microsoft-fabric-rti-mcp

What it is and what it does

This package implements a Model Context Protocol (MCP) server that acts as a bridge between AI agents and Microsoft Fabric Real-Time Intelligence services. It exposes a comprehensive set of tools for querying Kusto databases, managing Eventstreams, creating Activator triggers, and visualizing geospatial data through Maps. The server translates natural language requests from AI agents into KQL queries and Fabric API calls, handling authentication via Azure Identity.

The package includes 13+ Kusto tools for query execution and diagnostics, 17 Eventstream tools for creation and management, 2 Activator tools for alert setup, and 7 Map tools for visualization. It also bundles a KQL Copilot Skill that teaches agents about Kusto syntax, query patterns, and optimization. The package is in Public Preview and targets Python 3.10+, with dependencies on httpx, fastmcp, azure-kusto-data, azure-identity, azure-kusto-ingest, and msal.

Use it for:

• Enable AI agents to query Eventhouse data and perform trend analysis on historical datasets through natural language prompts.
• Automate real-time alerting by creating Activator triggers that notify teams via email or Teams when KQL-monitored conditions occur.
• Build and manage Eventstreams programmatically to ingest and process sensor or IoT data in real time.
• Generate execution plans and compare query efficiency before running expensive Kusto queries against large datasets.
• Create and manage geospatial visualizations on Maps by connecting Lakehouse data sources through the MCP interface.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

An MCP server that bridges AI agents to Microsoft Fabric Real-Time Intelligence services, exposing Kusto queries, Eventstreams, Activators, and Maps as tools through the Model Context Protocol.

Yes, with conditions. The package is actively maintained and offers low install friction, but its Pre-Alpha status and explicit note that implementation may significantly change before General Availability mean it is best suited for exploration, prototyping, or integration into AI agent systems where breaking changes are acceptable. Production deployments should monitor the repository for stability signals and version milestones.

Install

microsoft-fabric-rti-mcp on PyPI

pip install microsoft-fabric-rti-mcp

uv add microsoft-fabric-rti-mcp

poetry add microsoft-fabric-rti-mcp

Installing microsoft-fabric-rti-mcp

Before you install

Low install friction with a pure-Python wheel and six runtime dependencies. The package is actively maintained with recent commits, though it carries a Pre-Alpha status and is explicitly in Public Preview with potential for significant changes before General Availability.

License in practice

MIT license permits commercial and private use with minimal restrictions, making it safe to adopt in most projects.

Quickstart

pip install microsoft-fabric-rti-mcp

from microsoft_fabric_rti_mcp import ...
# Configure with Azure credentials via azure-identity
# Connect to Fabric RTI and call MCP tools (kusto_query, eventstream_list, etc.)

Requires Azure credentials configured via azure-identity and access to a Microsoft Fabric workspace with Real-Time Intelligence services enabled.

Verify before relying

• Whether the package can be used standalone or requires a specific MCP client/host application to function
• Performance characteristics and latency for typical Kusto queries or Eventstream operations
• Specific Azure roles or permissions required beyond basic Fabric workspace access

Package facts

Evidence: microsoft_fabric_rti_mcp-0.6.2-py3-none-any.whl

Tags

More Artificial Intelligence packages

Further reading