CyberSecurity s
Model Context Protocol Server For Cyber Security
claude mcp add --transport stdio secmate-ai-cybersecurity-mcps node /path/to/implementations/sqlmap-mcp/build/index.js
How to use
This MCP server collection focuses on cybersecurity-related model context servers. Each server is implemented as its own MCP with capabilities ranging from vulnerability and threat intelligence to cryptography, password analysis, and document processing. You can run individual servers or integrate them into Claude Desktop or your MCP orchestration layer by configuring mcpServers with the appropriate command, arguments, and any required environment variables. For example, sqlmap-mcp provides automated SQL injection testing for target URLs, threat-intel-mcp aggregates multiple threat intelligence sources (VirusTotal, AbuseIPDB, Shodan), and cve-lookup-mcp queries the NVD database for CVEs and related data. Other servers offer encryption tools, hash analysis, SSL/TLS checks, document conversion, and intelligent password analysis. Each server exposes its own API endpoints via the built index.js, so you can orchestrate cross-tool workflows, feed outputs between servers, and automate security assessments.
How to install
Prerequisites:
- Node.js (recommended LTS) and npm installed on your system
- Git to clone or pull the repository
Step-by-step installation:
-
Clone the repository or download the source: git clone <repository-url> cd <repository-root>
-
Install dependencies for all MCP implementations: npm install
-
Build each MCP server (per the project’s standard workflow): npm run build
-
Start or register the MCP servers in your environment:
- If using Claude Desktop or a central MCP orchestrator, ensure your config references the built entry points (build/index.js) for each server as shown in the mcp_config example.
- If you want to run a single server locally, navigate to the specific implementation and start it, for example: node implementations/sqlmap-mcp/build/index.js
-
Validate the setup:
- Use your MCP inspector or the server’s health endpoints to verify readiness.
- Ensure any required API keys (VirusTotal, AbuseIPDB, Shodan, NVD) are provided via environment variables as shown in the configuration.
Additional notes
Tips and common issues:
- Make sure to build all implementations before pointing your config to their build/index.js files.
- For API keys, keep them secure and do not commit them to version control. Use environment variables or secret managers.
- If a server fails to start due to missing environment variables, provide placeholders or empty strings in the env section and then supply real values in a secure runtime environment.
- The CLI or inspector tooling can help debug inter-server workflows; use npm run inspector to launch the MCP Inspector UI.
- Different servers may require additional runtime resources (e.g., network access for threat intel sources, or large hash databases); ensure your environment permits outbound connections as needed.
Related MCP Servers
mcp-security-hub
A growing collection of MCP servers bringing offensive security tools to AI assistants. Nmap, Ghidra, Nuclei, SQLMap, Hashcat and more.
frontmcp
TypeScript-first framework for the Model Context Protocol (MCP). You write clean, typed code; FrontMCP handles the protocol, transport, DI, session/auth, and execution flow.
shinzo-ts
TypeScript SDK for MCP server observability, built on OpenTelemetry. Gain insight into agent usage patterns, contextualize tool calls, and analyze server performance across platforms. Integrate with any OpenTelemetry ingest service including the Shinzo platform.
mcp -js
MCP server that exposes YepCode processes as callable tools for AI platforms. Securely connect AI assistants to your YepCode workflows, APIs, and automations.
openai -agent-dotnet
Sample to create an AI Agent using OpenAI models with any MCP server running on Azure Container Apps
mcp-bun
Bun Javascript Runtime MCP Server for AI Agents