Power BI CLI - semantic models (.NET TOM) and PBIR reports for token-efficient AI agent usage, built for Claude Code
Find a file
2026-03-26 15:15:44 +02:00
.github/workflows fix: CI workflow triggers on master branch, not main 2026-03-26 14:40:24 +02:00
assets style: redesign header SVG with 3D block pixel art in Power BI yellow 2026-03-26 15:15:44 +02:00
src/pbi_cli style: apply ruff format to all source and test files 2026-03-26 14:55:44 +02:00
tests style: apply ruff format to all source and test files 2026-03-26 14:55:44 +02:00
.gitignore feat: initial pbi-cli project with all 20+ command groups 2026-03-26 13:05:53 +02:00
CHANGELOG.md feat: add REPL mode, test suite, CI/CD, and Claude Skills (Sprints 6-8) 2026-03-26 13:54:24 +02:00
CONTRIBUTING.md docs: add CONTRIBUTING.md and SECURITY.md for GitHub repo tabs 2026-03-26 14:52:55 +02:00
LICENSE feat: initial pbi-cli project with all 20+ command groups 2026-03-26 13:05:53 +02:00
pyproject.toml chore: bump version to 0.2.0 for release 2026-03-26 14:59:18 +02:00
README.md fix: CI workflow triggers on master branch, not main 2026-03-26 14:40:24 +02:00
SECURITY.md docs: add CONTRIBUTING.md and SECURITY.md for GitHub repo tabs 2026-03-26 14:52:55 +02:00

pbi-cli

Give Claude Code the Power BI skills it needs.
Install once, then just ask Claude to work with your semantic models.

PyPI Python CI License

Get StartedSkillsAll CommandsREPL ModeContributing


What is this?

pbi-cli gives Claude Code (and other AI agents) the ability to manage Power BI semantic models. It ships with 5 skills that Claude discovers automatically. You ask in plain English, Claude uses the right pbi commands.

graph LR
    A["<b>You</b><br/>'Add a YTD measure<br/>to the Sales table'"] --> B["<b>Claude Code</b><br/>Uses Power BI skills"]
    B --> C["<b>pbi-cli</b>"]
    C --> D["<b>Power BI</b><br/>Desktop / Fabric"]

    style A fill:#1a1a2e,stroke:#f2c811,color:#fff
    style B fill:#16213e,stroke:#4cc9f0,color:#fff
    style C fill:#0f3460,stroke:#7b61ff,color:#fff
    style D fill:#1a1a2e,stroke:#f2c811,color:#fff

Get Started

pip install pbi-cli-tool        # 1. Install
pbi setup                       # 2. Download the MCP binary
pbi skills install              # 3. Give Claude the Power BI skills
pbi connect -d localhost:54321  # 4. Connect to your model

That's it. Open Claude Code and start asking.

Requires: Python 3.10+ and Power BI Desktop (local) or a Fabric workspace (cloud).


Skills

After running pbi skills install, Claude Code discovers 5 Power BI skills. Each skill teaches Claude a different area of Power BI development. You don't need to memorize commands. Just describe what you want.

graph TD
    YOU["You: 'Set up RLS for<br/>regional managers'"] --> CC["Claude Code"]
    CC --> SK{"Picks the<br/>right skill"}
    SK --> S1["Modeling"]
    SK --> S2["DAX"]
    SK --> S3["Deployment"]
    SK --> S4["Security"]
    SK --> S5["Documentation"]

    style YOU fill:#1a1a2e,stroke:#f2c811,color:#fff
    style CC fill:#16213e,stroke:#4cc9f0,color:#fff
    style SK fill:#0f3460,stroke:#7b61ff,color:#fff
    style S1 fill:#1a1a2e,stroke:#f2c811,color:#fff
    style S2 fill:#1a1a2e,stroke:#4cc9f0,color:#fff
    style S3 fill:#1a1a2e,stroke:#7b61ff,color:#fff
    style S4 fill:#1a1a2e,stroke:#06d6a0,color:#fff
    style S5 fill:#1a1a2e,stroke:#ff6b6b,color:#fff

Modeling

"Create a star schema with Sales, Products, and Calendar tables"

Claude creates the tables, sets up relationships, marks the date table, and adds formatted measures. Covers tables, columns, measures, relationships, hierarchies, and calculation groups.

Example: what Claude runs behind the scenes
pbi table create Sales --mode Import
pbi table create Products --mode Import
pbi table create Calendar --mode Import
pbi relationship create --from-table Sales --from-column ProductKey --to-table Products --to-column ProductKey
pbi relationship create --from-table Sales --from-column DateKey --to-table Calendar --to-column DateKey
pbi table mark-date Calendar --date-column Date
pbi measure create "Total Revenue" -e "SUM(Sales[Revenue])" -t Sales --format-string "$#,##0"

DAX

"What are the top 10 products by revenue this year?"

