Our Work
Custom MCP

Query your custom products from Claude.

We connected an internal application to Claude through MCP, an open protocol that lets Claude talk to external systems. Users ask in plain words. Claude answers with the data.

System

Internal

Protocol

MCP

Interface

Claude

Claude
Claude
Happy Friday, Valentina
Show me billable hour by person for August.
Chat
Cowork
Fable 5 High
Billable hours by person · August
108 hs
Jane Doe
152 hs
John Smith
78 hs
Richard Roe
174 hs
Alex Johnson
124 hs
Sam Taylor
59 hs
Mary Major
Situation

You don’t need to build AI into your custom product

Scenario

Your legacy systems already contain the data your team needs. The challenge is making that data available to AI without adding a chatbot or building a new interface into each application.

Opportunity

MCP lets us connect the system directly to Claude without changing the original application. Generative UI takes it a step further, letting Claude present each answer in the format that best fits the question: text, a table, a chart, or another visual.

Experiment

Query your system directly from Claude

We tested this with KZHoras, our internal system for tracking project hours and time off.

We built an MCP server that gives Claude access to its data, with permissions defining what each user can see. Users query KZHoras from a conversation, in Claude, without another AI interface.

Internal system

Internal system

Keeps its own interface, database and users.

MCP server

MCP server

Exposes only the data and functions we decide.

Claude

Claude

Where the question is asked and the answer is built.

How it works

From a question to your system data

01

The user asks Claude

They use natural language without needing to know how KZHoras is structured.

02

Claude calls KZHoras through the MCP server

The server receives the request and calls the KZHoras API.

03

Claude builds the answer

Claude queries KZHoras and answers in the format that fits the question: text, a table, a chart, or an interactive visualization you can click into.

Demo

See it working

A query, from the question in Claude to the answer built with KZHoras data.

The stack
Claude

Claude · AI interface

Where the question is asked and the answer is built.

Custom MCP Server

Custom MCP Server · Protocol layer

Exposes only the data and functions we decide.

KZHoras API

KZHoras API · Internal system

The system of record for project hours and time off.

Dokploy

Dokploy · Hosting

Runs the MCP Server.

Benefits

What this makes possible

Keep using the systems you already have

No need to rebuild the application or create a new AI interface.

Ask without knowing the system

Users query data in natural language instead of learning reports, filters, or internal structures.

Connect your system data to AI

Claude becomes another way to access the existing system.

Match the answer to the question

Results can come back as text, a table, a chart, or an interactive visualization.

Want your users to query your system from Claude?

Start a conversation
Dark background with subtle diagonal light beams fading toward top right corner.
llms.txt