SemanticOps MCP (for Power BI) MCP Server
io.github.maxanatsko/mcp-engine
AI-powered Power BI Desktop editor—query models, create measures, and optimize performance through natural language.
What this kind of tool is for
- Query, inspect, or seed a database without writing a one-off script.
- Let your agent look up schema details before it writes migration code.
- Move a small dataset between tools without leaving the terminal.
How to compare servers like this
- Engine match:
- Confirm it speaks your exact database and version, not just the family.
- Access scope:
- Read-only connections are the safe default — start there before granting writes.
- Safety rails:
- Check whether destructive statements need an explicit confirmation before they run.
- Maintenance signal:
- Database drivers change; a recently updated tool is less likely to break mid-query.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the SemanticOps MCP (for Power BI) MCP server?
SemanticOps MCP is an MCP server that enables AI assistants to read and modify Power BI Desktop files programmatically. It allows you to query your data model, create measures, manage relationships, and optimize performance through natural language commands. The server runs locally on Windows and macOS with zero telemetry.
SemanticOps MCP bridges AI assistants and Power BI Desktop, letting you interact with your BI models conversationally. Instead of manually editing Power BI files, you can ask Claude or other AI to query your model, create or modify measures, adjust relationships, and improve performance—all with the ability to test changes before deploying and rollback mistakes if needed.
How to install SemanticOps MCP (for Power BI)
Copy-paste configuration for popular MCP clients.
{
"mcpServers": {
"mcp-engine": {
"command": "npx",
"args": [
"-y",
"mcp-engine"
]
}
}
}Tools & capabilities
Tools this server exposes to the agent.
Power BI Model Querying— Query and inspect Power BI Desktop data models programmaticallyMeasure Creation— Create and modify DAX measures in Power BI modelsRelationship Management— Manage and configure relationships between tables in Power BIPerformance Optimization— Optimize Power BI model performance through AI-assisted suggestions
Use cases
- Create and refine DAX measures using natural language instructions
- Query your Power BI data model to understand structure and relationships
- Optimize model performance by identifying and fixing inefficiencies
- Test changes to your Power BI file before deploying to production
- Rollback accidental modifications to your Power BI Desktop files
SemanticOps MCP (for Power BI) MCP server FAQ
SemanticOps MCP is an MCP server that lets AI assistants like Claude read and modify Power BI Desktop files. You can query models, create measures, manage relationships, and optimize performance through natural language.
SemanticOps uses a proprietary license that permits both personal and commercial use. Check semanticops.dev/license for full details.
Installation takes under 5 minutes. Visit semanticops.dev/getting-started for step-by-step instructions. The server is available via npm as 'mcp-engine' and works on Windows and macOS.
No. SemanticOps MCP runs entirely locally and collects zero telemetry. All data processing happens on your machine. Your AI assistant provider (e.g., Anthropic) may process your interactions based on their privacy policy.
SemanticOps MCP runs on Windows 10/11 and macOS. It's compatible with Claude Desktop, Claude Code CLI, Visual Studio Code, and any MCP-compatible client.
Yes. SemanticOps lets you test modifications to your Power BI files before deployment and rollback mistakes if needed.
README (reference)
Source of truth, from the repository.
Quick Links
- Full Documentation - Installation, guides, and examples
- Download Latest Release
- Get Support - FAQ and troubleshooting
What It Does
SemanticOps MCP (formerly MCP Engine) is an MCP server that enables AI assistants (Claude, Copilot, ChatGPT) to read and modify Power BI Desktop files programmatically. Query your model, create measures, manage relationships, and optimize performance through natural language.
Learn more at semanticops.dev | View all features
Privacy
This MCP server runs locally and collects zero telemetry. All data processing happens on your machine. Your AI assistant may send data to its provider (e.g., Anthropic, OpenAI) based on your interactions.
Installation
Installation is straightforward and takes under 5 minutes.
Requirements: Windows 10/11, or MacOS platform
Compatible with:
- Claude Desktop (Windows & macOS)
- Claude Code CLI (Windows & macOS)
- Visual Studio Code
- Any MCP-compatible client
License
Proprietary license with permitted personal and commercial use.
View full license | Third-party notices
Author
Built by Maxim Anatsko | Powered by Model Context Protocol
© 2025-2026 Maxim Anatsko. All rights reserved.
Related MCP servers
Determines which NPDES stormwater permit governs a US site and its requirements, cited to source.
Deterministic CMS NCCI/MUE claim scrubbing and CARC/RARC denial explanations, cited to source.
STR legality, permits and lodging tax by city, each field cited to its source jurisdiction.
Medical RAG: semantic search for clinical guidelines, drug interactions, diagnoses & EHR data.
View repository →Sourced Art Blocks artist research, holding-duration data, and current agent bounties from AB5D.
View repository →
AccInt
Local Work Model MCP server for agent work that learns from real outcomes.

![AB[500] research and bounties logo](/api/logo?url=https%3A%2F%2Fgithub.com%2Fmaxand98.png%3Fsize%3D128)