powerbi-mcp

A Model Context Protocol (MCP) server that lets AI assistants interact with Microsoft Power BI Desktop and Power BI Service to inspect semantic models, run DAX, test Row-Level Security, and perform safe model/report modifications (notably via PBIP file editing for renames).

Evaluated Mar 30, 2026 (21d ago)
Repo ↗ Ai Ml mcp power-bi dax data-analytics security pii-masking model-refactoring row-level-security pbip
⚙ Agent Friendliness
57
/ 100
Can an agent use this?
🔒 Security
62
/ 100
Is it safe for agents?
⚡ Reliability
38
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
80
Documentation
70
Error Messages
0
Auth Simplicity
60
Rate Limits
10

🔒 Security

TLS Enforcement
70
Auth Strength
70
Scope Granularity
60
Dep. Hygiene
45
Secret Handling
60

Docs claim HTTPS-oriented deployment is implied (MCP over local/command execution not fully specified), include PII detection with masking and configurable access policies, and describe query audit logging with policy violation flags. However, repository-level implementation details (TLS enforcement, secure secret storage, dependency scanning/CVE status) are not provided in the supplied content, so scores are conservative.

⚡ Reliability

Uptime/SLA
0
Version Stability
60
Breaking Changes
40
Error Recovery
50
AF Security Reliability

Best When

You want an MCP-compatible tool that an AI agent can call to explore/query Power BI models and safely apply PBIP-based refactors with PII masking and audit logging.

Avoid When

You need an official, fully managed Microsoft-supported integration, or you plan to use TOM rename operations instead of PBIP tools for changes to report-bound entities.

Use Cases

  • Natural-language querying of Power BI datasets (execute DAX)
  • Listing model metadata (tables/columns/measures) for agent-driven exploration
  • Testing and validating RLS roles during development
  • Bulk renaming of tables/columns/measures in PBIP projects while updating both semantic model and report bindings to avoid broken visuals
  • Security-aware auditing of queries and policy-based masking/blocking of sensitive fields

Not For

  • Using the deprecated TOM-based batch rename tools for renaming (can break report visuals)
  • Serving as a public API for end users without additional deployment/security hardening
  • Providing guarantees about exact Power BI internal compatibility across all PBIP formats/versions beyond what the repo docs claim

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: Azure AD app registration (for cloud connectivity)
OAuth: Yes Scopes: Yes

Docs reference Azure AD App Registration with Dataset.Read.All and Workspace.Read.All for Power BI Service access; Desktop connectivity implies local connection without a described OAuth flow.

Pricing

Free tier: No
Requires CC: No

Open-source (MIT) tooling per repository metadata; pricing not applicable.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • TOM-based rename tools are explicitly deprecated and can break report visuals; use PBIP rename tools for tables/columns/measures.
  • PBIP workflow requires closing Power BI Desktop before editing and reopening afterward.
  • Cloud connectivity requires appropriate Azure AD permissions and XMLA endpoint enablement; failures may occur if prerequisites are missing.
  • PBIP repair/diagnostics tools may be needed if renames were performed outside the PBIP tools.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for powerbi-mcp.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered