Power BI Authoring MCP Server (Local)
Gives Claude direct access to Power BI semantic models through the Tabular Object Model, letting you modify tables, columns, measures, and relationships using natural language. Works against Power BI Desktop files, Fabric workspaces, or TMDL project files on disk. You can bulk rename hundreds of objects, refactor DAX measures, apply best practice rules, or execute queries for validation. Ships as both an npm package and a VS Code extension that hooks into GitHub Copilot. Microsoft built this for agentic workflows where an LLM needs to autonomously plan and execute modeling changes across your entire BI layer. Still in public preview, so expect the API to shift before GA.
- GitHub stars
- 1.3K
- tools
- 21
- transport
- STDIO
- last updated
- Nov 6, 2026
Tools
21 toolsPublic tool metadata for what this MCP can expose to an agent.
connection_operationsConnect to Power BI Desktop or Fabric workspaces
Connect to Power BI Desktop or Fabric workspaces
No parameter schema in public metadata yet.
database_operationsManage semantic models - connect, create, update, list databases, import/export TMDL folders, deploy to Fabric
Manage semantic models - connect, create, update, list databases, import/export TMDL folders, deploy to Fabric
No parameter schema in public metadata yet.
transaction_operationsControl database transactions (begin, commit, rollback, get status)
Control database transactions (begin, commit, rollback, get status)
No parameter schema in public metadata yet.
model_operationsWork with the overall model (get, create, update, refresh, get stats, rename)
Work with the overall model (get, create, update, refresh, get stats, rename)
No parameter schema in public metadata yet.
table_operationsManage tables (create, update, delete, get, list, refresh, rename)
Manage tables (create, update, delete, get, list, refresh, rename)
No parameter schema in public metadata yet.
column_operationsManage individual table columns (create, update, delete, get, list, rename)
Manage individual table columns (create, update, delete, get, list, rename)
No parameter schema in public metadata yet.
measure_operationsManage individual DAX measures (create, update, delete, get, list, rename, move between tables)
Manage individual DAX measures (create, update, delete, get, list, rename, move between tables)
No parameter schema in public metadata yet.
relationship_operationsHandle relationships between tables (create, update, delete, activate/deactivate, find)
Handle relationships between tables (create, update, delete, activate/deactivate, find)
No parameter schema in public metadata yet.
dax_query_operationsExecute and validate DAX queries against the model
Execute and validate DAX queries against the model
No parameter schema in public metadata yet.
trace_operationsPerform trace operations on semantic model to capture and analyze Analysis Services events.
Perform trace operations on semantic model to capture and analyze Analysis Services events.
No parameter schema in public metadata yet.
partition_operationsManage table partitions (create, update, delete, refresh specific partitions)
Manage table partitions (create, update, delete, refresh specific partitions)
No parameter schema in public metadata yet.
user_hierarchy_operationsWork with user-defined hierarchies (create, update, delete levels, reorder)
Work with user-defined hierarchies (create, update, delete levels, reorder)
No parameter schema in public metadata yet.
calculation_group_operationsManage calculation groups and calculation items for time intelligence and other calculations
Manage calculation groups and calculation items for time intelligence and other calculations
No parameter schema in public metadata yet.
security_role_operationsConfigure security roles and row-level security (RLS) table permissions
Configure security roles and row-level security (RLS) table permissions
No parameter schema in public metadata yet.
perspective_operationsManage perspectives and their members (filtered views of the model for different audiences)
Manage perspectives and their members (filtered views of the model for different audiences)
No parameter schema in public metadata yet.
named_expression_operationsWork with named expressions and Power Query parameters (create, update, delete, get, list, rename)
Work with named expressions and Power Query parameters (create, update, delete, get, list, rename)
No parameter schema in public metadata yet.
function_operationsManage individual DAX user-defined functions
Manage individual DAX user-defined functions
No parameter schema in public metadata yet.
culture_operationsManage cultures for multi-language support (create, update, delete, get valid culture names)
Manage cultures for multi-language support (create, update, delete, get valid culture names)
No parameter schema in public metadata yet.
object_translation_operationsHandle translations for model objects across different cultures/languages
Handle translations for model objects across different cultures/languages
No parameter schema in public metadata yet.
calendar_operationsManage calendar objects and time intelligence column groups
Manage calendar objects and time intelligence column groups
No parameter schema in public metadata yet.
query_group_operationsOrganize and manage query groups for Power Query expressions
Organize and manage query groups for Power Query expressions
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
✨ Power BI Authoring MCP Server
[!IMPORTANT] When authoring semantic models in a Fabric workspace, use the remote (hosted) Power BI Authoring MCP server. It requires no local installation, and Microsoft manages updates. See Power BI Authoring MCP server to compare the remote and local options.
The Power BI Authoring MCP Server implements the MCP specification to create a seamless connection between AI agents and Power BI semantic models.
The Power BI Authoring MCP Server brings Power BI semantic modeling capabilities to your AI agents through a local MCP server. This allows developers and AI applications to interact with Power BI models in entirely new ways, from using natural language to execute modeling changes to autonomous AI agentic development workflows.
powerbi-modeling-mcp-diagram
💡 What can you do?
Details
- Repository
- github.com/microsoft/powerbi-modeling-mcp
- Categories
- AI & LLM Tools, Data & Analytics
- Package
@microsoft/powerbi-modeling-mcp- Transport
- STDIO
- Registry
- MCP registry, active
More from microsoft
Related AI & LLM Tools MCP servers
View all
Nautilus Compass Memorychunxiaoxx/nautilus-compassLocal-first long-term memory for AI agents, with byte-recomputable signed verification receipts.1.3Kstars
Attestixvibetensor/attestixAI agent identity, signed credentials, delegated authority and governance evidence.723stars
Remote MacOs Usebaryhuang/mcp-remote-macos-useThe only general AI agent that does NOT requires extra API key, giving you full control on your local and remote MacOs from Claude Desktop App482stars
Marm Mcp Serverlyellr88/marm-memoryUniversal MCP Server with advanced AI memory capabilities and semantic search.0stars