Tabular MCP Server

Tabular mcp mcp server lets Claude, Cursor and other MCP clients work with Tabular MCP directly. This server allows MCP-enabled LLM clients to communicate with your tabular models and help you debug, analyse and compose DAX queries.

What Tabular MCP does

This server allows MCP-enabled LLM clients to communicate with your tabular models and help you debug, analyse and compose DAX queries.

Tools it exposes

Once connected, the assistant can call these 9 tools directly:

• Port — Specify the Power BI Desktop instance port to connect to (required)
• Obfuscation — Protect sensitive data with configurable encryption strategies: - None (default): No obfuscation - All: Mask all values - Dimensions: Mask only
• list_objects — The list_objects tool exposed by this server
• get_object_details — The get_object_details tool exposed by this server
• list_functions — The list_functions tool exposed by this server
• get_function_details — The get_function_details tool exposed by this server
• run_query — The run_query tool exposed by this server
• validate_query — The validate_query tool exposed by this server
• analyze_query_performance — The analyze_query_performance tool exposed by this server

Installing the tabular mcp mcp server

Setup follows the standard MCP pattern: clone or install the server, then register it in your client's configuration file and restart the client. The configuration snippets on this page cover Claude Desktop, Claude Code and Cursor.

Configuration

The server reads one environment variable: PBI_DB_ID. Keep credentials in your client's env block or a secrets manager rather than committing them.

Requirements

• Power BI Desktop (with a PBIX file open for discovery) - Windows OS - Visual Studio Code (for MCP server integration) - .NET 8.0 Runtime

Where it fits

AI-service servers chain other models into your assistant, turning a single chat into a small production pipeline. Tabular MCP sits in that group, and the shape of its toolset — Port, Obfuscation, list_objects among others — tells you what it is really for. Worth comparing against the other ai services servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.

Practical notes

• This server runs locally, so it operates with whatever access your machine and its credentials already have. Scope that deliberately rather than by default.
• With 9 tools exposed, expect a noticeable bump in prompt size — disable it in projects that never use Tabular MCP.
• Maintained by jonaolden.
• MCP clients ask for confirmation before each tool call by default. Keep that on while you learn what the tabular mcp mcp server actually does with your data.
• Every entry in this directory is reviewed by hand before it goes live, and details are checked against the project's own documentation.