Windows-first DAX and MCP toolkit for Power BI semantic models
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"dax-query-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# dax-query-mcp [](https://pypi.org/project/dax-query-mcp/) MCP server for running DAX queries against Power BI semantic models. Check out [making use of skills and extensions](docs/dax-mcp-skill-and-extension-guide.md) for getting better results since the MCP can't do it all ## Features - **Connection-centric MCP server** — discover models, query with DAX, inspect schemas - **Relationship-aware context** — teach the LLM your model with markdown, structured dictionaries, relationships, and progressive context bundles - **Fuzzy search** — search columns and measures across tables by name or description - **Server-authored follow-ups** — every query response includes a durable next-step workflow for exports, charts, scaffolds, and workstation saves - **Export anywhere** — CSV, clipboard, Power Query M code, Streamlit apps, standalone Python projects - **Query builder** — save `.dax` + `.dax.queryBuilder` artifacts, open directly in DAX Studio - **Workstation session** — save, list, and batch-export queries during an exploration session - **Durable query packs** — turn saved DAX into portable packs with a manifest, batch runner, Streamlit explorer, and Power Query files - **Validated query libraries** — keep connection-scoped, known-good DAX examples that improve future context without creating a full pack ## Prerequisites 1. **uv** — Python package manager. Install with: ```powershell winget install astral-sh.uv ``` 2. **For MSOLAP connections: Windows + MSOLAP provider** — the default transport uses COM/ADODB. Download from [Microsoft](https://learn.microsoft.com/en-us/analysis-services/client-libraries?view=asallproducts-allversions) — grab the **"AMO + ADOMD.NET"** or **"MSOLAP (OLE DB)"** installer. If you already have Power BI Desktop, Excel with Power Pivot, or SSMS installed, you likely have it. To check: open PowerShell and run: ```powershell (New-Object System.Data.OleDb.OleD…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.