Fabric RTI

v1.0.0Databasesstable

MCP server for Fabric Real-Time Intelligence (https://aka.ms/fabricrti) supporting tools for Eventhouse (https://aka.ms/eventhouse), Azure Data Explorer (https://aka.ms/adx, and other RTI services (coming soon)

fabric-rtimcpai-integration
Share:
116
Stars
0
Downloads
0
Weekly
0/5

What is Fabric RTI?

Fabric RTI is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server for fabric real-time intelligence (https://aka.ms/fabricrti) supporting tools for eventhouse (https://aka.ms/eventhouse), azure data explorer (https://aka.ms/adx, and other rti services (co...

MCP server for Fabric Real-Time Intelligence (https://aka.ms/fabricrti) supporting tools for Eventhouse (https://aka.ms/eventhouse), Azure Data Explorer (https://aka.ms/adx, and other RTI services (coming soon)

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

Features

  • MCP server for Fabric Real-Time Intelligence (https://aka.ms

Use Cases

Access Microsoft Fabric's Real-Time Intelligence services.
Query data from Eventhouse and Azure Data Explorer via MCP.
Work with Fabric analytics and monitoring tools.
microsoft

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMay 18, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx fabric-rti

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 RTI

The Fabric RTI MCP Server connects AI assistants to Microsoft Fabric's Real-Time Intelligence platform, including Eventhouse, Azure Data Explorer (Kusto), Eventstreams, Activator, and Map services. It exposes over 30 tools across these services, enabling AI agents to execute KQL queries, manage real-time data pipelines, create monitoring triggers, and visualize geospatial data. Developers and data engineers working with Microsoft Fabric can use this server to query and manage streaming analytics workloads directly from their AI coding assistant without switching contexts.

Prerequisites

  • Python 3.9+ and pip or uv package manager installed
  • Microsoft Fabric workspace with Real-Time Intelligence services (Eventhouse or Azure Data Explorer)
  • Azure CLI installed and logged in, or another Azure credential provider for DefaultAzureCredential authentication
  • An MCP-compatible client such as VS Code with GitHub Copilot, Claude Desktop, or Cursor
  • Network access to your Kusto/Eventhouse cluster endpoint
1

Install the package

Install the microsoft-fabric-rti-mcp package from PyPI using pip or uv. Using uv tool install is recommended as it creates an isolated environment.

pip install microsoft-fabric-rti-mcp
# or with uv (recommended)
uv tool install microsoft-fabric-rti-mcp
2

Authenticate with Azure

The server uses Azure Identity's DefaultAzureCredential chain. Log in with the Azure CLI before starting the server so credentials are automatically discovered.

az login
3

Configure environment variables

Set the required environment variables for your Eventhouse or Azure Data Explorer cluster. KUSTO_SERVICE_URI is the cluster endpoint and KUSTO_SERVICE_DEFAULT_DB is the default database to query.

export KUSTO_SERVICE_URI="https://yourcluster.kusto.windows.net"
export KUSTO_SERVICE_DEFAULT_DB="YourDatabase"
# Optional: for Fabric API access
export FABRIC_API_BASE="https://api.fabric.microsoft.com/v1"
4

Add the server to your MCP client

Configure your MCP client (Claude Desktop, VS Code, or Cursor) to launch the server. The configuration JSON below uses the uvx runner for Claude Desktop.

5

Verify connection by running a test query

Once configured, open your MCP client and ask it to list databases in your Eventhouse. This confirms the server is running and credentials are valid.

Fabric RTI Examples

Client configuration

Claude Desktop configuration using uvx to run the Fabric RTI MCP server with required environment variables.

{
  "mcpServers": {
    "fabric-rti": {
      "command": "uvx",
      "args": ["microsoft-fabric-rti-mcp"],
      "env": {
        "KUSTO_SERVICE_URI": "https://yourcluster.kusto.windows.net",
        "KUSTO_SERVICE_DEFAULT_DB": "YourDatabase",
        "FABRIC_API_BASE": "https://api.fabric.microsoft.com/v1",
        "FABRIC_RTI_TRANSPORT": "stdio"
      }
    }
  }
}

Prompts to try

Example prompts to use with the Fabric RTI MCP server after setup.

- "Get all databases in my Eventhouse cluster"
- "Sample 10 rows from the StormEvents table"
- "Run a KQL query: SignalRServiceDiagnosticLogs | count"
- "List all Eventstreams in my Fabric workspace"
- "Create a Teams alert trigger when error rate exceeds 5% for my IoT stream"
- "Show me details of the Eventstream named SensorData"

Troubleshooting Fabric RTI

Authentication fails with DefaultAzureCredential error

Run 'az login' in your terminal and ensure your Azure account has Viewer or Contributor access to the Fabric workspace. If using a service principal, set AZURE_CLIENT_ID, AZURE_CLIENT_SECRET, and AZURE_TENANT_ID environment variables.

KQL queries return 'cluster not found' or connection timeout

Verify KUSTO_SERVICE_URI is the correct cluster URI (format: https://<clustername>.<region>.kusto.windows.net). Test connectivity by running 'az kusto cluster show' or opening the cluster URL in a browser.

Server fails to start after pip install

Ensure you are running Python 3.9+ with 'python --version'. If using uv, run 'uv tool install microsoft-fabric-rti-mcp' to install in an isolated environment and ensure ~/.local/bin is in your PATH.

Frequently Asked Questions about Fabric RTI

What is Fabric RTI?

Fabric RTI is a Model Context Protocol (MCP) server that mcp server for fabric real-time intelligence (https://aka.ms/fabricrti) supporting tools for eventhouse (https://aka.ms/eventhouse), azure data explorer (https://aka.ms/adx, and other rti services (coming soon) It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Fabric RTI?

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

Which AI clients work with Fabric RTI?

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

Is Fabric RTI free to use?

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

Browse More Databases MCP Servers

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

Quick Config Preview

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

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

Read the full setup guide →

Ready to use Fabric RTI?

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