Fabric-Analytics

A Model Context Protocol (MCP) server that enables AI assistants to securely access and analyze Microsoft Fabric Analytics data through authenticated API calls.

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

View docs

Command

claude mcp add --transport stdio santhoshravindran7-fabric-analytics-mcp python -m fabric_analytics_mcp \
  --env PORT="5000" \
  --env LOG_LEVEL="INFO" \
  --env FABRIC_API_KEY="your-fabric-api-key" \
  --env ASSET_STORAGE_PATH="path/to/storage"

How to use

Fabric-Analytics MCP Server exposes a comprehensive set of MCP tools to interact with the Microsoft Fabric platform. It offers workspace management, capacity and resource handling, authentication helpers, and a suite of analytics and monitoring commands designed for AI assistants and automation workflows. Tools cover creating and managing Fabric workspaces, assigning and listing capacities, configuring Git integrations, and provisioning environments and data pipelines. When used with an MCP-enabled assistant, you can query and operate Fabric resources in a structured, protocol-friendly manner, enabling real-time monitoring, automated provisioning, and governance across your Fabric deployments.

How to install

Prerequisites:

Python 3.8+ and pip
Access to a host with network connectivity to Fabric resources
Optional: a compatible MCP client or controller depending on your environment

Install from PyPI (recommended):

pip install fabric-analytics-mcp

Run locally (example):

python -m fabric_analytics_mcp

Environment variables (example):

PORT: 5000
FABRIC_API_KEY: your-fabric-api-key
ASSET_STORAGE_PATH: /var/lib/fabric-analytics
LOG_LEVEL: INFO|DEBUG


If you prefer a Node.js deployment, you can install the MCP server package from npm and run it with Node. The repository supports both Python and Node deployments; choose the path that matches your environment.

Node.js route (if using Node):

npm install -g fabric-analytics-mcp fabric-analytics-mcp


Configure startup to run as a service or in a container as needed.

Additional notes

Notes and tips:

Ensure your FABRIC_API_KEY (or equivalent credentials) has the required permissions to manage workspaces, capacities, and environments.
If you deploy in Kubernetes, configure readiness and liveness probes to monitor the MCP server health.
Use the provided env vars to tune logging, storage paths, and ports according to your environment.
When upgrading, verify compatibility with your existing MCP clients and AI tooling to avoid protocol drift.
For debugging, run with LOG_LEVEL=DEBUG and inspect the logs for RPC/HTTP metadata and error traces.

Related MCP Servers

mcp-for-beginners

14.5k

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable, and secure AI workflows from session setup to service orchestration.

bitbucket

Bitbucket MCP - A Model Context Protocol (MCP) server for integrating with Bitbucket Cloud and Server APIs

mcp-arr

MCP server for *arr media management suite

crawlbase

Crawlbase MCP Server connects AI agents and LLMs with real-time web data. It powers Claude, Cursor, and Windsurf integrations with battle-tested web scraping, JavaScript rendering, and anti-bot protection enabling structured, live data inside your AI workflows.

dockashell

DockaShell is an MCP server that gives AI agents isolated Docker containers to work in. MCP tools for shell access, file operations, and full audit trail.

google-knowledge-graph

MCP server for Google's free public Knowledge Graph Search API - search for structured entity information about people, places, organizations, and concepts