🔥 Power BI MCP Servers

Dual Power BI integration for Claude Desktop - Local .pbix analysis + Live Azure API queries

✨ Features

This repository provides two complementary MCP servers for comprehensive Power BI integration:

🏠 Local Analysis Server (pbixray-mcp-server)

• Analyze local .pbix files without cloud connection
• Extract DAX measures, Power Query M code, relationships
• Explore data model structure and table contents
• Perfect for offline analysis and documentation

☁️ Azure Live API Server (powerbi-azure-mcp)

• Query live Power BI datasets via REST API
• Execute DAX queries in real-time
• List workspaces, datasets, and table schemas
• Authenticate with Azure service principal

🚀 Quick Start

Prerequisites

• Claude Desktop installed
• Node.js 18+ and Python 3.8+
• Azure service principal with Power BI permissions (for live API)

Installation

1. Clone this repository:

   git clone https://github.com/anix-lynch/powerbi-mcp-servers.git
   cd powerbi-mcp-servers
   

2. Setup Local Server:

   cd pbixray-mcp-server
   python -m venv venv
   source venv/bin/activate  # Windows: venv\Scripts\activate
   pip install mcp pbixray numpy "mcp[cli]"
   

3. Setup Azure Server:

   cd ../powerbi-azure-mcp
   npm install
   cp .env.example .env
   # Edit .env with your Azure credentials
   

4. Configure Claude Desktop: Add to your MCP configuration:

   {
     "mcpServers": {
       "powerbi-local": {
         "command": "bash",
         "args": ["-c", "source ~/path/to/pbixray-mcp-server/venv/bin/activate && python ~/path/to/pbixray-mcp-server/src/pbixray_server.py --max-rows 100"]
       },
       "powerbi-azure": {
         "command": "node",
         "args": ["/path/to/powerbi-azure-mcp/src/server.mjs"]
       }
     }
   }
   

🎮 Usage Examples

Local File Analysis

"Load this PBIX file: /Users/username/Downloads/sales-report.pbix"
"What tables are in this model?"
"Show me all DAX measures from the Sales table"
"Get the Power Query M code"

Live Azure Queries

"Test my Power BI connection"
"List all my Power BI workspaces"
"Execute this DAX query: EVALUATE Sales"
"Show me table schema for dataset [dataset-id]"

🔧 Configuration

Azure Setup

Create a service principal with these permissions:

• Dataset.Read.All
• Workspace.ReadWrite.All

Environment Variables

AZURE_CLIENT_ID=your-app-id
AZURE_CLIENT_SECRET=your-client-secret  
AZURE_TENANT_ID=your-tenant-id

📁 Project Structure

powerbi-mcp-servers/
├── pbixray-mcp-server/          # Local .pbix analysis
│   ├── src/pbixray_server.py    # Python MCP server
│   ├── demo/                    # Sample files
│   └── requirements.txt
├── powerbi-azure-mcp/           # Live Azure API
│   ├── src/server.mjs           # Node.js MCP server  
│   ├── package.json
│   └── .env.example
└── docs/                        # Documentation

🎯 Available Tools

Local Server Tools

• load_pbix_file - Load Power BI file for analysis
• get_tables - List all tables in the model
• get_dax_measures - Access DAX measures with filtering
• get_power_query - Display M/Power Query code
• get_relationships - Get data model relationships
• get_table_contents - Retrieve table data with pagination

Azure Server Tools

• test_connection - Test Azure authentication
• list_workspaces - List accessible workspaces
• list_datasets - Browse datasets in workspace
• execute_dax_query - Run DAX queries against live data
• get_dataset_tables - Explore table schemas
• get_dataset_info - Get dataset metadata

🤝 Contributing

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Credits

• PBIXRay - Power BI file analysis library
• Model Context Protocol - MCP specification
• Microsoft Power BI REST API

---

Built with ❤️ for the Claude + Power BI community