Azure Usage

Provides an MCP server to analyze Azure CSV usage data, generate cost summaries, and answer natural language queries.

python

1

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "rithik-perera-codecrunchmcp": {
      "command": "python",
      "args": [
        "claude_mcp.py"
      ]
    }
  }
}

You run an MCP server that analyzes Azure usage data from CSV files, returning cost insights, summaries, and visualizations. It lets you answer natural language questions about Azure usage and costs, enabling quick understanding of where your money goes and which services and regions drive the highest spend.

How to use

To use Azure Usage MCP Server, start the local MCP server and connect to it with your MCP client. You can ask questions like which regions incur the most cost, what your top services are, or to generate visuals and summaries of your Azure usage data. Your queries are processed against the Azure CSV you provide, and the server responds with actionable insights.

How to install

Prerequisites: Python 3.8+ and pip are required.

Install the required dependencies from the project root.

pip install -r requirements.txt

Place your Azure usage CSV file in a data directory. The default file name is BCAzureUsage 1.csv.

Start the MCP server to begin listening for queries.

python claude_mcp.py

Configuration and usage notes

The server is configured for MCP clients with a simple local execution model. The configuration example shows how to register a local MCP process that runs Python code and exposes the MCP interface.

{
  "mcpServers": {
    "azure-usage-analyzer": {
      "command": "python",
      "args": ["claude_mcp.py"],
      "cwd": "path/to/mcp-server",
      "env": {}
    }
  }
}

Notes and tips

There are no special environment variables required to run the server in the provided setup. If you need to adjust the behavior, you can modify the command arguments or the working directory accordingly.

Available tools

analyze_csv

Parses the Azure usage CSV data and prepares it for analytics, including data cleaning and normalization.

generate_cost_summaries

Creates cost summaries by service, region, and time period to highlight spending patterns.

visualizations

Generates visual representations (charts/graphs) of cost and usage metrics.

top_services_by_cost

Identifies the services that contribute the most to overall Azure spend.

nlp_query

Processes natural language questions about Azure usage and returns structured insights.