What is powerbi-analyst-mcp CLAUDE.md?

Coding instructions for a server that connects an AI agent to Microsoft Power BI, a tool for business reports and data analysis.

Use them when adding or removing Power BI tools, changing versions, building the installable bundle, or running its tests.

They keep the server's tools, package manifest, versions, and build output consistent, while noting where credentials must be protected.

How mbrummerstedt/powerbi-analyst-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to mbrummerstedt/powerbi-analyst-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/mbrummerstedt/powerbi-analyst-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/mbrummerstedt/powerbi-analyst-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/mbrummerstedt/powerbi-analyst-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/mbrummerstedt/powerbi-analyst-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/mbrummerstedt/powerbi-analyst-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/mbrummerstedt/powerbi-analyst-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/mbrummerstedt/powerbi-analyst-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/mbrummerstedt/powerbi-analyst-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 625 This file is loaded in full into every session.

When invoked 625 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00625	$0.00625
Opus 5	$0.00313	$0.00313
Sonnet 5	$0.00125	$0.00125
Haiku 4.5	$0.00063	$0.00063

Measured 10d ago against content hash 52e5b7d7170d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

powerbi-analyst-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Power BI Analyst MCP Server

Architecture

powerbi_mcp/ — the MCP server package (auth, client, tools, models, output, history)
bundle/ — mcpb bundle config (manifest.json, pyproject.toml, build.sh)
dist/ — built .mcpb bundle output
tests/ — pytest suite (unit + integration)

Bundle Rules

Every tool registered in powerbi_mcp/tools.py must also be listed in bundle/manifest.json tools array. The build script (bundle/build.sh) enforces this — it will fail if they're out of sync.

When adding or removing a tool:

Add/remove the @mcp.tool() function in tools.py
Add/remove the entry in bundle/manifest.json tools array
Run bash bundle/build.sh — it validates the match before building

Version Bumping

Version lives in two places — keep them in sync:

bundle/manifest.json → "version": "X.Y.Z"
bundle/pyproject.toml → version = "X.Y.Z"

Building the Bundle

bash bundle/build.sh

Output: dist/miinto-powerbi-analyst.mcpb

Security — Bundle and Manifest Contain Secrets

bundle/manifest.json and dist/*.mcpb contain baked-in org credentials (POWERBI_CLIENT_ID, POWERBI_TENANT_ID). Both are in .gitignore for this reason.

NEVER:

git add -f bundle/manifest.json or git add -f dist/
Attach the .mcpb file to a GitHub release
Publish the bundle anywhere public

The bundle is for internal distribution only — share it directly with users, not via public URLs or release assets.

Running Tests

uv run --extra dev python -m pytest tests/ -x -q

Integration tests (tagged integration) require a live Power BI token and are skipped by default.

Dataset Discovery

All tools use in-group (/groups/) API endpoints. The correct discovery flow is:

list_apps → workspaceId → list_datasets(workspace_id) → dataset_id → execute_dax / list_tables / etc.

The list_workspaces tool has been removed. It caused permission errors in app-managed orgs because dataset access is granted through Power BI apps, not direct workspace membership. The workspace_id for all tool calls must come from list_apps (the workspaceId field), never from workspace enumeration.

Read the full file on GitHub · 65 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

10d ago First seen · 65 lines · 625 tokens per session scan A 52e5b7d7170d

Subscribe to this mod's changes

powerbi-analyst-mcp CLAUDE.md is an instructions file published in the GitHub repository mbrummerstedt/powerbi-analyst-mcp (14 stars, last pushed 4mo ago), licensed MIT. It adds 625 tokens to every session, about $0.0031 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Analytics and metrics

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

powerbi-analyst-mcp: Instructions file for Claude Code