MCP.so
Sign In

🚀 MCP KQL Server

@4R9UN

Repository

About 🚀 MCP KQL Server

Kusto and Log Analytics MCP server help you execute a KQL (Kusto Query Language) query within an AI prompt, analyze, and visualize the data.

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-kql-server": {
      "command": "python",
      "args": [
        "-m",
        "mcp_kql_server",
        "--transport",
        "http",
        "--host",
        "127.0.0.1",
        "--port",
        "8000",
        "--http-path",
        "/mcp",
        "--stateless-http"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is MCP KQL Server?

MCP KQL Server is an MCP server that transforms natural language questions into optimized KQL queries with intelligent schema discovery, AI-powered caching, and seamless Azure Data Explorer integration. It is for data analysts, developers, and AI agents who need to query Azure Data Explorer using plain English.

How to use MCP KQL Server?

Install with pip install mcp-kql-server, then configure your MCP client (e.g., Claude Desktop, VSCode) to launch the server via python -m mcp_kql_server. The server provides two main tools: execute_kql_query for NL2KQL conversion and direct KQL execution, and kql_schema_memory for schema discovery and cache management.

Key features of MCP KQL Server

  • Natural Language to KQL (NL2KQL) conversion
  • Execute raw KQL queries directly
  • Schema discovery and AI-powered caching
  • Support for JSON, CSV, and table output formats
  • Schema-grounded repair of invalid query columns
  • Cache management and memory statistics

Use cases of MCP KQL Server

  • Query Azure Data Explorer without writing KQL manually
  • Explore database schemas and table structures interactively
  • Generate analysis reports with visualizations from natural language prompts

FAQ from MCP KQL Server

What are the prerequisites for running MCP KQL Server?

Python 3.10 or higher, Azure CLI installed and authenticated (via az login), and access to an Azure Data Explorer cluster.

How do I configure MCP KQL Server for my MCP client?

Add a stdio or HTTP entry to your client's MCP settings file. For Claude Desktop, add {"command": "python", "args": ["-m", "mcp_kql_server"]} to mcp_settings.json. For shared environments, use --transport http.

What transports does MCP KQL Server support?

It supports stdio, HTTP, streamable HTTP, and SSE transports, configurable via the --transport option or the FASTMCP_TRANSPORT environment variable.

How does the server handle authentication?

Authentication is delegated to the Azure CLI. The server can check Azure CLI auth on startup via --auth-on-startup or the MCP_KQL_AUTH_ON_STARTUP environment variable.

Where does MCP KQL Server store its schema cache?

Cached schema data is stored in %APPDATA%\KQL_MCP on Windows or ~/.local/share/KQL_MCP on Linux and macOS.

Frequently asked questions

What are the prerequisites for running MCP KQL Server?

Python 3.10 or higher, Azure CLI installed and authenticated (via `az login`), and access to an Azure Data Explorer cluster.

How do I configure MCP KQL Server for my MCP client?

Add a stdio or HTTP entry to your client's MCP settings file. For Claude Desktop, add `{"command": "python", "args": ["-m", "mcp_kql_server"]}` to `mcp_settings.json`. For shared environments, use `--transport http`.

What transports does MCP KQL Server support?

It supports stdio, HTTP, streamable HTTP, and SSE transports, configurable via the `--transport` option or the `FASTMCP_TRANSPORT` environment variable.

How does the server handle authentication?

Authentication is delegated to the Azure CLI. The server can check Azure CLI auth on startup via `--auth-on-startup` or the `MCP_KQL_AUTH_ON_STARTUP` environment variable.

Where does MCP KQL Server store its schema cache?

Cached schema data is stored in `%APPDATA%\KQL_MCP` on Windows or `~/.local/share/KQL_MCP` on Linux and macOS.

Comments

Basic information

Category

Data & Analytics

License

MIT

Transports

stdio

Author

4R9UN

More Data & Analytics MCP servers

Jitsu

Jitsu

Jitsu is an open-source Customer Data Platform — an MIT-licensed alternative to Segment. This MCP server gives your AI assistant direct control over a Jitsu workspace, so you can run and debug data pipelines in conversat

SiteGuru

Your site's real SEO data in your AI assistant. SiteGuru crawls your website and connects to Google Search Console and Google Analytics. This server exposes that data to your assistant, so you can ask what's broken, wha

S

Stratyfix

Stratyfix

Stratyfix is an AI-driven sales intelligence platform. This connector lets managers and reps ask about their own Stratyfix data in the chat they already use. Are we going to make the quarter? Who needs my attention this

Kinetic Pricing

Kinetic Pricing

Kinetic Pricing lets you run pricing research with your own customers and manage the work around each decision. Create Van Westendorp, Gabor-Granger, MaxDiff, and choice-based conjoint studies; preview and launch surveys

CoinLobster

CoinLobster

The only MCP server with live whale trades across 15 exchanges plus on-chain DEX flow. Smart Money Radar, real liquidations and outcome-scored signals. No API key required.

3