About Azure Data Explorer MCP Server
Azure Data Explorer MCP Server lets clients authenticate to Azure Data Explorer and run KQL queries. It is intended for users who want to query an ADX database through an MCP client and view formatted results.
Key features
- 01Service-principal authentication
- 02Run KQL queries
- 03Formatted query results
Use cases
- 01Querying an ADX database from an MCP client
- 02Reviewing formatted results of KQL queries
MCP support
It exposes login and query tools to MCP clients over stdio, enabling authentication to Azure Data Explorer and execution of KQL queries.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEAzure Data Explorer MCP Server
This is a Model Context Protocol (MCP) server that can login to Azure Data Explorer and run KQL queries.
Features
- Login to Azure Data Explorer using service principal (client credentials)
- Run KQL queries against an Azure Data Explorer database
- View formatted query results
Prerequisites
- Node.js (v16 or higher)
- npm (v7 or higher)
- Azure Data Explorer cluster
- Service Principal with access to Azure Data Explorer
Setup
- Clone or download this repository
- Install dependencies:
npm install
- Build the project:
npm run build
Running the server
Start the server:
npm start
The server will listen on standard input/output (stdio), which is the format expected by MCP clients like Claude for Desktop.
Usage with Claude for Desktop
- Configure Claude for Desktop to use this MCP server by editing the
claude_desktop_config.jsonfile:
{
"mcpServers": {
"adx-query-server": {
"command": "node",
"args": [
"/absolute/path/to/this/repository/build/index.js"
]
}
}
}
-
Restart Claude for Desktop
-
Use the MCP server through Claude by asking it to:
- Login to Azure Data Explorer
- Run KQL queries
Available Tools
login-to-adx
Authenticates with Azure Data Explorer using client credentials.
Parameters:
cluster: The ADX cluster URL (e.g., https://mycluster.eastus.kusto.windows.net)database: The database nametenantId: The Azure tenant IDclientId: The Azure client/application IDclientSecret: The Azure client secret
run-adx-query
Runs a KQL query against the connected Azure Data Explorer database.
Parameters:
query: The KQL query to execute
Development
To run the server in development mode:
npm run dev
License
ISC
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.