MCP.so
ログイン

Azure Data Explorer MCP Server

@cheng306

基本情報

カテゴリ

データと分析

トランスポート

stdio

作者

cheng306

Azure Data Explorer MCP Server について

概要はまだありません

#mcp-server#azure-data-explorer#kql-query

Azure Data Explorer MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "adx-query-server": {
      "command": "node",
      "args": [
        "/absolute/path/to/this/repository/build/index.js"
      ]
    }
  }
}

Azure Data Explorer MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Azure Data Explorer MCP Server?

It is a Model Context Protocol (MCP) server that authenticates to Azure Data Explorer using a service principal and executes KQL queries. It returns formatted results for use by MCP clients like Claude for Desktop.

How to use Azure Data Explorer MCP Server?

Clone the repository, install dependencies (npm install), build (npm run build), and start (npm start). The server communicates via stdio. Configure it in Claude for Desktop by editing claude_desktop_config.json to point to the built index.js. Then ask Claude to login and run queries.

Key features of Azure Data Explorer MCP Server

  • Login to Azure Data Explorer with client credentials
  • Run KQL queries against an ADX database
  • View formatted query results
  • Works over stdio with any MCP client

Use cases of Azure Data Explorer MCP Server

  • Query Azure Data Explorer interactively through a chat interface
  • Automate KQL reporting using Claude for Desktop
  • Integrate ADX data exploration into AI workflows

よくある質問

1

What is the Azure Data Explorer MCP Server used for?

It allows an MCP client like Claude for Desktop to authenticate to an Azure Data Explorer cluster and run KQL queries, returning the results in a readable format.

2

What are the prerequisites to run this server?

Node.js v16 or higher, npm v7 or higher, an Azure Data Explorer cluster, and a service principal with access to that cluster.

3

How do I configure it with Claude for Desktop?

Edit the `claude_desktop_config.json` file to add the server with `command: "node"` and `args` pointing to the absolute path of the built `index.js` file, then restart Claude.

4

What tools does the server expose?

Two tools: `login-to-adx` (parameters: cluster, database, tenantId, clientId, clientSecret) and `run-adx-query` (parameter: query).

5

How does the server authenticate to Azure Data Explorer?

It uses a service principal (client credentials) – the tenant ID, client ID, and client secret are provided as parameters to the `login-to-adx` tool.

コメント

「データと分析」の他のコンテンツ