MCP server for creating, reading, writing, and evaluating Power BI .pbix/.pbit files — no Power BI Desktop required
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":"pbix-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.
# pbix-mcp [](https://github.com/d0nk3yhm/pbix-mcp/actions/workflows/ci.yml) [](https://pypi.org/project/pbix-mcp/) [](https://pypi.org/project/pbix-mcp/) [](https://www.python.org/downloads/) [](https://opensource.org/licenses/MIT) An MCP server for **creating**, reading, writing, and evaluating Power BI `.pbix` and `.pbit` files — **no Power BI Desktop required**. The PBIX binary format is independently reimplemented in pure Python — every structure pbix-mcp's supported capabilities require, with no templates, skeletons, or Microsoft binaries. Generated files open in PBI Desktop with full interactivity: view data, add measures, create visuals, and refresh — verified with PBI Desktop March 2026. The DAX engine has **verified parity with Power BI Desktop on 100% of the DAX surface Desktop can evaluate in a query** — all 435 query-evaluable of the engine's 467 functions (the other 32 are proven not query-evaluable by Desktop itself, so there is nothing to match). Two proof layers: per-function goldens captured from Desktop's own workspace engine (359 value probes, 1e-9 tolerance) and a full-corpus 1:1 match — **432/432** grand totals, **1,705/1,705** measure×dimension filter-context cells, **397/397** calculated columns (v0.9.63; latest sweep 534/534 comparable measures across the corpus). Exposes 133 tools covering report creation (all 6 data types, cross-table relationships, CSV/SQLite/SQL Server/MySQL/PostgreSQL/Excel/JSON/Azure SQL data sources, DirectQuery, and DAX measures), layout editing (rename / reorder / hide / duplicate pages, move & copy visuals — identically on classic `Report/Layout` and service-authored **PBIR**), visual management, bookmarks, cust…
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.