mcp-engine-public MCP — Сценарии использования, Установка & Живое демо

Зачем использовать

Ключевые функции

Reads Power BI tabular model structure (tables, columns, measures, relationships)
Runs DAX queries against the open model
Creates and modifies DAX measures
Manages relationships between tables
Local-only execution — no data leaves the machine

Живое демо

Как выглядит на практике

engine-public.replay ▶ готово

0/0

Установка

Выберите клиент

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "engine-public": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/maxanatsko/mcp-engine-public"
      ],
      "_inferred": true
    }
  }
}

Откройте Claude Desktop → Settings → Developer → Edit Config. Перезапустите после сохранения.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "engine-public": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/maxanatsko/mcp-engine-public"
      ],
      "_inferred": true
    }
  }
}

Cursor использует ту же схему mcpServers, что и Claude Desktop. Конфиг проекта приоритетнее глобального.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "engine-public": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/maxanatsko/mcp-engine-public"
      ],
      "_inferred": true
    }
  }
}

Щёлкните значок MCP Servers на боковой панели Cline, затем "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "engine-public": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/maxanatsko/mcp-engine-public"
      ],
      "_inferred": true
    }
  }
}

Тот же формат, что и Claude Desktop. Перезапустите Windsurf для применения.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "engine-public",
      "command": "TODO",
      "args": [
        "See README: https://github.com/maxanatsko/mcp-engine-public"
      ]
    }
  ]
}

Continue использует массив объектов серверов, а не map.

~/.config/zed/settings.json

{
  "context_servers": {
    "engine-public": {
      "command": {
        "path": "TODO",
        "args": [
          "See README: https://github.com/maxanatsko/mcp-engine-public"
        ]
      }
    }
  }
}

Добавьте в context_servers. Zed перезагружается автоматически.

claude mcp add engine-public -- TODO 'See README: https://github.com/maxanatsko/mcp-engine-public'

Однострочная команда. Проверить: claude mcp list. Удалить: claude mcp remove.

Сценарии использования

Реальные сценарии: mcp-engine-public

Write DAX without memorizing syntax

👤 Power BI analysts new to DAX ⏱ ~15 min intermediate

Когда использовать: You know what you want in English; you don't want to debug CALCULATE for an hour.

Предварительные требования

Power BI Desktop with a model open — Launch Power BI Desktop and open your .pbix
MCP Engine installed and connected — See mcpengine.dev — installer under 5 min

Поток

Orient the model

List the tables in the open model and key measures.✓ Скопировано

→ Model map
Write the measure

Create a DAX measure 'YoY Revenue' that returns current revenue minus same period prior year, using Date[Date] for time intelligence.✓ Скопировано

→ DAX + creation confirmation
Validate

Run the measure over 2024 vs 2025 and spot-check 3 rows.✓ Скопировано

→ Numbers that look right

Итог: A working measure with validation, not a guess.

Подводные камни

Time intelligence requires a properly marked date table — Verify Date table is marked as a date table first
Model calculations differ between DirectQuery and Import — Be aware of your storage mode; DirectQuery imposes DAX restrictions

Auto-document an existing Power BI model

👤 Analysts inheriting a .pbix ⏱ ~25 min beginner

Когда использовать: The original author is gone and the model has 40 tables of mystery.

Поток

Dump structure

Dump the model: every table's role, every measure's DAX, every relationship.✓ Скопировано

→ Full structural listing
Write prose docs

Write a one-page explanation of this model for a new analyst: what it reports on, main tables, key measures.✓ Скопировано

→ Human-readable model doc

Итог: Useful documentation without reading every measure yourself.

Сочетать с: filesystem

Refactor measures to follow naming + modeling conventions

👤 Teams standardizing Power BI practices ⏱ ~30 min intermediate

Когда использовать: Measures are named inconsistently (e.g. 'Total Sales' vs 'SumSales').

Поток

Find violations

List measures that don't follow the naming convention '<Verb> <Subject> [<Modifier>]'.✓ Скопировано

→ Violation list
Rename safely

Propose renames; list any visuals or calculated tables that reference each old name.✓ Скопировано

→ Rename plan with dependencies

Итог: A consistent measure catalog with broken references caught before you hit Apply.

Комбинации

Сочетайте с другими MCP — эффект x10

engine-public + filesystem

Export model documentation as a Markdown file alongside the .pbix

Document the model and save as ~/Docs/PBI/sales-model.md next to sales.pbix.✓ Скопировано

engine-public + postgres

Cross-check PBI measures against raw Postgres queries

PBI says Q1 revenue is $4.2M. Run the same query on the source Postgres DB and tell me if there's a discrepancy.✓ Скопировано

Инструменты

Что предоставляет этот MCP

Инструмент	Входные данные	Когда вызывать	Стоимость
get_model_structure	(none)	Session start	free (local)
run_dax	query: str	Ad-hoc DAX query	free (local)
create_measure	table, name, expression	Add new measure	free (write)
update_measure	table, name, expression	Modify existing	free (write)
manage_relationship	from_table, from_col, to_table, to_col, action: create\|delete\|update	Schema changes	free (write)

Стоимость и лимиты

Во что обходится

Квота API: None — local only
Токенов на вызов: Model dumps can be large; focus queries
Деньги: Proprietary license with permitted personal + commercial use (see mcpengine.dev/license)
Совет: Ask for specific tables rather than a full model dump on complex reports.

Безопасность

Права, секреты, радиус поражения

Хранение учётных данных: None required — uses PBI Desktop's session

Исходящий трафик: Zero telemetry claimed; all local to PBI Desktop

Proprietary license — review terms at mcpengine.dev/license before enterprise use.
Changes write directly to the open model — save your .pbix before risky refactors.

Устранение неполадок

Частые ошибки и исправления

No Power BI instance found

Ensure Power BI Desktop is running with a report open; the MCP connects to the local port it exposes.

Проверить: Check Task Manager for msmdsrv process

DAX error: Column not found

Table/column reference is case-sensitive and must match exactly. Use the model structure dump to get names right.

Проверить: get_model_structure

Changes don't persist after closing PBI

PBI Desktop doesn't auto-save — Ctrl+S after each batch of changes.

Проверить: Title bar shows no asterisk

Альтернативы

mcp-engine-public в сравнении

Альтернатива	Когда использовать	Компромисс
Tabular Editor 3 (scripting)	You want a full scripting environment for PBI/SSAS models	Paid; no MCP surface
DAX Studio	You only need a DAX query tool	No write operations; no AI layer

Ещё

Ресурсы

📖 Читать официальный README на GitHub

🐙 Открытые задачи

🔍 Все 400+ MCP-серверов и Skills