/ 디렉터리 / 플레이그라운드 / mcp-engine-public
● 커뮤니티 maxanatsko ⚡ 바로 사용

mcp-engine-public

제작: maxanatsko · maxanatsko/mcp-engine-public

Chat with your Power BI model — read schema, run DAX, create measures, manage relationships — all locally, no cloud round-trip.

MCP Engine (mcp-engine-public) by Maxim Anatsko connects to a local Power BI Desktop instance. Read model structure, run DAX queries, create and modify measures, and manage relationships via natural language. Runs locally (Windows/macOS) with zero telemetry.

왜 쓰나요

핵심 기능

라이브 데모

실제 사용 모습

engine-public.replay ▶ 준비됨
0/0

설치

클라이언트 선택

~/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
    }
  }
}

Claude Desktop → Settings → Developer → Edit Config 열기. 저장 후 앱 재시작.

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

Cursor는 Claude Desktop과 동일한 mcpServers 스키마 사용. 프로젝트 설정이 전역보다 우선.

VS Code → Cline → MCP Servers → Edit
{
  "mcpServers": {
    "engine-public": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/maxanatsko/mcp-engine-public"
      ],
      "_inferred": true
    }
  }
}

Cline 사이드바의 MCP Servers 아이콘 클릭 후 "Edit Configuration" 선택.

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

Claude Desktop과 같은 형식. Windsurf 재시작 후 적용.

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

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

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

context_servers에 추가. 저장 시 Zed가 핫 리로드.

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

한 줄 명령. claude mcp list로 확인, claude mcp remove로 제거.

사용 사례

실전 활용법: mcp-engine-public

Write DAX without memorizing syntax

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

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

사전 조건
  • 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
흐름
  1. Orient the model
    List the tables in the open model and key measures.✓ 복사됨
    → Model map
  2. Write the measure
    Create a DAX measure 'YoY Revenue' that returns current revenue minus same period prior year, using Date[Date] for time intelligence.✓ 복사됨
    → DAX + creation confirmation
  3. Validate
    Run the measure over 2024 vs 2025 and spot-check 3 rows.✓ 복사됨
    → Numbers that look right

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

함정
  • 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

언제 쓸까: The original author is gone and the model has 40 tables of mystery.

흐름
  1. Dump structure
    Dump the model: every table's role, every measure's DAX, every relationship.✓ 복사됨
    → Full structural listing
  2. Write prose docs
    Write a one-page explanation of this model for a new analyst: what it reports on, main tables, key measures.✓ 복사됨
    → Human-readable model doc

결과: Useful documentation without reading every measure yourself.

함께 쓰기: filesystem

Refactor measures to follow naming + modeling conventions

👤 Teams standardizing Power BI practices ⏱ ~30 min intermediate

언제 쓸까: Measures are named inconsistently (e.g. 'Total Sales' vs 'SumSales').

흐름
  1. Find violations
    List measures that don't follow the naming convention '<Verb> <Subject> [<Modifier>]'.✓ 복사됨
    → Violation list
  2. Rename safely
    Propose renames; list any visuals or calculated tables that reference each old name.✓ 복사됨
    → Rename plan with dependencies

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

조합

다른 MCP와 조합해 10배 효율

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.✓ 복사됨
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.✓ 복사됨

도구

이 MCP가 노출하는 것

도구입력언제 호출비용
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)

비용 및 제한

운영 비용

API 쿼터
None — local only
호출당 토큰
Model dumps can be large; focus queries
금액
Proprietary license with permitted personal + commercial use (see mcpengine.dev/license)
Ask for specific tables rather than a full model dump on complex reports.

보안

권한, 시크릿, 파급범위

자격 증명 저장: None required — uses PBI Desktop's session
데이터 외부 송신: Zero telemetry claimed; all local to PBI Desktop

문제 해결

자주 발생하는 오류와 해결

No Power BI instance found

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

확인: 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.

확인: get_model_structure
Changes don't persist after closing PBI

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

확인: Title bar shows no asterisk

대안

mcp-engine-public 다른 것과 비교

대안언제 쓰나단점/장점
Tabular Editor 3 (scripting)You want a full scripting environment for PBI/SSAS modelsPaid; no MCP surface
DAX StudioYou only need a DAX query toolNo write operations; no AI layer

더 보기

리소스

📖 GitHub에서 공식 README 읽기

🐙 열린 이슈 보기

🔍 400+ MCP 서버 및 Skills 전체 보기