Power BI Modeling MCP

Brings Power BI semantic modeling capabilities to AI agents through a local MCP server. Enables developers and AI applications to interact with Power BI models in new ways—from using natural language to execute modeling changes to autonomous AI agentic development workflows.

What can you do?

• Build and Modify Semantic Models with Natural Language - Create, update, and manage tables, columns, measures, relationships, and more across Power BI Desktop and Fabric semantic models
• Bulk Operations at Scale - Execute batch modeling operations on hundreds of objects simultaneously with transaction support and error handling
• Apply modeling best practices - Easily evaluate and implement modeling best practices against your model
• Agentic Development Workflows - Work with TMDL and Power BI Project files, enabling AI agents to autonomously plan, create, and execute complex modeling tasks
• Query and Validate DAX - Execute and validate DAX queries against your model to test measures, troubleshoot calculations, and explore data

Features

• Connects to Power BI Desktop, Fabric workspaces, or Power BI Project (PBIP) files
• Supports read-only and read-write modes with optional confirmation prompts
• Transaction support for atomic operations
• Comprehensive modeling operations across all Power BI objects
• DAX query execution and performance analysis
• Multi-language support with culture and translation management
• Built-in prompts for common scenarios

Command Line Options

• --start - Starts the MCP server (required)
• --readwrite - Enables write operations with confirmation prompts (default)
• --readonly - Safe mode, prevents any write operations
• --skipconfirmation - Automatically approves operations without prompts
• --compatibility - Set to PowerBI (default) or Full for Analysis Services
• --authmode - Set authentication mode: interactive (default) or serviceprincipal

Important Notes

⚠️ Use caution - Always create a backup before performing operations. LLMs may produce unexpected results.

⚠️ Data Privacy - The server runs locally but sends data to the LLM provider. Review your organization's AI data-handling policies.

⚠️ Security - Uses Azure Identity SDK for authentication. Follow Microsoft security guidance for MCP servers.