Skip to content

LAD-A2A Logo

Local Agent Discovery for A2A

An open protocol for discovering A2A-capable agents on local networks.


The Problem

When a device joins a network—hotel Wi-Fi, office LAN, cruise ship, hospital campus—how does the user's AI assistant discover and connect to local agents?

  • A2A defines agent-to-agent communication
  • MCP defines agent-to-tool integration
  • LAD-A2A defines agent discovery

The Solution

LAD-A2A provides:

  • Zero-Configuration Discovery via mDNS/DNS-SD, well-known endpoints, or DHCP
  • Defense in Depth with TLS, signed AgentCards, DIDs, and user consent
  • Graceful Degradation from consumer Wi-Fi to enterprise networks
  • Ecosystem Alignment that hands off to standard A2A once discovery completes

How It Fits

Protocol Stack

Protocol Role
LAD-A2A Discovery & Trust Bootstrap
A2A Agent-to-Agent Communication
MCP Agent-to-Tools/Data

LAD-A2A is the first handshake. It answers "who's here?" so that A2A can answer "what can you do?"

See It In Action

Real mDNS discovery → LAD-A2A protocol → A2A JSON-RPC communication

Quick Start

Experience LAD-A2A with a fully working demo featuring two AI agents:

cd demo
cp .env.example .env
# Add your OpenAI API key to .env
./run_demo.sh

Open http://localhost:8000 to see:

  • Real mDNS discovery (_a2a._tcp.local)
  • LAD-A2A protocol in action
  • A2A JSON-RPC 2.0 communication
  • LLM-based query routing

Run Locally

cd reference
pip install -e .

# Start a discovery server (development only)
python -m server.lad_server --name "My Agent" --port 8080

# Discover agents
python -m client.lad_client --url http://localhost:8080

TLS Required in Production

The example above uses HTTP for local development only. In production, all endpoints MUST use TLS 1.2+ per the security requirements.

Use Cases

Environment Example
Hotels "What's the spa schedule?"
Cruise Ships "Where's tonight's show?"
Offices "Book conference room 4B"
Hospitals "Navigate to radiology"
Stadiums "Find my seat"
Smart Cities "Next bus to downtown?"

Next Steps