Numasec

v1.0.0Securitystable

The AI Agent for Cyber Security.

ai-agentai-securityappsecbug-bountycli
Share:
371
Stars
0
Downloads
0
Weekly
0/5

What is Numasec?

Numasec is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to ai agent for cyber security.

The AI Agent for Cyber Security.

This server falls under the Security category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • The AI Agent for Cyber Security.

Use Cases

Cybersecurity agent analysis
App security scanning
Bug bounty assessment
LicenseAGPL-3.0
Languagetypescript
Versionv1.0.0
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx numasec

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Numasec

Numasec is an AI-powered cybersecurity agent available as both a CLI tool and an MCP server, designed for application security testing, bug bounty research, and authorized penetration testing. It wraps a full security operations workflow — including scope management, runbook execution, vulnerability intelligence lookups, evidence capture, and report generation — and can optionally drive local security tools such as nmap, sqlmap, ffuf, gobuster, nikto, nuclei, and trivy when they are installed on the system.

Prerequisites

  • Node.js 18+ or Bun runtime installed
  • An MCP-compatible client such as Claude Desktop, or use via the standalone CLI
  • Optional: Local security tools (nmap, sqlmap, ffuf, gobuster, nikto, nuclei, trivy) for expanded scanning capabilities
  • Only use against systems you own or have explicit written authorization to test
1

Install Numasec globally

Install the Numasec CLI and MCP server globally via npm or Bun. The Docker image is also available if you prefer a containerized environment.

# npm
npm install -g numasec

# Bun
bun add -g numasec

# Docker
docker run -it --rm -v "$PWD:/work" -w /work francescostabile/numasec:latest
2

Run the initial health check

Start the CLI and run the /doctor command to verify which optional security tools are detected on your PATH and confirm the agent is functioning correctly.

numasec
# Then inside the agent:
/doctor
3

Set the operation mode

Choose an operational mode that matches your engagement. The 'appsec' mode configures the agent for web application security testing.

/mode appsec
4

Run a security runbook against a target

Execute a built-in runbook such as 'appsec-web-triage' against a local or authorized target URL. The agent will systematically probe the target and record findings.

/runbook run appsec-web-triage http://localhost:3000
5

Add Numasec as an MCP server

To use Numasec tools from Claude Desktop, add it to your MCP config. This allows Claude to invoke security scanning and reporting tools conversationally.

{
  "mcpServers": {
    "numasec": {
      "command": "npx",
      "args": ["numasec"]
    }
  }
}
6

Generate and share a findings report

After a security assessment, use /share to produce a shareable bundle of your observations, evidence, and findings for stakeholders or bug bounty platforms.

/share

Numasec Examples

Client configuration

MCP config block to register Numasec in Claude Desktop. The agent tools become available for conversational security analysis.

{
  "mcpServers": {
    "numasec": {
      "command": "npx",
      "args": ["numasec"]
    }
  }
}

Prompts to try

Example prompts for web application security testing and vulnerability research workflows.

- "Check what security tools are available in this environment"
- "Run the appsec web triage runbook against http://localhost:3000 and summarize findings"
- "Look up recent CVEs related to the Express.js framework"
- "List all observations captured so far and group them by severity"
- "Generate a penetration test report for today's session and create a sharing bundle"

Troubleshooting Numasec

Optional tools like nmap or sqlmap are not detected by /doctor

Install the missing tools system-wide so they are on your PATH (e.g., `brew install nmap` on macOS or `apt install nmap` on Debian). Re-run /doctor after installing.

Docker image cannot access localhost targets

When running via Docker, use `host.docker.internal` instead of `localhost` for targets running on your host machine, or use `--network host` on Linux.

numasec command not found after global install

Check that your npm global bin directory is on your PATH: run `npm bin -g` and add that directory to your shell's PATH. Alternatively, use `npx numasec` without a global install.

Frequently Asked Questions about Numasec

What is Numasec?

Numasec is a Model Context Protocol (MCP) server that ai agent for cyber security. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Numasec?

Follow the installation instructions on the Numasec GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Numasec?

Numasec works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Numasec free to use?

Yes, Numasec is open source and available under the AGPL-3.0 license. You can use it freely in both personal and commercial projects.

Numasec Alternatives — Similar Security Servers

Looking for alternatives to Numasec? Here are other popular security servers you can use with Claude, Cursor, and VS Code.

Casdoor

13.6k

An open-source Agent-first Identity and Access Management (IAM) /LLM MCP & agent gateway and auth server with web UI supporting OpenClaw, MCP, OAuth, OIDC, SAML, CAS, LDAP, SCIM, WebAuthn, TOTP, MFA, Face ID, Google Workspace, Azure AD

ghidraMCP

9.0k

An Model Context Protocol server that enables LLMs to autonomously reverse engineer applications by exposing Ghidra's decompilation and analysis tools. It allows AI agents to list code structures, rename methods, and analyze binaries directly through

HexStrike AI

8.9k

HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly b

IDA Pro MCP

8.7k

Enables AI-assisted reverse engineering in IDA Pro by providing tools to analyze binaries, decompile functions, manage comments, search patterns, and interact with the IDA database through natural language.

Anthropic Cybersecurity Skills

6.6k

754 structured cybersecurity skills for AI agents · Mapped to 5 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND & NIST AI RMF · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platform

Hooker

5.1k

🔥🔥 hooker is a Frida-based reverse engineering toolkit for Android. It offers a user-friendly CLI, universal scripts, auto hook generation, memory roaming to detect activities/services, one-click SOCKS5 proxy setup, Frida JustTrustMe, and BoringSSL u

Browse More Security MCP Servers

Explore all security servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "numasec": { "command": "npx", "args": ["-y", "numasec"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Numasec?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides