Fabric RTI

You can run the Fabric RTI MCP Server to expose Fabric Real-Time Intelligence capabilities as modular tools that AI agents can call. It links your Fabric RTI services to an MCP client, enabling querying, analysis, and real-time data streaming through a unified interface.

How to use

Use an MCP client to interact with the Fabric RTI MCP Server. You will discover tools grouped by service (Eventhouse, Eventstreams, Activator, and Map). Describe your goal in natural language, and the MCP client will translate it into the appropriate tool calls to read data, run queries, manage event streams, or configure alerts.

How to install

Prerequisites you need before installing the MCP server are Python, a running MCP client, and a method to install the server package from PyPI or from source. You will also need to install the uv runtime as shown in the commands below.

Install the uv runtime on Windows (example shown):

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Install from PyPI via VS Code

Open the command palette and add a new MCP server from Pip, then install the package by its PyPI name. This adds the server to your configuration.

Exact steps you will follow in the UI:

• Command: MCP: Add Server

• Choose: install from Pip

• Package name: microsoft-fabric-rti-mcp

Configuration after installation

Your settings.json (or mcp.json) should include the Fabric RTI MCP Server with its environment variables. This example shows the basic environment you need to enable default Fabric RTI integration.

{
  "mcp": {
    "server": {
      "fabric-rti-mcp": {
        "command": "uvx",
        "args": [
          "microsoft-fabric-rti-mcp"
        ],
        "env": {
          "KUSTO_SERVICE_URI": "https://help.kusto.windows.net/",
          "KUSTO_SERVICE_DEFAULT_DB": "Samples",
          "FABRIC_API_BASE_URL": "https://api.fabric.microsoft.com/v1"
        }
      }
    }
  }
}

Manual Install (Install from source)

If you prefer building from source, follow these steps to install and run the server locally.

1. Ensure Python 3.10+ is installed and added to your PATH.

2. Clone the repository.

3. Install dependencies.

4. Add the settings below into your vscode settings.json or your mcp.json.

5. Adjust the path to the repository location on your machine.

6. Adjust the cluster URI to match your Kusto cluster and the default database to your database.

7. If you supply a shots table for semantic search, configure the embeddings endpoint.

{
  "mcp": {
    "servers": {
      "fabric-rti-mcp": {
        "command": "uv",
        "args": [
          "--directory",
          "C:/path/to/fabric-rti-mcp/",
          "run",
          "-m",
          "fabric_rti_mcp.server"
        ],
        "env": {
          "KUSTO_SERVICE_URI": "https://help.kusto.windows.net/",
          "KUSTO_SERVICE_DEFAULT_DB": "Samples",
          "FABRIC_API_BASE_URL": "https://api.fabric.microsoft.com/v1"
        }
      }
    }
  }
}

Available tools

kusto_known_services

List all available Kusto services configured in the MCP

kusto_query

Execute KQL queries on the specified database

kusto_command

Execute Kusto management commands (destructive operations)

kusto_list_databases

List all databases in the Kusto cluster

kusto_list_tables

List all tables in a specified database

kusto_get_entities_schema

Get schema information for all entities in a database

kusto_get_table_schema

Get detailed schema information for a specific table

kusto_get_function_schema

Get schema information for a specific function

kusto_sample_table_data

Retrieve random sample records from a specified table

kusto_sample_function_data

Retrieve random sample records from a function result

kusto_ingest_inline_into_table

Ingest inline CSV data into a table

kusto_get_shots

Retrieve semantically similar query examples from a shots table

eventstream_list

List all Eventstreams in your Fabric workspace

eventstream_get

Get detailed information about a specific Eventstream

eventstream_get_definition

Retrieve complete JSON definition of an Eventstream

eventstream_create

Create new Eventstreams with custom configuration

eventstream_update

Modify existing Eventstream settings and destinations

eventstream_delete

Remove Eventstreams and associated resources

eventstream_start_definition

Start an Eventstream definition session

eventstream_get_current_definition

Get the current Eventstream definition

eventstream_clear_definition

Clear the current Eventstream definition

eventstream_add_sample_data_source

Add a sample data source to an Eventstream

eventstream_add_custom_endpoint_source

Add a custom endpoint data source to an Eventstream

eventstream_add_derived_stream

Add a derived stream to an Eventstream

eventstream_add_eventhouse_destination

Add an Eventhouse destination to an Eventstream

eventstream_add_custom_endpoint_destination

Add a custom endpoint destination to an Eventstream

eventstream_validate_definition

Validate an Eventstream definition

eventstream_create_from_definition

Create an Eventstream from a JSON definition

eventstream_list_available_components

List available components for Eventstreams

activator_list_artifacts

List all Activator artifacts in a Fabric workspace

activator_create_trigger

Create new Activator triggers with KQL source monitoring and alerts

map_list

List all Map items in your Fabric workspace

map_get

Get detailed information about a specific Map item

map_get_definition

Retrieve the full JSON definition of a Map item

map_create

Create a new Map item from a provided configuration

map_update_definition

Replace the full JSON definition of an existing Map item

map_update

Partially update properties of an existing Map item

map_delete

Delete a Map item