Skip to main content

Quickstart

Deploy Tier 1 (Discovery & Registry) and see what AI agents and MCP servers are running in your environment.

Prerequisites​

  • Docker Engine 24+ with Compose v2
  • 2 GB RAM available for containers
  • Port 8443 available
  • GHCR access token (provided by Watchlight AI)

Install​

cd deploy/tier1-discovery/docker-compose
./bootstrap.sh

The bootstrap script will:

  1. Validate prerequisites (Docker 24+, Compose v2)
  2. Collect configuration (domain, version, log level)
  3. Pull container images from GHCR
  4. Generate secrets in memory (never stored on disk)
  5. Start all services
  6. Register the discovery scanner
  7. Export self-signed CA cert (localhost mode)

Access​

URLDescription
https://localhost:8443Registry Dashboard
https://localhost:8443/topologyInteractive Topology Graph
https://localhost:8443/api/v1/serversRegistry API

Connect Your Agents​

Add your containers to the beacon-partner Docker network so wl-discover can find them:

# your-project/docker-compose.yml
services:
  my-agent:
    networks: [default, beacon-partner]

networks:
  beacon-partner:
    external: true

wl-discover scans the beacon-partner network, probes ports for MCP servers, and detects agent frameworks (LangGraph, CrewAI, AutoGen, LangChain).

Self-Register via API​

curl -k -X POST https://localhost:8443/api/v1/agents/register \
  -H 'Content-Type: application/json' \
  -d '{"name": "my-agent", "agent_type": "autonomous", "description": "My research agent"}'

Common Commands​

# View logs
docker compose -f docker-compose/docker-compose.yml logs -f

# Stop (preserves data)
docker compose -f docker-compose/docker-compose.yml down

# Full reset (destroys all data)
./docker-compose/bootstrap.sh --reset

Next Steps​