PBIXRay MCP Server V2

PBIXRay MCP Server V2

Enables Claude AI to analyze Power BI Desktop models with comprehensive capabilities including DAX analysis, performance monitoring with Storage Engine/Formula Engine breakdown, VertiPaq statistics, and natural language querying of model structure and data.

Category
访问服务器

README

PBIXRay MCP Server V2 - Enhanced Edition

Version: 2.0 Enhanced
Status: Production Ready Last Updated: 2025-10-04

What is This?

The PBIXRay MCP Server V2 is a Model Context Protocol (MCP) server that enables Claude AI to analyze Power BI Desktop models with advanced performance analysis capabilities including Storage Engine (SE) and Formula Engine (FE) breakdown.

Key Features

  • Auto-detect Power BI Desktop instances
  • Full Model Exploration - Tables, columns, measures, relationships
  • DAX Analysis - Measures, calculated columns, with expressions
  • Power Query (M) - View data source configurations
  • Performance Analysis - Advanced SE/FE timing with SessionTrace
  • VertiPaq Stats - Storage and compression metrics
  • Search Capabilities - Find objects and text across the model
  • Natural Language - Ask Claude questions about your model

System Requirements

  • OS: Windows 10/11 (64-bit)
  • .NET Framework: 4.7.2+ (usually pre-installed)
  • Power BI Desktop: Latest version recommended
  • Claude Desktop: Latest version
  • Disk Space: ~200 MB

Quick Start

1. Extract the Package

Extract the entire folder to your preferred location, for example:

C:\Tools\pbixray-mcp-server

2. Verify Installation (Optional)

cd C:\Tools\pbixray-mcp-server
.\scripts\test_connection.ps1

3. Configure Claude Desktop

.\scripts\install_to_claude.ps1

This will automatically configure Claude Desktop for you.

4. Restart Claude Desktop

  • Fully close Claude Desktop (check Task Manager)
  • Reopen Claude Desktop

5. Test It!

  1. Open Power BI Desktop with a .pbix file
  2. In Claude, say: "Detect my Power BI Desktop instances"
  3. Say: "Connect to instance 0"
  4. Say: "What tables are in this model?"

You are now analyzing Power BI with Claude AI!

Documentation

  • Quick Reference - docs/QUICK_REFERENCE.md - Command cheat sheet
  • FAQ - docs/FAQ.md - Frequently asked questions
  • Troubleshooting - docs/TROUBLESHOOTING.md - Common issues
  • Deployment Guide - docs/DEPLOYMENT_GUIDE.md - Team deployment

Available Tools

Key tools available:

  • detect_powerbi_desktop - Find running Power BI instances
  • connect_to_powerbi - Connect to a specific instance
  • list_tables - List all tables in the model
  • list_measures - List DAX measures
  • describe_table - Get detailed table information
  • run_dax_query - Execute DAX queries
  • analyze_query_performance - SE/FE performance analysis
  • get_vertipaq_stats - Storage and compression metrics
  • search_objects - Find tables, columns, measures
  • export_model_schema - Export complete model structure

Folder Structure

pbixray-mcp-server/
├── venv/              # Python environment (portable)
├── src/               # Server source code
├── lib/dotnet/        # Analysis Services DLLs
├── docs/              # Documentation
├── scripts/           # Helper scripts
├── config/            # Configuration templates
├── logs/              # Auto-generated logs
└── requirements.txt   # Python dependencies

Example Usage

You: "Analyze the performance of this DAX query"

Claude: [Runs analyze_query_performance with 3 runs]

Results:
- Total: 245ms
- Storage Engine: 189ms (77%)
- Formula Engine: 56ms (23%)
- SE Queries: 12

The query is SE-heavy, indicating most time is spent 
retrieving data. Consider adding filters to reduce 
the amount of data scanned.

Maintenance

Update Python Packages

.\venv\Scripts\pip.exe install --upgrade -r requirements.txt

Verify Health

.\verify_installation.ps1 -Verbose

For Team Distribution

To package for colleagues:

.\scripts\package_for_distribution.ps1

This creates a ready-to-share ZIP file on your Desktop.

Troubleshooting

No instances detected?

  • Ensure Power BI Desktop is running
  • Open a .pbix file (not just Power BI)
  • Wait 10-15 seconds after opening

Connection fails?

  • Verify instance index (usually 0)
  • Restart Power BI Desktop
  • Check docs/TROUBLESHOOTING.md

Claude does not see the server?

  • Run: .\scripts\install_to_claude.ps1
  • Restart Claude Desktop completely
  • Check JSON syntax in config

Credits

Built with:

  • MCP SDK - Model Context Protocol
  • Python.NET - CLR integration
  • Analysis Services Client Libraries - Microsoft
  • Power BI Desktop - Microsoft

Version History

  • V2.0 Enhanced (Oct 2025) - SessionTrace integration, improved SE/FE analysis
  • V2.0 (Oct 2025) - WMI-based detection, stability improvements
  • V1.0 (Sep 2025) - Initial release

Privacy and Security

  • All processing is local - No data sent to external servers
  • Localhost only - Binds to 127.0.0.1
  • No network exposure - Completely offline capable
  • Claude conversations - May be stored by Anthropic (review their policy)

Happy Analyzing!

For questions or issues, see the FAQ or Troubleshooting Guide in the docs folder.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选