
SemanticOps MCP (for Power BI)
io.github.maxanatskoPublished by GitHub account maxanatskov3.9.119Updated Oct 24, 2026
Power BI MCP server (Supports Windows and macOS)
Overview
A local MCP server that lets AI assistants read and modify Power BI Desktop files, querying models, creating measures and managing relationships.
- What you can do
- Query Power BI models and inspect their structure through natural language requests to the assistant, with no tool list published in the manifest, so exact capabilities come from the vendor documentation rather than this entry.
- When to use it
- Useful when you work with Power BI Desktop files and want an assistant to help explore a model, draft measures or adjust relationships without editing everything by hand.
- Requirements
- Runs as a local stdio process installed from the npm package mcp-engine. Needs Windows 10/11 or macOS and an MCP-compatible client such as Claude Desktop, Claude Code CLI or Visual Studio Code. No environment variables or headers are declared.
Installation
In SourceWeft
- Open SemanticOps MCP (for Power BI) in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
SemanticOps
Rollback mistakes. Test before deploy. Control what AI can change.
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
Security
Report vulnerabilities privately to [email protected] or through GitHub private vulnerability reporting. See SECURITY.md.
Author
Built by Maxim Anatsko | Powered by Model Context Protocol
© 2025-2026 Maxim Anatsko. All rights reserved.
Source: README.md at commit 6b3bbda
Tools
0Version history
1- v3.9.119LatestSep 16, 2026
Score
40% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Declare a license in the repository or the registry entry.