Azure Data Explorer
A Model Context Protocol (MCP) server that enables AI assistants to query and analyze Azure Data Explorer databases through standardized interfaces.
What is Azure Data Explorer?
Azure Data Explorer is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol (mcp) server that enables ai assistants to query and analyze azure data explorer databases through standardized interfaces.
A Model Context Protocol (MCP) server that enables AI assistants to query and analyze Azure Data Explorer databases through standardized interfaces.
This server falls under the Databases category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A Model Context Protocol (MCP) server that enables AI assist
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx adxConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Azure Data Explorer
The Azure Data Explorer MCP Server enables AI assistants to query and explore Azure Data Explorer (ADX/Kusto) clusters through a standardized Model Context Protocol interface. It exposes tools for executing KQL queries, listing database tables, inspecting schemas, sampling table contents, and retrieving table statistics including row counts and storage size. Data engineers and analysts use it to give Claude or other AI clients direct, authenticated access to ADX and Microsoft Fabric Eventhouse databases for natural-language-driven data exploration.
Prerequisites
- Python 3.12+ with uv installed
- An Azure Data Explorer cluster with a database you have read access to
- Azure CLI installed and authenticated (az login) or a service principal with AZURE_TENANT_ID and AZURE_CLIENT_ID
- The cluster URL in the format https://yourcluster.region.kusto.windows.net
- An MCP-compatible client such as Claude Desktop
Clone the repository
Clone the adx-mcp-server repository to your local machine.
git clone https://github.com/pab1it0/adx-mcp-server.git
cd adx-mcp-serverAuthenticate with Azure
Log in with the Azure CLI using an account that has at least Viewer access to the ADX cluster and database. This provides the DefaultAzureCredential used by the server.
az loginSet required environment variables
Create a .env file or export these variables. ADX_CLUSTER_URL and ADX_DATABASE are the only required settings; the rest are optional.
ADX_CLUSTER_URL=https://yourcluster.region.kusto.windows.net
ADX_DATABASE=your_database
# Optional: for AKS workload identity
# AZURE_TENANT_ID=your-tenant-id
# AZURE_CLIENT_ID=your-client-idRun the server locally to verify
Use uv to start the server in stdio mode and confirm it connects to ADX without errors.
uv run src/adx_mcp_server/main.pyAdd the server to your MCP client configuration
Insert the following block into claude_desktop_config.json to have Claude Desktop manage the server process. Replace the directory path and env values with your actual settings.
{
"mcpServers": {
"adx": {
"command": "uv",
"args": [
"--directory",
"/full/path/to/adx-mcp-server",
"run",
"src/adx_mcp_server/main.py"
],
"env": {
"ADX_CLUSTER_URL": "https://yourcluster.region.kusto.windows.net",
"ADX_DATABASE": "your_database"
}
}
}
}Azure Data Explorer Examples
Client configuration
Claude Desktop configuration to launch the ADX MCP server via uv with cluster connection settings in the env block.
{
"mcpServers": {
"adx": {
"command": "uv",
"args": [
"--directory",
"/home/user/adx-mcp-server",
"run",
"src/adx_mcp_server/main.py"
],
"env": {
"ADX_CLUSTER_URL": "https://mycluster.westeurope.kusto.windows.net",
"ADX_DATABASE": "telemetry"
}
}
}
}Prompts to try
Sample prompts that exercise the KQL query and schema discovery tools.
- "List all tables in the connected ADX database."
- "Show me the schema of the Events table including all column types."
- "Run this KQL query: Events | where Timestamp > ago(1h) | summarize count() by Source"
- "Show me a sample of 10 rows from the Logs table."
- "What are the row count and storage size of the Telemetry table?"Troubleshooting Azure Data Explorer
'Error: spawn uv ENOENT' in Claude Desktop
Claude Desktop may not inherit your shell's PATH. Either set the full path to uv in the command field (e.g. /home/user/.local/bin/uv) or add NO_UV=1 to the env block to fall back to the installed Python.
Authentication fails with 'DefaultAzureCredential: no credential found'
Run 'az login' in the same user session before starting Claude Desktop. For CI/AKS environments, set AZURE_TENANT_ID, AZURE_CLIENT_ID, and ensure the workload identity token is mounted at ADX_TOKEN_FILE_PATH.
KQL query returns 'Access denied' on a specific table
Grant the Azure identity used at least 'Database Viewer' or table-level 'Viewer' permissions in the ADX cluster IAM settings via the Azure portal or az kusto commands.
Frequently Asked Questions about Azure Data Explorer
What is Azure Data Explorer?
Azure Data Explorer is a Model Context Protocol (MCP) server that model context protocol (mcp) server that enables ai assistants to query and analyze azure data explorer databases through standardized interfaces. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Azure Data Explorer?
Follow the installation instructions on the Azure Data Explorer GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Azure Data Explorer?
Azure Data Explorer works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Azure Data Explorer free to use?
Yes, Azure Data Explorer is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Azure Data Explorer Alternatives — Similar Databases Servers
Looking for alternatives to Azure Data Explorer? Here are other popular databases servers you can use with Claude, Cursor, and VS Code.
Excelize
★ 20.6kGo language library for reading and writing Microsoft Excel™ (XLAM / XLSM / XLSX / XLTM / XLTX) spreadsheets
MCP Toolbox for Databases
★ 15.3kOpen source MCP server specializing in easy, fast, and secure tools for Databases.
DBHub
★ 2.8kA universal database gateway MCP server that enables AI assistants to connect to and query multiple databases (PostgreSQL, MySQL, MariaDB, SQL Server, SQLite) with support for schema exploration, SQL execution, and secure connections via SSH tunnels.
Tabularis
★ 2.1kA lightweight, cross-platform database client for developers. Supports MySQL, PostgreSQL and SQLite. Hackable with plugins. Built for speed, security, and aesthetics.
Postgres AI Guide
★ 1.7kMCP server and Claude plugin for Postgres skills and documentation. Helps AI coding tools generate better PostgreSQL code.
Anyquery
★ 1.7k🏎️ 🏠 ☁️ - Query more than 40 apps with one binary using SQL. It can also connect to your PostgreSQL, MySQL, or SQLite compatible database. Local-first and private by design.
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.
Set Up Azure Data Explorer in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Azure Data Explorer?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.