ENKO
Talk to us

Engineering the foundationsof trusted AI.

BLUEURBAN develops AI engines that connect business data to queries, guide text generation, publish structured knowledge and link document decisions to evidence.

Explore our technology

AI results your business can use

ENTERPRISE MCP

Enterprise data, available to AI.

QueryMind / Claude

What BLUEURBAN brings to the conversation.

QueryMind returns the query result and its conditions. Claude selects the tool and composes the answer.

QueryMind workspace
A separate foundation demo: student enrollment is queried in a Korean-language workspace. The result, generated SQL and evidence can be inspected.
QueryMind MCP in Claude
A separate ERP demo: compare sales-order totals across periods using an approved query tool. This is the MCP conversation shown alongside the workspace.
QueryMind workspace · separate foundation demo (Korean UI)

QueryMind workspace · separate foundation demo (Korean UI)

ClaudeQueryMind MCP
Actual QueryMind MCP calls and answers in Claude, with the greeting and interface notices edited for presentation.

Demonstration sequence

  1. Question

    A business question is entered in the AI client.

  2. Tool call

    Claude calls BLUEURBAN’s QueryMind MCP tool.

  3. Result & conditions

    The answer includes the result and the conditions used.

  4. Request & response

    The tool’s arguments and response JSON can be inspected.

Separate demos are shown together. Greeting and interface notices are edited for presentation; query, tool calls and answers are preserved. Synthetic ERP data. Waiting segments were omitted; duration is not response time.

Explore the MCP technology

For AI to work in a business,
it needs to understand the business.

A data connection is only the beginning. The meaning of revenue, the scope of access, and the source of an answer matter too. BLUEURBAN builds these conditions into software engines.

Explore the architecture
DatabasesBusiness documentsBusiness rules
MEANING · CONTROL · EVIDENCE

Data, knowledge and tools
that AI can use

Business meaning

Connect company terminology and metrics to explicit data definitions.

Execution control

Apply validation, access checks and read-only boundaries along the query path.

Inspectable evidence

Keep queries, returned results and the sources behind answers connected.

Turn enterprise queries
into tools AI can call.

Built on QueryMind’s semantic interpretation, SQL validation and read-only execution.

Explore MCP technologyVisit QueryMind

MCP, the Model Context Protocol, connects AI to external tools. BLUEURBAN develops technology that validates enterprise query definitions, fixes their scope, and publishes them as reusable tools for authenticated AI clients.

DEFINE

Define a business query

Specify the inputs and query structure, then compile and check the definition. Accepted definitions become the basis for publication.

PUBLISH

Publish an approved scope

Freeze the definition selected by an administrator and expose it within tenant context. Retain the definition, timestamp and exclusion reasons.

CALL

Check each call and result

Run the parameterized query through the read-only path, applying access checks, result limits and masking to the response.

BLUEURBAN’s QueryMind returns the query result and conditions. Claude selects the tool and composes the answer.

Beyond a single interface.
A foundation for different work.

Different business questions call on related technology. These application contexts are drawn from product and training materials.

MANUFACTURING & OPERATIONS

Ask business questions
of operational data.

Connect business terms and metrics, then aggregate with SQL inside the permitted scope.

Natural-language data access
EDUCATION & ADMINISTRATION

Inspect the result.
Understand its basis.

For questions such as enrollment by academic year, expose the generated SQL and supporting result context.

Answers linked to evidence
KNOWLEDGE & CONTENT

Make documents and facts
usable as AI evidence.

Publish approved information in structured formats and develop generation and reasoning engines that work with context and evidence.

Explore the technology areas

Application examples, not customer adoption claims or performance measurements.

Understand the thinking
behind the technology.

All engineering posts
Engineering · November 9, 2026

The model proposes, the system decides: the design and operating method four engines share

Text-to-SQL, controlled generation, knowledge publishing, document reasoning: why four engines in different fields stand on the same three rules, and how those rules are kept in code and operations.

Text-to-SQL · November 9, 2026

Before a question becomes SQL: a Text-to-SQL engine built on semantic contracts and AST validation, and the QueryMind deployments it runs

The hard part of turning language into SQL is not generation but meaning and boundaries. Injecting metric contracts into the syntax tree, rejecting forbidden nodes before execution, running read-only — the design and five months in the field.

MCP publishing · November 9, 2026

Publishing approved queries as MCP tools: QueryMind Connect, which never regenerates SQL per call

The most dangerous way to open enterprise data to an AI client is to let the model write SQL on every call. Here only administrator-frozen definitions become tools, every call runs under argument, permission and output limits — and a real call recorded on November 8, 2026.

Core technology.
Put into practice.

BLUEURBAN develops software for data access, controlled generation, knowledge publishing and document reasoning. QueryMind, TextMind, FactMind and Jupgo are implementations of these technologies in different domains.

Meet the company
Business opened
SEP 2023
Based in
Dongtan, South Korea
Business
AI software development

Build the foundation
for AI in your business.

Talk to us about technology adoption, business partnerships, investment and strategic collaboration.

Contact BLUEURBAN