Tabular MCP
T

Tabular MCP

MCPBI is a server that provides Model Context Protocol (MCP) services for locally running tabular models (such as those in PowerBI Desktop). It supports interaction between LLM clients using the MCP protocol and tabular models for debugging, analyzing, and writing DAX queries.
2.5 points
7.5K

What is MCPBI?

MCPBI is a Model Context Protocol server specifically designed to connect to locally running PowerBI tabular models. It allows client tools that support the MCP protocol (such as Copilot) to interact with your data model, helping to debug, analyze, and write DAX queries.

How to use MCPBI?

You can connect MCPBI to your PowerBI Desktop instance through simple configuration, and then any MCP-compatible client can interact with your data model through the standard protocol.

Use cases

Suitable for data analysts and BI developers who need to: - Query the data model through natural language - Debug complex DAX expressions - Analyze the model structure and relationships - Validate DAX syntax - Optimize query performance

Main features

List measures
Get a list of all measures in the model, including names,所属 tables, data types, and visibility status
Get measure details
View the complete definition and properties of a specific measure
Model metadata query
Get the complete structure information of tables, columns, and relationships
Execute DAX query
Support the complete DAX query syntax, including the DEFINE block and EVALUATE statement
DAX syntax validation
Check the syntax of DAX expressions and provide error analysis
Query performance analysis
Identify potential performance bottlenecks in query execution
Advantages
Seamlessly integrate with local PowerBI Desktop instances
Support the full DAX query capabilities
Provide rich access to model metadata
The standardized MCP protocol ensures client compatibility
Lightweight and easy to set up
Limitations
Only support locally running PowerBI instances
Require ADOMD.NET connection support
Performance is limited by local machine resources

How to use

Install MCPBI
Download the pre-compiled executable file from Releases or build from the source code
Configure PowerBI connection
Run the discovery tool to automatically detect PowerBI instances or manually specify the port
Configure the client
Configure the MCPBI server information in the mcp.json of the client (such as VS Code)
Start using
Interact with your PowerBI model through the client tool

Usage examples

Analyze sales data
Get sales trend analysis through natural language queries
Debug DAX measures
Check the calculation logic of measures and validate the results
Model structure analysis
Understand the tables and relationships in the data model

Frequently Asked Questions

Which PowerBI versions does MCPBI support?
How to find the port number of the PowerBI instance?
Does it support remote PowerBI services?
What should I do if a connection error occurs when executing a query?

Related resources

ADOMD.NET documentation
Microsoft official ADOMD.NET connection documentation
DAX query guide
A detailed guide on executing DAX queries through ADOMD.NET
GitHub repository
Project source code and issue tracking
MCP protocol specification
The complete specification of the Model Context Protocol

Installation

Copy the following command to your Client for configuration
{
    "mcpServers": {
      "MCPBI": {
        "command": "C:\\dir\\to\\mcpbi.exe",
        "args": []
      }
    }
  }

{
    "mcpServers": {
      "MCPBI": {
        "command": "C:\\dir\\to\\mcpbi.exe",
        "args": ["--port","12345"]
      }
    }
  }
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
6.1K
4.5 points
M
Moltbrain
MoltBrain is a long-term memory layer plugin designed for OpenClaw, MoltBook, and Claude Code, capable of automatically learning and recalling project context, providing intelligent search, observation recording, analysis statistics, and persistent storage functions.
TypeScript
6.2K
4.5 points
B
Bm.md
A feature-rich Markdown typesetting tool that supports multiple style themes and platform adaptation, providing real-time editing preview, image export, and API integration capabilities
TypeScript
14.5K
5 points
S
Security Detections MCP
Security Detections MCP is a server based on the Model Context Protocol that allows LLMs to query a unified security detection rule database covering Sigma, Splunk ESCU, Elastic, and KQL formats. The latest version 3.0 is upgraded to an autonomous detection engineering platform that can automatically extract TTPs from threat intelligence, analyze coverage gaps, generate SIEM-native format detection rules, run tests, and verify. The project includes over 71 tools, 11 pre-built workflow prompts, and a knowledge graph system, supporting multiple SIEM platforms.
TypeScript
5.9K
4 points
P
Paperbanana
Python
8.5K
5 points
F
Finlab Ai
FinLab AI is a quantitative financial analysis platform that helps users discover excess returns (alpha) in investment strategies through AI technology. It provides a rich dataset, backtesting framework, and strategy examples, supporting automated installation and integration into mainstream AI programming assistants.
6.7K
4 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
7.7K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
8.2K
5 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
21.7K
4.5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
25.9K
4.3 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
74.9K
4.3 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
36.3K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
67.3K
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
36.5K
5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
22.1K
4.5 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
100.8K
4.7 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase