AIFoundry Connector-FabricGraphQL

MCP Client and Server apps to demo integration of Azure OpenAI-based AI agent with a Data Warehouse, exposed through GraphQL in Microsoft Fabric.

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

View docs

Command

claude mcp add --transport stdio lazauk-aifoundry-mcpconnector-fabricgraphql python MCP_Client_Gradio.py \
  --env AOAI_API_BASE="Base URL of the Azure OpenAI endpoint" \
  --env AOAI_DEPLOYMENT="Deployment name of the Azure OpenAI model" \
  --env AOAI_API_VERSION="API version of the Azure OpenAI endpoint" \
  --env AZURE_FABRIC_GRAPHQL_ENDPOINT="Microsoft Fabric GraphQL API endpoint"

How to use

This MCP server enables an Azure OpenAI powered agent to access and manipulate data stored in a Microsoft Fabric GraphQL API through the MCP framework. The integration exposes the GraphQL data resources to the AI agent via MCP tools and prompts, enabling bidirectional data interaction (queries and mutations) with your Fabric data warehouse. The server is driven by a Python-based Gradio UI, which also serves as the MCP client to initialize the system and establish connectivity to Fabric's GraphQL endpoint. Use the provided environment variables to configure authentication, API endpoints, and the GraphQL connection for seamless data access during agent reasoning and action execution.

How to install

Prerequisites:

Python 3.8+ installed on your system
Git installed
Access to the repository containing MCP_Client_Gradio.py and requirements.txt

Step-by-step installation:

Clone the repository: git clone https://github.com/your-org/your-repo.git cd your-repo
Create and activate a Python virtual environment (optional but recommended):
- On Windows: python -m venv venv .\venv\Scripts\activate
- On macOS/Linux: python3 -m venv venv source venv/bin/activate
Install required Python packages: pip install -r requirements.txt
Configure environment variables (see below) and run the client: python MCP_Client_Gradio.py

Additional notes

Environment variables:

AOAI_API_BASE: Base URL of the Azure OpenAI endpoint
AOAI_API_VERSION: API version of the Azure OpenAI endpoint
AOAI_DEPLOYMENT: Deployment name of the Azure OpenAI model
AZURE_FABRIC_GRAPHQL_ENDPOINT: GraphQL endpoint URL for Fabric

Common issues:

Ensure the GraphQL endpoint is reachable from your execution environment.
If the OpenAI endpoint requires authentication, ensure AOAI_API_BASE and related vars are correctly set.
If using a firewall or VPN, confirm outbound access to the GraphQL and OpenAI endpoints.

Troubleshooting tips:

If the Gradio UI fails to launch, verify Python dependencies in requirements.txt.
Check that the MCP server script path (MCP_Client_Gradio.py) exists in the working directory.
Validate that environment variables are exported in your shell session before starting the client.