Fabric Analytics

v1.0.0Analyticsstable

The Fabric-Analytics-MCP server enables AI agents to interact directly with Microsoft Fabric using natural language. It transforms complex data engineering tasks—such as workspace management, data exploration, and job execution—into intuitive, conver

mcpmicrosoftmicrosoft-fabricmodel-context-protocol
Share:
111
Stars
0
Downloads
0
Weekly
0/5

What is Fabric Analytics?

Fabric Analytics is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to fabric-analytics-mcp server enables ai agents to interact directly with microsoft fabric using natural language. it transforms complex data engineering tasks—such as workspace management, data explora...

The Fabric-Analytics-MCP server enables AI agents to interact directly with Microsoft Fabric using natural language. It transforms complex data engineering tasks—such as workspace management, data exploration, and job execution—into intuitive, conver

This server falls under the Analytics category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • The Fabric-Analytics-MCP server enables AI agents to interac

Use Cases

Manage Microsoft Fabric workspaces, datasets, and reports using natural language.
Execute DAX queries and trigger dataset refreshes through Claude.
Perform data engineering tasks in Fabric with conversational commands.
LicenseMIT License
Languagejavascript
Versionv1.0.0
UpdatedMay 5, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx fabric-analytics-mcp

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Fabric Analytics

The Microsoft Fabric Analytics MCP Server is a comprehensive Model Context Protocol server that gives AI assistants direct access to Microsoft Fabric's data platform through 52 tools. It covers full workspace lifecycle management, notebook creation and execution, Spark job monitoring via the Livy API, capacity assignment, role-based access control, Git integration, and automated migration of Spark workloads from Azure Synapse Analytics to Fabric. Teams use it to manage their entire Fabric estate through natural language without leaving their AI assistant.

Prerequisites

  • Node.js 18 or higher
  • A Microsoft Fabric workspace with at least Contributor access
  • A valid Fabric bearer token (obtainable from app.powerbi.com/embedsetup) or Azure service principal credentials (FABRIC_CLIENT_ID, FABRIC_CLIENT_SECRET, FABRIC_TENANT_ID)
  • For Spark monitoring: Livy API access enabled on the Fabric capacity
  • An MCP-compatible client such as Claude Desktop or GitHub Copilot
1

Clone and build the server

Clone the Fabric Analytics MCP repository, install Node.js dependencies, and build the TypeScript project.

git clone https://github.com/santhoshravindran7/Fabric-Analytics-MCP.git
cd Fabric-Analytics-MCP
npm install && npm run build
2

Obtain a Fabric bearer token

Navigate to https://app.powerbi.com/embedsetup in your browser to generate a bearer token for your Fabric workspace. Tokens expire after approximately one hour. For long-running setups consider using service principal credentials instead.

3

Configure environment variables

Set the required environment variables. The simplest method for Claude Desktop is the bearer token approach, which avoids interactive OAuth flows that time out in the sandboxed environment.

FABRIC_AUTH_METHOD=bearer_token
FABRIC_TOKEN=your_bearer_token_here
FABRIC_WORKSPACE_ID=your_workspace_id
ENABLE_HEALTH_SERVER=false
4

Add the server to Claude Desktop

Edit claude_desktop_config.json to register the Fabric Analytics MCP server with your credentials.

{
  "mcpServers": {
    "fabric-analytics": {
      "command": "node",
      "args": ["C:\\path\\to\\Fabric-Analytics-MCP\\build\\index.js"],
      "env": {
        "FABRIC_AUTH_METHOD": "bearer_token",
        "FABRIC_TOKEN": "your_bearer_token_here",
        "FABRIC_WORKSPACE_ID": "your_workspace_id",
        "ENABLE_HEALTH_SERVER": "false"
      }
    }
  }
}
5

Restart Claude Desktop

Fully quit and relaunch Claude Desktop. The 52 Fabric tools should appear in the available tool list. If you see a 60-second timeout, verify that FABRIC_AUTH_METHOD is set to bearer_token.

Fabric Analytics Examples

Client configuration

Claude Desktop config using bearer token authentication — the recommended approach to avoid interactive OAuth timeouts.

{
  "mcpServers": {
    "fabric-analytics": {
      "command": "node",
      "args": ["C:\\path\\to\\Fabric-Analytics-MCP\\build\\index.js"],
      "env": {
        "FABRIC_AUTH_METHOD": "bearer_token",
        "FABRIC_TOKEN": "your_bearer_token_here",
        "FABRIC_WORKSPACE_ID": "your_workspace_id",
        "ENABLE_HEALTH_SERVER": "false"
      }
    }
  }
}

Prompts to try

These prompts exercise workspace management, Spark monitoring, and migration capabilities.

- "Create a new workspace called 'Analytics-Q1-2025' and assign it to our premium capacity"
- "List all workspaces in my tenant and show their capacity assignments"
- "Add user [email protected] as Admin to the Analytics workspace"
- "List all running Spark applications across all workspaces and cancel any failed ones"
- "Discover assets from my Synapse workspace 'analytics-synapse' and show how the notebooks would be transformed"
- "Migrate all notebooks from Synapse workspace 'analytics-synapse' to Fabric workspace and create a lakehouse called 'MigratedData'"

Troubleshooting Fabric Analytics

Claude Desktop times out for 60 seconds on startup

This is caused by interactive OAuth flows blocking the sandboxed environment. Set FABRIC_AUTH_METHOD to bearer_token and provide FABRIC_TOKEN with a valid token from app.powerbi.com/embedsetup. The server automatically prioritizes this variable over interactive flows.

Bearer token expires during a session

Fabric bearer tokens expire after approximately one hour. Regenerate a fresh token from app.powerbi.com/embedsetup and update the FABRIC_TOKEN value in your config, then restart Claude Desktop. For production use, configure service principal credentials (FABRIC_CLIENT_ID, FABRIC_CLIENT_SECRET, FABRIC_TENANT_ID) which auto-refresh.

Tool calls return 'workspace not found' errors

Verify that FABRIC_WORKSPACE_ID contains the correct GUID for your workspace (visible in the Fabric portal URL). Ensure your bearer token or service principal has at least Contributor access to that workspace.

Frequently Asked Questions about Fabric Analytics

What is Fabric Analytics?

Fabric Analytics is a Model Context Protocol (MCP) server that fabric-analytics-mcp server enables ai agents to interact directly with microsoft fabric using natural language. it transforms complex data engineering tasks—such as workspace management, data exploration, and job execution—into intuitive, conver It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Fabric Analytics?

Follow the installation instructions on the Fabric Analytics GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Fabric Analytics?

Fabric Analytics works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Fabric Analytics free to use?

Yes, Fabric Analytics is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Browse More Analytics MCP Servers

Explore all analytics servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "fabric-analytics-mcp": { "command": "npx", "args": ["-y", "fabric-analytics-mcp"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Fabric Analytics?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides