ruvnet

Agent Name Service — Security skill for Claude Code

Security community

Agent Name Service (ANS) Protocol, introduced by the OWASP GenAI Security Project, is a foundational framework designed to facilitate secure discovery and interaction among AI agents.

How to install Agent Name Service

This entry records only its repository, not the path inside it, so there is no exact command to give. Open ruvnet/Agent-Name-Service and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Agent Name Service does

Agent Name Service (ANS) Protocol, introduced by the OWASP GenAI Security Project, is a foundational framework designed to facilitate secure discovery and interaction among AI agents.

Alternatives in Security

Trail Of Bits Claude-code-config — Opinionated production defaults from a top security firm: sandboxing, permissions, hooks, skills, MCP server c 1.6k ★
Sail Skill — SAIL V2 (Secure AI Lifecycle) as an agent skill — the full 91-risk catalog for AI/agent gap assessments, secur 122 ★
Audit Infra — Infrastructure-first security audit — secrets, supply chain, CI/CD, LLM/skill security, OWASP, STRIDE 98 ★

README

Agent Name Service (ANS)

A secure registry for AI agents based on the [OWASP GenAI Security Project's](https://genai.owasp.org/) Agent Name Service (ANS) Protocol. ANS provides a foundational framework for secure discovery and interaction among AI agents.

Overview

The Agent Name Service is a centralized registry that enables:

Agent Registration: Securely register AI agents with unique identifiers and capabilities
Certificate Management: Issue and validate agent certificates for secure communications
Discovery: Resolve agent information in both A2A and MCP formats
Security Analysis: Integrate with Mastra.ai for threat modeling and security assessment

ANS bridges the gap between different agent communication protocols, allowing seamless interoperability between agents using Google's Agent-to-Agent (A2A) protocol and Anthropic's Model Context Protocol (MCP).

Features

Secure Registration: Register agents with unique names and capabilities with certificate generation
Multi-Protocol Support: Resolve agents in both A2A and MCP protocol formats
Integrated Threat Analysis: Security analysis using Mastra.ai integration
Lightweight Storage: SQLite persistence layer for easy deployment
Modular Architecture: Clean separation of concerns for extensibility

Installation

# Clone the repository
git clone https://github.com/yourusername/agent-name-service.git
cd agent-name-service

# Install dependencies
npm install

Usage

Basic Initialization

import { AgentNamingService } from './src/ans';

// Initialize the ANS service
const ans = new AgentNamingService();

Registering an Agent

// Register an agent
const result = await ans.registerAgent('my-agent', {
  version: '1.0.0',
  capabilities: ['text-generation', 'summarization'],
  description: 'AI assistant for content creation',
  provider: 'OpenAI',
  model: 'gpt-4',
  endpoints: [
    {
      protocol: 'ht