Tabular Mcp

An MCP server for local Tabular Models like PowerBI. It allows LLM clients to debug, analyze, and compose DAX queries by connecting to a local Tabular model instance.

This is a Model Context Protocol (MCP) server for locally running Tabular Models, i.e. PowerBI models running on PowerBI Desktop.

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

Example: Copilot querying Tabular Model via MCP

It connects to a local running instance of Tabular models using theAdomdConnection in ADOMD.NET.

Using this connection, the server then allows clients to executeDAX-queriesand retrieve model metadata (using DMV queries) through pre-defined tools for high accuracy, as well as custom DAX queries for debugging and development.

# Example: Connect to Power BI Desktop instance on port 56751 dotnet run -- --port 56751

# Example: Protect customer/product names while keeping sales figures visible dotnet run -- --port 56751 --obfuscation-strategy dimensions --encryption-key "YourSecureKey123!"

# Example: Increase row limit for analysis dotnet run -- --port 56751 --max-rows 2000

Use [ListTables], [GetTableColumns], and [GetTableRelationships] to quickly understand an unfamiliar model's structure without manually clicking through Power BI Desktop.

LLM clients can use [ListMeasures] and [GetMeasureDetails] to learn your existing DAX patterns and suggest consistent new measures that follow your naming conventions and calculation styles.

Combine [RunQuery] with [ValidateDaxSyntax] to iteratively test and refine DAX expressions with immediate feedback on syntax and results.

- Validates DAX query syntax without execution
- Returns syntax correctness and error messages if applicable

- Analyzes DAX query performance and provides optimization suggestions
- Returns execution time, resource usage, and improvement recommendations

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

Download the releasefrom theReleasesdirectory or GitHub releases page and extract to your preferred location.

cd path\to\release .\pbi-local-mcp.DiscoverCli.exe

{ "mcpServers": { "MCPBI": { "type": "stdio", "command": "path\\to\\release\\mcpbi.exe", "cwd": "path\\to\\release", "args": ["--port", "YOUR_PBI_PORT"], "disabled": false, "alwaysAllow": [ "ListTables", "GetTableDetails", "GetTableColumns", "GetTableRelationships", "ListMeasures", "GetMeasureDetails", "PreviewTableData", "RunQuery", "ValidateDaxSyntax", "AnalyzeQueryPerformance", "ListFunctions", "GetFunctionDetails" ] } } }

git clone <repository-url> cd MCPBI

dotnet run --project pbi-local-mcp/pbi-local-mcp.csproj discover-pbi

Follow prompts to select instance and database.

{ "mcpServers": { "mcpbi-dev": { "type": "stdio", "command": "dotnet", "cwd": "path\\to\\MCPBI", "envFile": "path\\to\\MCPBI\\.env", "args": [ "exec", "path\\to\\MCPBI\\pbi-local-mcp\\bin\\Debug\\net8.0\\pbi-local-mcp.dll" ], "disabled": false, "alwaysAllow": [ "ListTables", "GetTableDetails", "GetTableColumns", "GetTableRelationships", "ListMeasures", "GetMeasureDetails", "PreviewTableData", "RunQuery", "ValidateDaxSyntax", "AnalyzeQueryPerformance", "ListFunctions", "GetFunctionDetails" ] } } }

Replacepath\\to\\MCPBIwith your actual repository path.

- Use either port or envFile: You can specify the Power BI port directly inargsor useenvFileto load from.env.
- Port argument: The--portargument in the release configuration connects to the specific Power BI Desktop instance on that port
- envFile: The development setup usesenvFileto automatically loadPBI_PORTandPBI_DB_IDfrom.env
- alwaysAllow: Lists all tools that can be used without requiring user approval for each invocation
- Working directory: Thecwdparameter sets the working directory where the.envfile is located

An MCP server that enables LLM clients to interact with GDB for debugging and binary analysis.

Connect any MCP-compatible IDE (Cursor, VS Code, Claude Code, Windsurf, JetBrains) to a running Isaac Sim instance and control it with plain-English prompts -- create robots, build scenes, run simulations, and debug physics all from your editor.

Security-first MCP bridge between Claude Code and your Chrome, with HMAC pairing, a per-domain allowlist, and opt-in JS evaluation for driving and debugging live browser sessions.

Hydrolix time-series datalake integration providing schema exploration and query capabilities to LLM-based workflows.

614 million contacts, live SMTP-verified. Invalid emails cost you $0. Connect Argorant with any Agent through CLI, MCP or API and build verified lists in Claude, GPT or Hermes.

Chinese writing toolbox for Claude Code: text analysis, outline generation, GB/T 7714 references,character frequency

A lightweight MCP server for connecting to Apache Doris and other MySQL-compatible databases, providing tools and prompts for LLM applications.

C# SQL Agent MCP server featuring raw SQL input, strict AST validation, and an embedded Admin UI. Eliminates LLM hallucinations and security risks across 6 major databases.

Build and access a personal LLM knowledge base from your editor or client without any infrastructure setup.

Mantora is a local-first MCP observer: a lightweight UI + proxy for inspecting LLM data access (sessions, tool calls, results) with protective defaults.