Skip to main content
Glama

šŸ”’ CyberMCP

AI-powered Cybersecurity API Testing with Model Context Protocol (MCP)

License: MIT Node.js TypeScript

CyberMCP is a Model Context Protocol (MCP) server that enables AI agents to perform comprehensive security testing on backend APIs. It provides 14 specialized security tools and 10 resources for identifying vulnerabilities like authentication bypass, injection attacks, data leakage, and security misconfigurations.

šŸš€ Quick Start

# Clone and setup
git clone https://github.com/your-username/CyberMCP.git
cd CyberMCP
npm install
npm run build

# Test the server
npm run test-server

# Start interactive testing
npm run test-interactive

Related MCP server: MCPwner

✨ Features

  • šŸ” Authentication Testing - JWT analysis, bypass detection, OAuth2 flows

  • šŸ’‰ Injection Testing - SQL injection, XSS vulnerability detection

  • šŸ“Š Data Protection - Sensitive data exposure, path traversal checks

  • ā±ļø Rate Limiting - DoS vulnerability assessment

  • šŸ›”ļø Security Headers - OWASP security header validation

  • šŸ“š Comprehensive Resources - Security checklists and testing guides

šŸ› ļø Security Tools (14 Total)

Category

Tools

Authentication

basic_auth, token_auth, oauth2_auth, api_login, auth_status, clear_auth, jwt_vulnerability_check, auth_bypass_check

Injection Testing

sql_injection_check, xss_check

Data Protection

sensitive_data_check, path_traversal_check

Infrastructure

rate_limit_check, security_headers_check

šŸŽÆ IDE Integration

CyberMCP works with all major AI-powered IDEs:

  • Claude Desktop - Direct MCP integration

  • Cursor IDE - Built-in MCP support

  • Windsurf (Codeium) - Native MCP protocol

  • VS Code + Cline - Extension-based integration

šŸ“– Complete Setup Guide - Detailed configuration for each IDE

šŸ“‹ Usage Example

"Use basic_auth with username 'admin' and password 'secret123' 
then use auth_bypass_check on https://api.example.com/users 
to test for authentication bypass vulnerabilities"

The AI agent will:

  1. Configure authentication credentials

  2. Test the protected endpoint for bypass vulnerabilities

  3. Provide detailed security analysis and recommendations

šŸ“Š Testing & Validation

# Comprehensive tool testing
npm run test-tools

# Manual interactive testing  
npm run test-interactive

# Quick setup verification
npm run quick-start

# MCP Inspector (GUI)
npm run inspector

šŸ“ Project Structure

CyberMCP/
ā”œā”€ā”€ src/                    # TypeScript source code
│   ā”œā”€ā”€ tools/             # 14 security testing tools
│   ā”œā”€ā”€ resources/         # Security checklists & guides
│   └── utils/             # Authentication & utilities
ā”œā”€ā”€ docs/                  # Documentation
ā”œā”€ā”€ scripts/               # Testing & utility scripts  
ā”œā”€ā”€ examples/              # Configuration examples
ā”œā”€ā”€ dist/                  # Built JavaScript (generated)
└── README.md              # This file

šŸ”§ Development

# Development mode with hot reload
npm run dev

# Build TypeScript
npm run build

# Start server (stdio mode)
npm start

# Start HTTP server
TRANSPORT=http PORT=3000 npm start

šŸ“– Documentation

šŸ¤ Contributing

  1. Fork the repository

  2. Create a feature branch: git checkout -b feature/new-security-tool

  3. Make your changes and add tests

  4. Submit a pull request

šŸ“„ License

This project is licensed under the MIT License - see the LICENSE file for details.

šŸ”— Resources


šŸ”’ Secure your APIs with AI-powered testing!

For support and questions, please create an issue.

Available Tools

14 tools
api_loginD

Inputs: credentials (required), login_url (required), header_name, method, +2 more.

auth_bypass_checkD

Inputs: endpoint (required), auth_header, auth_token, http_method, +1 more.

auth_statusD

Inputs: no named parameters.

basic_authD

Inputs: password (required), username (required).

clear_authD

Inputs: no named parameters.

jwt_vulnerability_checkD

Inputs: jwt_token (required).

oauth2_authD

Inputs: client_id (required), token_url (required), authorization_url, client_secret, +5 more.

path_traversal_checkD

Inputs: endpoint (required), parameter_name (required), http_method, use_auth.

rate_limit_checkD

Inputs: endpoint (required), auth_header, http_method, request_body, +2 more.

security_headers_checkD

Inputs: endpoint (required), http_method, use_auth.

sensitive_data_checkD

Inputs: endpoint (required), http_method, request_body, use_auth.

sql_injection_checkD

Inputs: endpoint (required), original_value (required), parameter_name (required), http_method, +1 more.

token_authD

Inputs: token (required), expires_in, refresh_token, token_type.

xss_checkD

Inputs: endpoint (required), parameter_name (required), http_method, use_auth.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    C2.1/5.0

    Scored across 14 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose focused on specific security testing or authentication functions, with no overlap between authentication methods (e.g., api_login, basic_auth, oauth2_auth) and vulnerability checks (e.g., sql_injection_check, xss_check, path_traversal_check). The tools are well-differentiated by their target areas, making misselection unlikely.

    Naming Consistency4/5

    The naming follows a consistent snake_case pattern throughout, with most tools using clear descriptive names (e.g., sql_injection_check, security_headers_check). However, there are minor deviations like 'auth_bypass_check' versus 'jwt_vulnerability_check' where some use underscores more consistently than others, but overall the pattern is predictable and readable.

    Tool Count5/5

    With 14 tools, the count is well-scoped for a cybersecurity testing server, covering a comprehensive range of authentication methods and common vulnerability checks. Each tool appears to earn its place by addressing a specific aspect of security assessment, avoiding both excessive bloat and insufficient coverage.

    Completeness4/5

    The tool set provides strong coverage for security testing, including authentication (e.g., api_login, basic_auth, token_auth) and vulnerability checks (e.g., sql_injection_check, xss_check). Minor gaps might exist, such as lack of tools for specific advanced attacks or reporting features, but core workflows for authentication and basic security assessments are well-covered without dead ends.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      A Model Context Protocol server that generates and runs mock API servers from API documentation like OpenAPI/Swagger specs, enabling developers and AI assistants to quickly spin up mock backends for development and testing.
      18
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Model Context Protocol server for security research automation, integrating multiple security testing tools into LLM-driven workflows for secret scanning, static analysis, and vulnerability discovery.
      57
      Apache 2.0