Tools Index

This section describes each MCP tool from a user perspective (what to ask the LLM, when to use it, common pitfalls).

How users interact with tools

End users typically do not call tools directly. You describe your goal in natural language, and the LLM chooses which tools to use.

This wiki focuses on:

  • what each tool enables,
  • what to ask the LLM,
  • what to expect in locked-down environments.

Modes and availability (high level)

Tools may appear or disappear depending on how your organization runs the server:

  • Full: all tools available (subject to license).
  • Read-only: write-capable authoring tools are hidden/blocked; read/execute tools remain.
  • Browse-only: only discovery + schema browsing tools are exposed.

If a page describes a capability you don’t see, ask:

“Am I in full/read-only/browse-only mode? Which tools are available here?”

For a deeper “where does this work?” reference:

Quick “who gets what” table

Use the matrices (and interactive explorer) to answer “can I do X here?” quickly:

Semantic model coverage

MCP Engine can query and manage all Power BI semantic model object types:

15 Queryable Object Types

Full semantic model coverage
Measures
DAX calculations & aggregations
KPIs
Key performance indicators
Calculation Groups
Reusable calculation logic
UDFs
User-defined functions
Tables
Data tables & fact tables
Columns
Fields & calculated columns
Partitions
M/SQL/DAX/Entity partitions
Relationships
Table connections & cardinality
Hierarchies
Drill-down structures
RLS Roles
Row-level security filters
OLS Roles
Object-level security
Perspectives
Filtered model views
Cultures
40+ regional formats
Translations
Multi-language labels
VertiPaq Stats
Compression & memory analysis

Core tools (most users)

Model authoring (when writes are allowed)

Governance and lifecycle

Pro / Enterprise tools (if enabled)