MCP KQL Server runs on your own machine — the client starts it, so there is no endpoint to ping. 660 installs a week from pypi.
Execute KQL in AI prompts via NL2KQL with schema discovery and Azure Data Explorer integration
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add mcp-kql-server -- uvx mcp-kql-server
{
"mcpServers": {
"mcp-kql-server": {
"args": [
"mcp-kql-server"
],
"command": "uvx"
}
}
}
[mcp_servers.mcp-kql-server]
command = "uvx"
args = ["mcp-kql-server"]
{
"mcpServers": {
"mcp-kql-server": {
"args": [
"mcp-kql-server"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"mcp-kql-server": {
"args": [
"mcp-kql-server"
],
"command": "uvx"
}
}
}
Answers built from our own checks of this server.