Vitra AI Multi-Agent
Multi-agent system built with Google's ADK (Agent Development Kit) that creates a hierarchical customer service architecture for health and wellness retail. The implementation features a root agent that coordinates three specialized sub-agents: a shop attendant for general customer service, a seller for sales transactions, and a health mate for body care advice. Built for Portuguese-speaking markets, it leverages Gemini 2.5 Flash as the primary model and includes an MCP server component for search functionality, making it suitable for e-commerce platforms that need intelligent customer support across multiple domains of expertise.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- ecommerce
- Source
- PulseMCP
- Repository
- github.com/rafegal/multi-agent-lab
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Vitra AI Multi-Agent from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.