pbi-desktop-mcp-public and powerbi-mcp

These are competitors offering overlapping functionality—both enable AI assistants to interact with Power BI models through MCP, though the first provides lower-level programmatic access (DAX queries, measure management) while the second focuses on natural language abstraction over datasets.

pbi-desktop-mcp-public
58
Established
powerbi-mcp
51
Established
Maintenance 13/25
Adoption 10/25
Maturity 13/25
Community 22/25
Maintenance 6/25
Adoption 9/25
Maturity 15/25
Community 21/25
Stars: 206
Forks: 61
Downloads:
Commits (30d): 0
Language:
License:
Stars: 102
Forks: 44
Downloads:
Commits (30d): 0
Language: Python
License: MIT
No Package No Dependents
No Package No Dependents

About pbi-desktop-mcp-public

maxanatsko/pbi-desktop-mcp-public

The MCP Engine is a Power BI tool that lets AI assistants like Claude interact with your Power BI models programmatically: read your model structure, run DAX queries, create and modify measures, manage relationships, and perform advanced analytics - all through natural conversation.

Implements the Model Context Protocol (MCP) server standard, enabling seamless integration with Claude Desktop, VS Code, and other MCP-compatible clients through stdio transport. Features built-in rollback capabilities and dry-run testing to prevent unintended model changes, with all processing occurring locally—zero telemetry, no cloud data transmission. Supports Windows and macOS platforms, maintaining full compatibility with Power BI Desktop's native file format for direct model manipulation.

About powerbi-mcp

sulaiman013/powerbi-mcp

MCP server for natural language interaction with Power BI datasets

Implements dual connectivity to both Power BI Desktop (via TOM) and Power BI Service (via XMLA endpoints), exposing 34 tools for semantic model querying, DAX execution, and bulk refactoring. Solves the critical challenge of renaming tables without breaking report visuals through PBIP file-based editing—directly manipulating TMDL definitions and JSON report bindings rather than relying on TOM, which can't update the report layer.

Scores updated daily from GitHub, PyPI, and npm data. How scores work