Claude writes and executes DAX queries, validates syntax, and creates measures with time intelligence patterns like YTD, previous year, and rolling averages.

Example: what Claude runs behind the scenes
pbi dax execute "
EVALUATE
TOPN(
    10,
    ADDCOLUMNS(VALUES(Products[Name]), \"Revenue\", CALCULATE(SUM(Sales[Amount]))),
    [Revenue], DESC
)
"

Deployment

"Export the model to Git and deploy it to the Staging workspace"

Claude exports your model as TMDL files for version control, then imports them into another environment. Handles transactions for safe multi-step changes.

Example: what Claude runs behind the scenes
pbi database export-tmdl ./model/
# ... you commit to git ...
pbi connect-fabric --workspace "Staging" --model "Sales Model"
pbi database import-tmdl ./model/
pbi model refresh --type Full

Security

"Set up row-level security so regional managers only see their region"

Claude creates RLS roles with descriptions, sets up perspectives for different user groups, and exports role definitions for version control.

Example: what Claude runs behind the scenes
pbi security-role create "Regional Manager" --description "Users see only their region's data"
pbi perspective create "Executive Dashboard"
pbi perspective create "Regional Detail"
pbi security-role export-tmdl "Regional Manager"

Documentation

"Document everything in this model"

Claude catalogs every table, measure, column, and relationship. Generates data dictionaries, measure inventories, and can export the full model as TMDL for human-readable reference.

Example: what Claude runs behind the scenes
pbi --json model get
pbi --json model stats
pbi --json table list
pbi --json measure list
pbi --json relationship list
pbi database export-tmdl ./model-docs/

All Commands

22 command groups covering every Power BI MCP server operation. You rarely need these directly when using Claude Code, but they're available for scripting, CI/CD, or manual use.

Category Commands
Queries dax execute, dax validate, dax clear-cache
Model table, column, measure, relationship, hierarchy, calc-group
Deploy database export-tmdl, database import-tmdl, database export-tmsl, model refresh, transaction
Security security-role, perspective
Connect connect, connect-fabric, disconnect, connections list
Other partition, expression, calendar, trace, advanced, model get, model stats
Tools setup, repl, skills install, skills list

Use --json for machine-readable output (for scripts and AI agents):

pbi --json measure list
pbi --json dax execute "EVALUATE Sales"

Run pbi <command> --help for full options.


REPL Mode

For interactive work, the REPL keeps the MCP server running between commands (skipping the ~2-3s startup each time):

$ pbi repl

pbi> connect --data-source localhost:54321
Connected: localhost-54321

pbi(localhost-54321)> measure list
pbi(localhost-54321)> dax execute "EVALUATE TOPN(5, Sales)"
pbi(localhost-54321)> exit

Tab completion, command history, and a dynamic prompt showing your active connection.


How It Works

pbi-cli wraps Microsoft's official Power BI MCP server binary behind a CLI. The binary is downloaded automatically by pbi setup from the VS Code Marketplace.

graph TB
    subgraph CLI["pbi-cli"]
        A["CLI commands"] --> B["MCP client"]
    end
    B -->|"stdio"| C["Power BI MCP Server<br/>.NET binary"]
    C -->|"XMLA"| D["Power BI Desktop<br/>or Fabric"]

    style CLI fill:#16213e,stroke:#4cc9f0,color:#fff
    style C fill:#0f3460,stroke:#7b61ff,color:#fff
    style D fill:#1a1a2e,stroke:#f2c811,color:#fff

Why a CLI wrapper? When an AI agent uses an MCP server directly, the tool schemas consume ~4,000+ tokens per tool in the context window. A pbi command costs ~30 tokens. Same capabilities, 100x less context.

Configuration details

All config lives in ~/.pbi-cli/:

~/.pbi-cli/
  config.json          # Binary version, path, args
  connections.json     # Named connections
  repl_history         # REPL command history
  bin/{version}/       # MCP server binary

Binary resolution order:

  1. $PBI_MCP_BINARY env var (explicit override)
  2. ~/.pbi-cli/bin/ (managed by pbi setup)
  3. VS Code extension fallback

Development

git clone https://github.com/MinaSaad1/pbi-cli.git
cd pbi-cli
pip install -e ".[dev]"
ruff check src/ tests/         # Lint
mypy src/                      # Type check
pytest -m "not e2e"            # Run 120 tests

Contributing

Contributions are welcome! Please open an issue first to discuss what you'd like to change.

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes with tests
  4. Open a pull request

GitHub PyPI

MIT License