mcp-engine-public MCP — Anwendungsfälle, Installieren & Live-Demo

Warum nutzen

Hauptfunktionen

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

Live-Demo

In der Praxis

engine-public.replay ▶ bereit

0/0

Installieren

Wählen Sie Ihren Client

~/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
    }
  }
}

Öffne Claude Desktop → Settings → Developer → Edit Config. Nach dem Speichern neu starten.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor nutzt das gleiche mcpServers-Schema wie Claude Desktop. Projektkonfiguration schlägt die globale.

VS Code → Cline → MCP Servers → Edit

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

Klicken Sie auf das MCP-Servers-Symbol in der Cline-Seitenleiste, dann "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Gleiche Struktur wie Claude Desktop. Windsurf neu starten zum Übernehmen.

~/.continue/config.json

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

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json

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

In context_servers hinzufügen. Zed lädt beim Speichern neu.

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

Einzeiler. Prüfen mit claude mcp list. Entfernen mit claude mcp remove.

Anwendungsfälle

Praxisnahe Nutzung: mcp-engine-public

Write DAX without memorizing syntax

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

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

Voraussetzungen

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

Ablauf

Orient the model

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

→ 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.✓ Kopiert

→ DAX + creation confirmation
Validate

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

→ Numbers that look right

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

Fallstricke

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

Wann einsetzen: The original author is gone and the model has 40 tables of mystery.

Ablauf

Dump structure

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

→ 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.✓ Kopiert

→ Human-readable model doc

Ergebnis: Useful documentation without reading every measure yourself.

Kombinieren mit: filesystem

Refactor measures to follow naming + modeling conventions

👤 Teams standardizing Power BI practices ⏱ ~30 min intermediate

Wann einsetzen: Measures are named inconsistently (e.g. 'Total Sales' vs 'SumSales').

Ablauf

Find violations

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

→ Violation list
Rename safely

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

→ Rename plan with dependencies

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

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

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.✓ Kopiert

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.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

Werkzeug	Eingaben	Wann aufrufen	Kosten
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)

Kosten & Limits

Was der Betrieb kostet

API-Kontingent: None — local only
Tokens pro Aufruf: Model dumps can be large; focus queries
Kosten in €: Proprietary license with permitted personal + commercial use (see mcpengine.dev/license)
Tipp: Ask for specific tables rather than a full model dump on complex reports.

Sicherheit

Rechte, Secrets, Reichweite

Credential-Speicherung: None required — uses PBI Desktop's session

Datenabfluss: 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.

Fehlerbehebung

Häufige Fehler und Lösungen

No Power BI instance found

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

Prüfen: 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.

Prüfen: get_model_structure

Changes don't persist after closing PBI

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

Prüfen: Title bar shows no asterisk

Alternativen

mcp-engine-public vs. andere

Alternative	Wann stattdessen	Kompromiss
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

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen