analyses, fetching detailed reports, or configuring analysis parameters. The surface is functional but incomplete for a comprehensive analysis workflow.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Screens public GitHub repos and PRs to generate risk maps, findings, and merge-readiness signals.
Security reviews for coding agents: diffs checked against your org policy and live infrastructure.
Independent security review for AI-built apps. Watch a GitHub repo. Never a patch.
AI pentesting: run scans, triage vulnerabilities, review PRs, manage schedules and assets.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ayushgundecha/codesentry-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
