Skip to main content
Glama

Power BI PBIR MCP

Local MCP server for editing Power BI Project reports saved in PBIR format. It uses only the Python standard library and talks MCP over stdio.

Install

From GitHub:

pipx install git+https://github.com/bobzhou-source/powerbi-pbir-mcp.git
codex mcp add powerbi-pbir-report-mcp -- powerbi-pbir-mcp

From a local clone:

git clone https://github.com/bobzhou-source/powerbi-pbir-mcp.git
cd powerbi-pbir-mcp
python -m pip install -e .
codex mcp add powerbi-pbir-report-mcp -- powerbi-pbir-mcp

Restart Codex, then run /mcp.

Related MCP server: Power BI Report MCP Server

What It Does

  • Load .pbip, .pbir, .Report, or definition folders.

  • Scaffold Desktop-stable PBIP/PBIR projects.

  • Read semantic model tables, columns, measures, and source hints.

  • Batch page, visual, theme, and layout changes with pbir_apply_plan.

  • Validate JSON shape, bindings, layout bounds, and common Desktop blockers.

Workflow

PBIR MCP workflow

Example Prompt

Load C:\Reports\Supplier Dashboard.Report, summarize the pages and visuals,
then add an Executive Summary page with KPI cards and a supplier trend chart.
Use pbir_apply_plan and validate after edits.

Benchmark

Benchmark summary

Development

python -m unittest discover -s tests
python -m pbir_mcp_server

Publishing notes are in docs/PUBLISHING.md.

A
license - permissive license
-
quality - not tested
C
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/bobzhou-source/powerbi-pbir-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server