Skip to main content
Glama

Fabric MCP

by aci-labs
2
  • Linux
  • Apple
Integrations
  • Provides utilities for retrieving schemas and metadata from Delta tables in Microsoft Fabric lakehouses, including generating markdown documentation for Delta tables.

  • The project is hosted on GitHub and can be cloned from a GitHub repository, though it doesn't appear to offer specific GitHub API integration functionality.

  • Enables generation of documentation for Delta tables in Markdown format, making it easier to document and share table schemas and metadata.

Fabric MCP

Fabric MCP is a Python-based MCP server for interacting with Microsoft Fabric APIs. It provides utilities for managing workspaces, lakehouses, warehouses, and tables.(More incoming features will be added in the future). This project is inspired by the following project: https://github.com/Augustab/microsoft_fabric_mcp/tree/main

Features

  • List workspaces, lakehouses, warehouses, and tables.
  • Retrieve schemas and metadata for Delta tables.
  • Generate markdown documentation for Delta tables.

Requirements

Installation

  1. Clone the repository:
    git clone https://github.com/your-repo/fabric-mcp.git cd fabric-mcp
  2. Set up your virtual environment and install dependencies:
    uv sync
  3. Install dependencies:
    pip install -r requirements.txt

Usage

Connect to MS Fabric

  • Run the Azure CLI command to log in:
    az login --scope https://api.fabric.microsoft.com/.default

Running the MCP Server and coonecting to it using the MCP inspector

  • Run the MCP server with the inspector exposed for testing: bash uv run --with mcp mcp dev fabric_mcp.py This will start the server and expose the inspector at http://localhost:6274.

Running the MCP Server and coonecting to it using the MCP inspector

  • To use the MCP server with VSCode, you can set up a launch configuration in your launch.json file:
    { //Existing configurations... "mcp": { "servers": { "ms-fabric-mcp": { "type": "stdio", "command": "<FullPathToProjectFolder>\\.venv\\Scripts\\python.exe ", "args": [ "<FullPathToProjectFolder>\\fabric_mcp.py" ] } } } }
    This configuration allows you to run and connect to the MCP server directly from VSCode. And provide access to the Tools :
  • Using Agent mode in the Copilot chat, you can access the different tools available in the MCP server by specifying to tool name with #, for example #list_workspaces.

Available Tools

The following tools are available via the MCP server:

  • list_workspaces: List all available Fabric workspaces.
  • list_lakehouses(workspace): List all lakehouses in a specified workspace.
  • list_warehouses(workspace): List all warehouses in a specified workspace.
  • list_tables(workspace, lakehouse): List all tables in a specified lakehouse.
  • get_lakehouse_table_schema(workspace, lakehouse, table_name): Retrieve the schema and metadata for a specific Delta table.
  • get_all_lakehouse_schemas(workspace, lakehouse): Retrieve schemas and metadata for all Delta tables in a lakehouse.
  • set_lakehouse(workspace, lakehouse): Set the current lakehouse context.
  • set_warehouse(workspace, warehouse): Set the current warehouse context.
  • set_workspace(workspace): Set the current workspace context.

License

This project is licensed under the MIT License. See the LICENSE file for details.

-
security - not tested
F
license - not found
-
quality - not tested

A Python-based MCP server that enables interaction with Microsoft Fabric APIs for managing workspaces, lakehouses, warehouses, and tables through natural language.

  1. Features
    1. Requirements
      1. Installation
        1. Usage
          1. Connect to MS Fabric
          2. Running the MCP Server and coonecting to it using the MCP inspector
          3. Running the MCP Server and coonecting to it using the MCP inspector
          4. Available Tools
        2. License

          Related MCP Servers

          • -
            security
            A
            license
            -
            quality
            A Python-based MCP server that integrates OpenAPI-described REST APIs into MCP workflows, enabling dynamic exposure of API endpoints as MCP tools.
            Last updated -
            2
            39
            Python
            MIT License
            • Linux
            • Apple
          • -
            security
            F
            license
            -
            quality
            This is an MCP server that facilitates building tools for interacting with various APIs and workflows, supporting Python-based development with potential for customizable prompts and user configurations.
            Last updated -
            Python
          • A
            security
            A
            license
            A
            quality
            An MCP server implementation that integrates Claude with Salesforce, enabling natural language interactions with Salesforce data and metadata for querying, modifying, and managing objects and records.
            Last updated -
            7
            87
            15
            TypeScript
            MIT License
          • A
            security
            A
            license
            A
            quality
            An MCP server implementation that integrates Claude with Salesforce, enabling natural language interactions with Salesforce data and metadata for querying, modifying, and managing objects and records.
            Last updated -
            7
            18
            4
            TypeScript
            MIT License
            • Apple
            • Linux

          View all related MCP servers

          MCP directory API

          We provide all the information about MCP servers via our MCP API.

          curl -X GET 'https://glama.ai/api/mcp/v1/servers/aci-labs/ms-fabric-mcp'

          If you have feedback or need assistance with the MCP directory API, please join our Discord server