NMAP
Perform network scanning and security auditing using the NMAP utility.
MCP NMAP Server
A Model Context Protocol (MCP) server that enables AI assistants to perform network scanning operations using NMAP. This server provides a standardized interface for AI models to interact with NMAP, making it possible to perform network analysis and security assessments through AI conversations.
Prerequisites
- Windows operating system
- Node.js (v18 or higher)
- NMAP installed and accessible from Windows command line
- TypeScript for development
Installation
Installing via Smithery
To install NMAP Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install mcp-nmap-server --client claude
Manual Installation
Install the package globally using npm:
npm install -g mcp-nmap-server
Or install locally in your project:
npm install mcp-nmap-server
Features
The server provides access to NMAP's core functionality through a simple interface. It supports quick scans, full port scans, version detection, and custom timing templates. The implementation uses NMAP's native command-line interface, ensuring reliability and consistency with standard NMAP operations.
Configuration with Claude Desktop
To use this server with Claude Desktop on Windows, you'll need to configure it in the Claude configuration file located at:
C:\Users\YOUR_USERNAME\AppData\Roaming\Claude\config.json
Add the NMAP server to your configuration by adding it to the mcpServers section. Here's a complete example of a Claude Desktop configuration file:
{
"mcpServers": {
"nmap": {
"command": "node",
"args": [
"C:\\Users\\YOUR_USERNAME\\Downloads\\mcp-nmap-server\\dist\\index.js"
]
}
},
"globalShortcut": "Ctrl+Q"
}
Replace YOUR_USERNAME with your Windows username and adjust the path to where you've installed the NMAP server.
Usage with AI
Once configured, AI assistants like Claude can use the server through the run_nmap_scan function. The function accepts the following parameters:
{
target: string; // Host or network to scan
ports?: string; // Optional port specification (e.g., "80,443" or "1-1000")
scanType?: 'quick' | 'full' | 'version'; // Scan type (default: 'quick')
timing?: number; // NMAP timing template 0-5 (default: 3)
additionalFlags?: string; // Optional additional NMAP flags
}
Example conversation with Claude:
Human: Can you scan localhost for open ports?
Claude: I'll help you scan localhost using NMAP.
<runs nmap scan with parameters>
target: "localhost"
scanType: "quick"
timing: 3
License
MIT License
Support
For issues, suggestions, or contributions, please visit the GitHub repository.
संबंधित सर्वर
Alpha Vantage MCP Server
प्रायोजकAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
ConfigCat
interacts with ConfigCat feature flag platform. Supports managing feature flags, configs, environments, products and organizations. Helps to integrate ConfigCat SDK, implement feature flags or remove zombie (stale) flags.
MCP Server Boilerplate
A TypeScript boilerplate for building MCP servers with streamable HTTP and OAuth proxy support.
Gaffer.sh
CI Memory For Agents and Teams
HED MCP Server
An MCP server for Hierarchical Event Descriptors (HED) that automates sidecar creation and annotation for BIDS event files using LLMs.
DINO-X
Advanced computer vision and object detection MCP server powered by Dino-X, enabling AI agents to analyze images, detect objects, identify keypoints, and perform visual understanding tasks.
Flowise
Integrate with the Flowise API to create predictions and manage chatflows and assistants.
Terminal MCP Server
Execute commands on local or remote hosts via SSH. Supports session persistence and environment variables.
Bruno MCP Server
Execute Bruno collections using the Bruno CLI, with support for environment files and detailed test results.
Cloudflare MCP Server Example
An example of deploying a remote MCP server on Cloudflare Workers without authentication.
Fal.ai OpenAI Image
A server for the Fal.ai text-to-image API, powered by OpenAI's image model. Requires Fal.ai and OpenAI API keys.