- Home
- MCP servers
- MCP Kusto Server
MCP Kusto Server
- go
3
GitHub Stars
go
Language
6 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"abhirockzz-mcp_kusto": {
"command": "enter path to binary e.g. /Users/demo/Desktop/mcp_kusto",
"args": []
}
}
}This MCP server provides a set of tools to interact with Azure Data Explorer (Kusto) from your MCP-enabled clients. You can list databases and tables, inspect table schemas, and run read-only KQL queries against your Azure Data Explorer cluster. It authenticates using your Azure credentials, enabling you to explore data without leaving your development environment.
How to use
Use an MCP client (such as VS Code with MCP support) to connect to the Kusto MCP server. The server exposes these capabilities: list_databases to enumerate databases in a cluster, list_tables to list tables in a database, get_table_schema to retrieve a table’s schema, and execute_query to run read-only KQL queries against a database. You can combine these tools to explore your data model and verify query results as you analyze data.
How to install
Prerequisites: you need Go installed on your system to build the MCP server.
# Install Go if you don’t have it yet, then build the MCP server
# (Replace with your actual Go installation steps if needed)
# Build the MCP server binary
go build -o mcp_kusto main.go
Additional content
Configure your MCP client to connect to the local or remote MCP server. The following example shows how you would reference the local binary in a typical MCP client configuration.
{
"servers": {
"Kusto MCP server": {
"type": "stdio",
"command": "enter path to binary e.g. /Users/demo/Desktop/mcp_kusto",
"args": []
}
}
}
Notes and security
Authentication is performed using DefaultAzureCredential. Ensure your user principal has permissions to run .show databases, .show table, .show tables, and to execute queries on the target database. For local development, you can authenticate by logging in with the Azure CLI (az login). Always validate query results before using them for decisions.
Available tools
list_databases
Lists all databases in a specific Azure Data Explorer cluster.
list_tables
Lists all tables in a specific Azure Data Explorer database.
get_table_schema
Gets the schema of a specific table in an Azure Data Explorer database.
execute_query
Executes a read-only KQL query against a database.