Kusto MCP Server
An MCP (Model Context Protocol) server that provides tools for interacting with Azure Data Explorer (Kusto) clusters.
README
Kusto MCP Server
An MCP (Model Context Protocol) server that provides tools for interacting with Azure Data Explorer (Kusto) clusters. Query, manage connections, and explore schemas using AI assistants like Claude and GitHub Copilot.
Features
- Execute KQL queries and scripts
- Manage multiple cluster connections
- Explore database schemas
- Full Azure authentication support
- Works with Claude Desktop, Claude Code CLI, and VS Code with GitHub Copilot
Prerequisites
- Node.js 18+
- .NET 8 Runtime
- Kusto CLI (
microsoft.azure.kusto.toolsNuGet package) - Azure CLI (for authentication)
Install Kusto CLI
dotnet tool install -g Microsoft.Azure.Kusto.Tools
Or via NuGet:
nuget install microsoft.azure.kusto.tools -Version 14.0.3
Installation
Via npm (recommended)
npm install -g kusto-mcp-server
Via npx (no installation required)
npx kusto-mcp-server
Usage with AI Assistants
Claude Desktop
Add to your Claude Desktop configuration:
- Windows:
%APPDATA%\Claude\claude_desktop_config.json - macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Linux:
~/.config/claude/claude_desktop_config.json
{
"mcpServers": {
"kusto": {
"command": "npx",
"args": ["-y", "kusto-mcp-server"],
"env": {
"KUSTO_CLI_PATH": "~/.nuget/packages/microsoft.azure.kusto.tools/14.0.3/tools/net8.0/Kusto.Cli.dll"
}
}
}
}
Claude Code (CLI)
claude mcp add kusto -- npx -y kusto-mcp-server
Verify it's connected:
claude mcp list
VS Code with GitHub Copilot
Add to your VS Code settings.json (or .vscode/mcp.json in your workspace):
{
"mcp": {
"servers": {
"kusto": {
"command": "npx",
"args": ["-y", "kusto-mcp-server"],
"env": {
"KUSTO_CLI_PATH": "~/.nuget/packages/microsoft.azure.kusto.tools/14.0.3/tools/net8.0/Kusto.Cli.dll"
}
}
}
}
}
Or use the VS Code command palette:
- Open Command Palette (
Ctrl+Shift+P/Cmd+Shift+P) - Run "MCP: Add Server"
- Select "Command (stdio)"
- Enter command:
npx -y kusto-mcp-server - Enter server ID:
kusto
Authentication
Before using the server, authenticate with Azure:
az login
Available Tools
Query Tools
| Tool | Description |
|---|---|
kusto_query |
Execute KQL queries (primary tool) |
kusto_execute |
Advanced execution with full CLI options |
kusto_script |
Execute script files |
Connection Management
| Tool | Description |
|---|---|
kusto_connection_add |
Add/update a named connection |
kusto_connection_list |
List all configured connections |
kusto_connection_test |
Test connectivity |
kusto_connection_remove |
Remove a connection |
kusto_connection_set_default |
Set the default connection |
Schema & Help
| Tool | Description |
|---|---|
kusto_schema |
Get database schema information |
kusto_help |
Get help and CLI options |
Usage Examples
Add a Connection
kusto_connection_add({
name: "my-cluster",
cluster: "https://mycluster.kusto.windows.net",
database: "MyDatabase",
authMethod: "azcli",
isDefault: true
})
Execute a Query
kusto_query({
query: "StormEvents | summarize count() by State | top 10 by count_",
connectionName: "my-cluster"
})
Get Schema
kusto_schema({
scope: "tables",
connectionName: "my-cluster"
})
Execute Multiple Commands
kusto_execute({
commands: [
".show tables",
"StormEvents | count"
],
connectionName: "my-cluster"
})
Configuration
Environment variables:
| Variable | Description | Default |
|---|---|---|
KUSTO_CLI_PATH |
Path to Kusto.Cli.dll | Auto-detected |
KUSTO_DEFAULT_TIMEOUT |
Default query timeout (ms) | 60000 |
KUSTO_MAX_ROWS |
Default max rows | 10000 |
Development
# Clone the repository
git clone https://github.com/yeshsurya/kusto-mcp-server.git
cd kusto-mcp-server
# Install dependencies
npm install
# Build
npm run build
# Watch mode
npm run dev
# Run tests
npm test
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。