Charles Rossi

MCP & AI-agent developer · live production MCP platform · open to a first role

An early-career developer running a live production MCP platform — listed on Glama, with 2 fixes merged into Mastra (26k★ TS AI-agent framework: #19604, #19610). My proof of work is Velora: a multi-agent platform whose 61-tool MCP server Claude, ChatGPT and Gemini operate to run a real business. Bilingual EN/ES · Traductor Público + Técnico en Programación.

See the work ↓ GitHub ↗

Available · Remote · US/EU friendly · USD

Case study · live in production

Velora — where Claude, ChatGPT & Gemini run a real business

A chat-first, multi-agent commerce platform for businesses in Argentina. It exposes a production MCP server with 61 tools covering the full commerce cycle — and any MCP client can operate a real business through it, with HMAC-authenticated, multi-tenant access. This is the actual product, live.

somosvelora.com
Velora's product: Claude, ChatGPT and Gemini each operating the same business over MCP — selling, reading the live catalog with prices and stock, and generating a payment link.
The same MCP server, three clients. Claude sells and sends a MercadoPago link; ChatGPT reads the live catalog; Gemini queries sales — all over the open MCP standard, against one real business.
somosvelora.com
Velora landing page: a chat-first commerce assistant answering a customer about catalog stock in real time.
Chat-first surface — the assistant answers a customer about catalog & stock in real time.
Velora on mobile: the same chat-first commerce assistant, responsive on a phone.
Mobile — same surface, responsive.

61 tools, 14 packs

Fiscal invoicing (AFIP/ARCA), MercadoPago payments and payment links, logistics (sandbox), catalog, sales, cash register, and WhatsApp messaging via the Meta Cloud API.

Multi-agent over A2A

A supervisor + specialized sub-agents communicating over the A2A protocol, with signed agent identities (Ed25519), orchestrated with Google ADK and Gemini.

Built for production

Next.js / TypeScript on Cloud Run with Postgres. Idempotent money-path mutations, per-tenant isolation, webhook signature verification, async task queues.

Open the live product ↗ See the 61 tools live ↗ velora-mcp on GitHub ↗

Also shipped

Public, verifiable pieces of the same stack — each one live and callable by any MCP client, not a slide.

velora-mcp

Production

The Argentine commerce MCP server behind Velora: real AFIP/ARCA invoicing (live CAE), MercadoPago, logistics (sandbox), catalog and WhatsApp — 61 tools across 14 packs behind one HMAC-authenticated, multi-tenant endpoint.

GitHub ↗ tools.somosvelora.com ↗ Listed on Glama ↗

Public MCP endpoint

Live · no auth

tools.somosvelora.com/api/mcp/public — 9 pure Argentine fiscal tools (CUIT/CUIL/CBU validation, AFIP QR, IVA split, ARS parsing) that any AI agent can call with no key, no account, no install.

tools.somosvelora.com ↗

latam-tools

MCP registry

The pure, no-auth fiscal tools published as a standalone MCP server manifest — registered so any MCP-compatible client can discover and connect over Streamable HTTP.

GitHub ↗

Veripóliza

Live demo

An insurance certificate-of-coverage PDF verification engine: it reads certificate PDFs and returns structured, validated JSON — policy number, coverage dates, and each insured person's name and DNI — built to replace the manual retyping of certificate fields between two APIs. A Gemini model-consensus pipeline on Google Cloud Run (scale-to-zero). The live demo extracts 5/5 insured correctly from a real Sancor Seguros certificate.

Demo temporarily offline for maintenance

nanoclaw

Built · code public

A security-focused Microsoft Teams agent over Outlook: mention @nanoclaw in a chat and it reads your mail and calendar, drafts emails, and creates events — with a fail-closed allow-list, a write-confirmation gate on every send, and an untrusted-data envelope around tool results. A Claude tool-use loop on the Microsoft 365 Agents SDK, using the olk Outlook CLI, with secrets in GCP Secret Manager on Cloud Run. Code is public; not yet deployed to a live Teams tenant.

GitHub ↗

velora-track3

Google AI Agents Challenge

The multi-agent orchestration layer: a Supervisor plus 8 A2A sub-agents (Ed25519-signed) on Google ADK, Vertex AI and Cloud Run — Velora's entry in Google's international AI agent competition.

GitHub ↗ All repos ↗

Stack & skills

The tools behind the work — from protocol design to deployment.

Agents & protocols

Model Context Protocol (MCP) AI Agents Tool / Function Calling Multi-Agent Systems A2A Protocol Google ADK Claude API Gemini API

Build & platform

TypeScript Next.js Node.js Google Cloud Run PostgreSQL API Integration Webhooks

Integrations shipped

WhatsApp Business (Meta Cloud API) MercadoPago payments AFIP / ARCA invoicing Logistics / shipping (sandbox)

How I work

Production-grade, not demos Auth & rate limiting Multi-tenant isolation Idempotent money paths Fluent English US time-zone friendly

Background

Formal training, background, and the proof-of-work behind the build.

Education

University Technical Degree in Programming — 2-year program.

Sworn Certified Translator of English — Universidad del Aconcagua, Mendoza (2003–2008). English at a professional, near-native level.

Proof of work

Velora (personal project) · 2024–2026. Designed, built, and operated a multi-agent commerce platform end to end: product, code, deploys, and incident response on Google Cloud. Not a job — a proof of work.

Open BSP — Remote (US) · 2023–2025 · Entry-level — wrote and tested prompts for production AI agents.

No professional software development experience yet. Seeking my first role. The work speaks for itself.

Recognition

Velora was entered in Google's international AI agent competition (2026), built on Google ADK, the A2A protocol, Gemini, and Cloud Run.

How I build

Claude Code as a first-class workflow: specification, generation, rigorous review, and testing. It's how one developer shipped and operates a 61-tool production MCP platform. I direct; the AI executes.

Get in touch

Seeking my first developer role & open to collaborations

If you're working on MCP servers, AI agents, or production systems and want an early-career developer who has shipped them for real — paid trial or junior rate — I'd be glad to talk.

Book a call GitHub ↗

Available · Remote · US/EU · USD