Azure Log Analytics MCP

🚀 Azure Object Analyzer Log MCP Server

An MCP (Model Context Protocol) server for querying Azure Object Analyzer logs using natural language. This server enables large language models to convert natural language queries into KQL (Kusto Query Language) and execute them on Azure Object Analyzer.

🚀 Quick Start

The Azure Object Analyzer Log MCP Server offers a seamless way to query logs in Azure Object Analyzer using natural language. It bridges the gap between large language models and the Kusto Query Language, making log analysis more accessible.

✨ Features

• Natural Language to KQL Conversion: Utilize Claude AI to transform natural language queries into KQL.
• Query Execution: Execute KQL queries to access Azure Object Analyzer.
• Result Formatting: Format results for easy consumption by LLMs.
• Dual Modes: Support both CLI mode for direct interaction and MCP server mode for LLM integration.

📦 Installation

Prerequisites

• Node.js 18.x or higher
• An Azure subscription with access to the Object Analyzer workspace
• An Anthropic API key to use Claude AI
• Azure CLI configured with appropriate credentials

Installation Steps

# Clone the repository
git clone https://github.com/MananShahTR/azure-log-analytics-mcp.git
cd azure-log-analytics-mcp

# Install dependencies
npm install

# Build the project
npm run build

📚 Documentation

Configuration

The server requires the following environment variables:

• ANTHROPIC_API_KEY: Your Anthropic API key to use Claude AI

Azure credentials are obtained through Azure CLI credentials. Ensure you are logged in using az login before running the server.

You need to configure the following in the azure-service.ts file:

• subscriptionId: Your Azure subscription ID
• resourceGroup: The resource group containing your Object Analyzer resource
• appInsightsId: The name of your Application Insights resource

Usage

CLI Tool

# Run as a CLI tool
ANTHROPIC_API_KEY=your_key_here node build/index.js

MCP Server

# Run as an MCP server
ANTHROPIC_API_KEY=your_key_here node build/mcp-server.js

MCP Settings Configuration

Add the following to your MCP settings configuration file:

{
  "mcpServers": {
    "azure-log-analytics": {
      "command": "node",
      "args": ["path/to/azure-log-analytics-mcp/build/mcp-server.js"],
      "env": {
        "ANTHROPIC_API_KEY": "your_key_here"
      }
    }
  }
}

Tool Usage

Once connected, the MCP server provides the following tool:

• query_logs: Query Azure Object Analyzer using natural language
  • Parameters:
    • query: A natural language query about trace logs (required)
    • timeRange: An optional time range (e.g., "last 24 hours", "last week")
    • limit: The maximum number of results to return

💻 Usage Examples

Basic Usage

// Example of using the MCP tool
use_mcp_tool({
  server_name: "azure-log-analytics",
  tool_name: "query_logs",
  // Add other necessary parameters here
});