Azure Data Explorer MCP Server

What does “Azure Data Explorer” MCP Server do?

The Azure Data Explorer (ADX) MCP Server is a Model Context Protocol (MCP) server that enables AI assistants to seamlessly connect with Azure Data Explorer/Eventhouse clusters and databases. Through standardized MCP interfaces, it empowers AI tools and agents to execute KQL (Kusto Query Language) queries, explore database resources, retrieve table schemas, sample data, and access table statistics. The server supports interactive tools and authentication via Azure credentials, making it possible to securely manage and analyze large-scale data directly from AI-driven workflows. This integration enhances developer productivity by automating data exploration, querying, and management within Azure Data Explorer environments.

List of Prompts

No explicit prompt templates are mentioned in the repository.

List of Resources

• Tables listing
  • Enables AI assistants to list all tables in the configured Azure Data Explorer database.
• Table schema
  • Provides schema information for a selected table, including column names and types.
• Table data sampling
  • Allows sampling of data rows from any given table to provide context or previews for downstream tasks.
• Table statistics
  • Retrieves detailed statistics or metadata for tables, such as row counts and size.

List of Tools

• KQL Query Execution
  • Execute Kusto Query Language (KQL) queries against the connected Azure Data Explorer database.
• List Tables
  • Retrieve a list of all tables available in the specified database.
• View Table Schema
  • Access and display the schema (structure) of a selected table.
• Sample Table Data
  • Fetch a small sample of data from a table for inspection or context.
• Get Table Statistics
  • Obtain statistics or high-level details about a table, such as row counts and storage info.

Use Cases of this MCP Server

• Database Management
  • Automate table listing, schema retrieval, and data sampling, streamlining database exploration and management for developers and data scientists.
• Interactive Data Analysis
  • Quickly execute KQL queries and fetch results for exploratory analysis, making it easier for AI assistants and users to derive insights from large datasets.
• AI-Powered Data Exploration
  • Enable LLMs or AI agents to browse, summarize, and contextualize data from Azure Data Explorer, supporting use cases like report generation or anomaly detection.
• Integration with DevOps Pipelines
  • Leverage the MCP server in CI/CD processes to validate data, run health checks, and ensure data readiness before deployments.
• Security-Aware Data Operations
  • Utilize Azure authentication and workload identity support to ensure secure, compliant access to sensitive databases within organizational boundaries.

How to set it up

Windsurf

1. Ensure Node.js and necessary prerequisites are installed.
2. Open your Windsurf configuration file.
3. Add the Azure Data Explorer MCP server with the following JSON snippet:

   {
     "mcpServers": {
       "adx-mcp": {
         "command": "npx",
         "args": ["@adx/mcp-server@latest"]
       }
     }
   }
   

4. Save the configuration and restart Windsurf.
5. Verify that the MCP server is running and accessible.

Securing API keys (Windsurf)

{
  "mcpServers": {
    "adx-mcp": {
      "command": "npx",
      "args": ["@adx/mcp-server@latest"],
      "env": {
        "ADX_CLUSTER_URL": "https://yourcluster.region.kusto.windows.net",
        "ADX_DATABASE": "your_database"
      },
      "inputs": {}
    }
  }
}

Claude

1. Install the necessary dependencies for MCP integration in Claude.
2. Locate Claude’s configuration file.
3. Add the following MCP server configuration:

   {
     "mcpServers": {
       "adx-mcp": {
         "command": "npx",
         "args": ["@adx/mcp-server@latest"]
       }
     }
   }
   

4. Save changes and restart Claude.
5. Confirm the server connection is working.

Securing API keys (Claude)

{
  "mcpServers": {
    "adx-mcp": {
      "command": "npx",
      "args": ["@adx/mcp-server@latest"],
      "env": {
        "ADX_CLUSTER_URL": "https://yourcluster.region.kusto.windows.net",
        "ADX_DATABASE": "your_database"
      },
      "inputs": {}
    }
  }
}

Cursor

1. Install Node.js and ensure Cursor can access external MCP servers.
2. Open the Cursor MCP server configuration file.
3. Insert the MCP server JSON as below:

   {
     "mcpServers": {
       "adx-mcp": {
         "command": "npx",
         "args": ["@adx/mcp-server@latest"]
       }
     }
   }
   

4. Save and restart Cursor.
5. Test the MCP integration by running a sample KQL query.

Securing API keys (Cursor)

{
  "mcpServers": {
    "adx-mcp": {
      "command": "npx",
      "args": ["@adx/mcp-server@latest"],
      "env": {
        "ADX_CLUSTER_URL": "https://yourcluster.region.kusto.windows.net",
        "ADX_DATABASE": "your_database"
      },
      "inputs": {}
    }
  }
}

Cline

1. Confirm you have Node.js and Cline set up.
2. Edit your Cline MCP configuration file.
3. Add the server as follows:

   {
     "mcpServers": {
       "adx-mcp": {
         "command": "npx",
         "args": ["@adx/mcp-server@latest"]
       }
     }
   }
   

4. Save the file and restart Cline.
5. Ensure connectivity by running a database schema query.

Securing API keys (Cline)

{
  "mcpServers": {
    "adx-mcp": {
      "command": "npx",
      "args": ["@adx/mcp-server@latest"],
      "env": {
        "ADX_CLUSTER_URL": "https://yourcluster.region.kusto.windows.net",
        "ADX_DATABASE": "your_database"
      },
      "inputs": {}
    }
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "adx-mcp": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “adx-mcp” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Based on the information provided and its completeness, this MCP server rates around 7/10. It covers all major MCP requirements for Azure Data Explorer, but lacks explicit prompt templates and details about roots support.

MCP Score