Fabric RTI MCP 扩展

  }

- "Sample 10 rows from table 'StormEvents' in Eventhouse"

See [QUICKSTART_GUIDE.md](QUICKSTART_GUIDE.md) for detailed setup instructions and [mcp.json](mcp.json) for a template configuration.- "What can you tell me about StormEvents data?"

- "Analyze the StormEvents to come up with trend analysis across past 10 years of data"

## Features- "Analyze the commands in 'CommandExecution' table and categorize them as low/medium/high risks"



**SQL Lakehouse Tools:****SQL Lakehouse Analytics:**

- `sql_list_lakehouse_tables` - List all tables in your Lakehouse- "What tables are in my SQL lakehouse?"

- `sql_get_table_schema` - Get detailed schema for any table- "Show me the schema of table 'MyTable' in the lakehouse"

- "List all tables and their columns in my lakehouse"

**Query History Tools:**

- `query_history_list` - View recent SQL queries**Eventstream Management:**

- `query_history_get` - Get details about specific query execution- "List all Eventstreams in my workspace"

- "Show me the details of my IoT data Eventstream"

## Example Prompts



- "What tables are in my lakehouse?"### Available tools 

- "Show me the schema of the customers table"

- "List all tables and their column types"#### SQL Lakehouse - 2 Tools:

- "What queries have been run recently?"- **`sql_list_lakehouse_tables`** - List all tables in a Fabric SQL lakehouse

- **`sql_get_table_schema`** - Get detailed schema information for a specific table in the lakehouse

## Configuration

#### Eventhouse (Kusto) - 12 Tools:

### Required Environment Variables- **`kusto_known_services`** - List all available Kusto services configured in the MCP

- **`kusto_query`** - Execute KQL queries on the specified database

| Variable | Description | Example |- **`kusto_command`** - Execute Kusto management commands (destructive operations)

|----------|-------------|---------|- **`kusto_list_databases`** - List all databases in the Kusto cluster

| `FABRIC_SQL_ENDPOINT` | Your Fabric SQL endpoint (without https://) | `workspace.datawarehouse.fabric.microsoft.com` |- **`kusto_list_tables`** - List all tables in a specified database

| `FABRIC_LAKEHOUSE_NAME` | Name of your lakehouse (case-sensitive) | `MyLakehouse` |- **`kusto_get_entities_schema`** - Get schema information for all entities (tables, materialized views, functions) in a database

- **`kusto_get_table_schema`** - Get detailed schema information for a specific table

### Optional Environment Variables- **`kusto_get_function_schema`** - Get schema information for a specific function, including parameters and output schema

- **`kusto_sample_table_data`** - Retrieve random sample records from a specified table

| Variable | Description | Default |- **`kusto_sample_function_data`** - Retrieve random sample records from the result of a function call

|----------|-------------|---------|- **`kusto_ingest_inline_into_table`** - Ingest inline CSV data into a specified table

| `FABRIC_API_BASE` | Fabric API base URL | `https://api.fabric.microsoft.com/v1` |- **`kusto_get_shots`** - Retrieve semantically similar query examples from a shots table using AI embeddings

| `FABRIC_BASE_URL` | Fabric web base URL | `https://fabric.microsoft.com` |

| `UV_LINK_MODE` | Set to `copy` to avoid OneDrive hardlink issues | - |#### Eventstreams - 6 Tools:

- **`list_eventstreams`** - List all Eventstreams in your Fabric workspace

## Authentication- **`get_eventstream`** - Get detailed information about a specific Eventstream

- **`get_eventstream_definition`** - Retrieve complete JSON definition of an Eventstream

Uses Azure Identity [`DefaultAzureCredential`](https://learn.microsoft.com/en-us/azure/developer/python/sdk/authentication/credential-chains?tabs=dac) for secure authentication.

## Getting Started

**Recommended: Azure CLI**

### Prerequisites

```bash1. Install either the stable or Insiders release of VS Code:

# Windows   * [ Stable release](https://code.visualstudio.com/download)

winget install Microsoft.AzureCLI   * [ Insiders release](https://code.visualstudio.com/insiders)

2. Install the [GitHub Copilot](https://marketplace.visualstudio.com/items?itemName=GitHub.copilot) and [GitHub Copilot Chat](https://marketplace.visualstudio.com/items?itemName=GitHub.copilot-chat) extensions

# macOS3. Install `uv`  

brew install azure-cli```ps

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

# Linux```  

curl -sL https://aka.ms/InstallAzureCLIDeb | sudo bashor, check here for [other install options](https://docs.astral.sh/uv/getting-started/installation/#__tabbed_1_2)



# Authenticate4. Open VS Code in an empty folder

az login

```## Installation



The MCP server will automatically use your cached Azure CLI credentials.### 🔧 Install from GitHub (Recommended for Development)  



## DevelopmentIf you want to use the latest version or contribute to development, you can install directly from the GitHub repository:



### Install from Source#### Quick Setup Steps:



```bash1. **Prerequisites**

git clone https://github.com/melisa-l/fabric-rti-mcp.git   - Python 3.10+ installed and added to PATH

cd fabric-rti-mcp   - `uv` package manager installed (see installation steps above)

pip install -e ".[dev]"   - VS Code with GitHub Copilot extensions

   "mcp": {

           "fabric-rti-mcp": {

               "args": [

                   "C:/Users/YourUsername/fabric-rti-mcp/",

                   "-m",

               ],

                   "FABRIC_SQL_ENDPOINT": "your-workspace-name.datawarehouse.fabric.microsoft.com",

               }
           }
       }
   }

5. **Configure Environment Variables**
- **FABRIC_SQL_ENDPOINT** (Required): SQL endpoint for your Fabric lakehouse
  - Find: Fabric Portal → Lakehouse → SQL endpoint → Copy Server value
  - Format: `your-workspace-name.datawarehouse.fabric.microsoft.com`
- **FABRIC_LAKEHOUSE_NAME** (Required): Name of your lakehouse database

6. **Restart VS Code**
- Close and reopen VS Code for the MCP server to be recognized
- The server will automatically start when you use Copilot in Agent mode

#### Verify Installation:
1. Open GitHub Copilot Chat and switch to Agent mode
2. Type "@workspace /tools" to see available MCP tools
3. You should see tools from fabric-rti-mcp (SQL Lakehouse tools primarily)
4. Try a test query: "What tables are in my lakehouse?"

---

### Alternative: Install from PyPI (Pip)
The Fabric RTI MCP Server is also available on [PyPI](https://pypi.org/project/microsoft-fabric-rti-mcp/):

#### From VS Code
1. Open command palette (`Ctrl+Shift+P`) and run `MCP: Add Server`
2. Select "Install from Pip"
3. Enter package name: `microsoft-fabric-rti-mcp`
4. Follow the prompts to configure

The process will add these settings to your `settings.json`:

## Debugging the MCP Server locally
Assuming you have python installed and the repo cloned:

### Install locally
```bash
pip install -e ".[dev]"

https://{your-openai-resource}.openai.azure.com/openai/deployments/{deployment-name}/embeddings?api-version={api-version};impersonate

winget install Microsoft.AzureCLI

brew install azure-cli

curl -sL https://aka.ms/InstallAzureCLIDeb | sudo bash

az login

# Example from test_kusto_tools_live_http.py
auth_header = f"Bearer {token.token}"

headers = {
    "Content-Type": "application/json",
    "Accept": "application/json, text/event-stream",
    "Authorization": auth_header,
}