Skip to content
Anton GoncharovAI systems developer
RUEN

Go service · MCP · tools

Zerno MCP server

An agent is not given direct access to the database. It is given tools with clear arguments: look up stock, see where an order is, write down a lead. This server speaks the Model Context Protocol. The screen shows the request and the response as the agent sees them.

Scenario: Zerno, a fictional roastery: the same coffees and orders as the purchasing agent.

Demo screenshot: Zerno MCP server

Open the demo

Open the app

The tools read the demo database of the Go service. No model is called.

The app runs in your browser: nothing is sent to a server.

What the demo shows

  • JSON-RPC: a handshake, the tool list and a call

  • stock_lookup — green-coffee stock, all of it or one origin

  • order_status — order status by number

  • create_lead — a lead with a name, a phone and a coffee; a short phone number is refused

  • Tool descriptions in Russian or English, following the page language

How to try it

  1. Open the list

    “Tool list” shows three tools and the argument schema.

  2. Ask for stock

    “Stock” — the reply has kilograms for three origins.

  3. Find an order

    “Order З-1042” — the order is on its way along Kuibysheva Street.

  4. Leave a lead

    A name and a phone, “Create a lead”. “Empty phone” is refused by the tool.

No paid neural networks

No model is called: the demo shows the protocol and the tools. The data is the same PostgreSQL as the gateway and the purchasing agent.

The demo runs without OpenAI, YandexGPT or GigaChat API keys. Wherever a production system calls a model, there’s a local stub with the same interface — so the demo is free, always available and never makes things up.

What a production project adds

  • The same server is connected to an agent in Cursor, Claude or your own runtime
  • Tools talk to MoySklad, 1C and a CRM, rather than to demo tables
  • Each agent has its own access: reading stock is allowed, creating a lead depends on the role
  • A call journal next to the gateway, so you can see what the agent asked and what the database answered

Stack

  • Go
  • MCP
  • JSON-RPC
  • pgx
  • sqlc
  • PostgreSQL
  • React 19

Want the same for your business?

Tell me about your task — I’ll tell you what from the demo fits, how long it will take and what I’ll need from you.

Message me on TelegramSend a request

Other demos in this section

All demos

  • Web app · OCR · validating company details

    live

    Document recognition

    Upload an invoice or a certificate of completion — a photo, scan or PDF. The app recognizes the text, extracts company details and table rows and validates them: tax ID and account checksums, the total and VAT.

    • React
    • TypeScript
    • In-browser neural network

  • Web app · conversations · deals · analytics

    live

    Operator panel

    The workspace of an operator who receives difficult requests from a bot: a queue with a timer, a conversation summary, a reply draft, deals on a kanban board and analytics — on a live stream of customers.

    • React
    • TypeScript

  • Web app · Recharts · RBAC · audit

    live

    SaaS dashboard

    A SaaS revenue team’s workspace: MRR by plan, revenue movement, churn, customer health, CSV export for Excel and an activity log. All numbers are calculated from a single year of history — changing a plan in a customer card moves MRR on the charts immediately.

    • React
    • TypeScript

  • Web app · Laravel · PostgreSQL

    live

    Warehouse system on Laravel

    Warehouse accounting where stock is the sum of ledger entries, not a “qty--” field: orders with all-or-nothing reservation, picking by bin, receiving with CSV import, stocktaking and a ledger. A race between two real PHP processes in PostgreSQL shows why row locking is needed.

    • PHP

  • Web app · metrics · alerts

    live

    Bot monitoring

    How a bot is watched in production: how many requests, how fast it answers, how often it fails or doesn’t know the answer. A request log with a trace of every answer and rules that message the on-call engineer in Telegram when something goes wrong.

    • React
    • TypeScript

  • Go service · limits · journal

    live

    Model gateway

    One OpenAI-compatible entrance for the roastery’s bots: each has its own key, a per-minute cap and a daily token budget. Replaying the same key does not charge the budget again, and a failure of the primary model falls through to the backup.

    • Go
    • React
    • TypeScript

  • Go service · queue · approval

    live

    Purchasing agent

    A supplier request moves in steps through a queue: check stock, build a draft, wait for a person, and only then send. A cut-off send returns to the queue and does not create a second order.

    • Go
    • React
    • TypeScript

  • Python scraper · runs in the browser

    live

    Competitor price monitoring

    A Python scraper crawls the websites of three competitors of an electronics store every day: an HTML catalog with pagination, a sitemap with JSON-LD and an SPA with an API. It matches products with the catalog, sends notifications about changes, recommends a price by rules and exports a report to Excel. Python runs right in the browser.

    • Python
    • React
    • TypeScript

  • Web app · PWA · vanilla JS

    live

    Offline courier app

    A courier’s working day: orders, a call to the customer, handover with a photo and signature. The app opens and works without a network, and changes go to dispatch when the connection returns. If the dispatcher changed the same order in the meantime, the courier chooses which version is right.

    • Vanilla JS