MCP and AI agents

02 What I built

• 01

  MCP tool servers

  A tool server next to each business service (MCP is the standard way to give an AI tools). Every change shows a preview and needs a confirm, and many changes can be undone exactly.

• 02

  Agent service

  One AI service runs admin chat, support replies, AI search and the AI page builder, with a measured limit on how much text each tool sends to the AI.

• 03

  Public AI gateway

  Lets customers connect their own AI assistant to their own data, with OAuth sign-in. The gateway sets the identity and never trusts the caller, and checks block the call when in doubt.

• 04

  Prompt-injection guard

  Text from users, emails or web pages is cleaned and marked as untrusted before the AI reads it, and a detector catches hidden changes in tool results.

• 05

  Tool tests in CI

  Each tool server has a contract with a hash, so an unplanned change breaks the build, and AI eval tests run on every code change. One server was redesigned to a much smaller tool set and became the pattern for the rest.

• 06

  AI search for shoppers

  A shopper types a normal sentence, the AI only names the needs, and code turns them into filters with fixed tables, so the same words always give the same results.

• 07

  Support desk AI

  Connects the support desk to the AI agent with a confirm before it acts, checks incoming message signatures safely, and puts each new support email into the right ticket.

• 08

  AI usage billing

  Charges for AI use by holding credits first and then charging or giving them back, and blocks AI calls if billing is down.

03 How it works

1. 01Staff ask for a change in plain words, in chat.
2. 02The AI picks a tool from the right business service.
3. 03The tool shows a preview of the change first.
4. 04A person confirms, and only then is the change saved.
5. 05Many changes can be undone in one step.