Azure Pricing MCP Server
Provides AI assistants with real-time access to Azure retail pricing information, enabling price searches, regional cost comparisons, monthly bill estimates, and SKU discovery through natural language queries.
README
Azure Pricing MCP Server 💰
A Model Context Protocol (MCP) server that provides AI assistants with real-time access to Azure retail pricing information. Query VM prices, compare costs across regions, estimate monthly bills, and discover available SKUs—all through natural language.
<p align="center"> <img src="https://img.shields.io/badge/Azure-Pricing-0078D4?style=for-the-badge&logo=microsoft-azure&logoColor=white" alt="Azure Pricing"/> <img src="https://img.shields.io/badge/VS_Code-MCP-007ACC?style=for-the-badge&logo=visual-studio-code&logoColor=white" alt="VS Code MCP"/> </p>
🚀 Quick Start
# 1. Clone the repository
git clone https://github.com/msftnadavbh/AzurePricingMCP.git
cd azure-pricing-mcp
# 2. Set up virtual environment
python -m venv .venv
source .venv/bin/activate # Linux/Mac
# .venv\Scripts\activate # Windows
# 3. Install dependencies
pip install -r requirements.txt
# 4. Test the server
python -m azure_pricing_server
Then configure your AI assistant (VS Code, Claude Desktop, etc.) to use the MCP server.
✨ Features
| Feature | Description |
|---|---|
| 🔍 Price Search | Search Azure prices with filters (service, region, SKU, price type) |
| ⚖️ Price Comparison | Compare costs across regions or between different SKUs |
| 💡 Cost Estimation | Calculate monthly/yearly costs based on usage hours |
| 💰 Savings Plans | View 1-year and 3-year savings plan pricing |
| 🎯 Smart SKU Discovery | Fuzzy matching for service names ("vm" → "Virtual Machines") |
| 🌍 Multi-Currency | Support for USD, EUR, GBP, and more |
| 📊 Real-time Data | Live data from Azure Retail Prices API |
| 🏷️ Customer Discounts | Apply discount percentages to all pricing queries |
🛠️ Available Tools
| Tool | Description |
|---|---|
azure_price_search |
Search Azure retail prices with flexible filtering |
azure_price_compare |
Compare prices across regions or SKUs |
azure_cost_estimate |
Estimate costs based on usage patterns |
azure_discover_skus |
List available SKUs for a specific service |
azure_sku_discovery |
Intelligent SKU discovery with fuzzy name matching |
get_customer_discount |
Get customer discount information |
📋 Installation
Prerequisites
- Python 3.10+
- pip (Python package manager)
Option 1: Automated Setup
# Windows PowerShell
.\setup.ps1
# Linux/Mac/Cross-platform
python setup.py
Option 2: Manual Setup
# Clone repository
git clone https://github.com/msftnadavbh/AzurePricingMCP.git
cd azure-pricing-mcp
# Create virtual environment
python -m venv .venv
# Activate virtual environment
source .venv/bin/activate # Linux/Mac
.venv\Scripts\activate # Windows
# Install dependencies
pip install -r requirements.txt
Dependencies
mcp>=1.0.0
aiohttp>=3.9.0
pydantic>=2.0.0
requests>=2.31.0
🖥️ VS Code Integration
Step 1: Install GitHub Copilot
Ensure you have the GitHub Copilot extension installed.
Step 2: Configure MCP Server
Create or edit .vscode/mcp.json in your workspace:
{
"servers": {
"azure-pricing": {
"type": "stdio",
"command": "/absolute/path/to/azure-pricing-mcp/.venv/bin/python",
"args": ["-m", "azure_pricing_server"]
}
}
}
Windows users: Use the full path with forward slashes or escaped backslashes:
"command": "C:/path/to/azure-pricing-mcp/.venv/Scripts/python.exe"
Step 3: Restart MCP Server
- Open Command Palette (
Ctrl+Shift+P/Cmd+Shift+P) - Run: MCP: List Servers
- Click the refresh/restart button next to
azure-pricing
Step 4: Use in Copilot Chat
Open Copilot Chat and ask:
What's the price of Standard_D32s_v6 in East US 2?
You'll see the MCP tools being invoked with real Azure pricing data!
🤖 Claude Desktop Integration
Add to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"azure-pricing": {
"command": "python",
"args": ["-m", "azure_pricing_server"],
"cwd": "/path/to/azure-pricing-mcp"
}
}
}
💬 Example Queries
Once configured, ask your AI assistant:
| Query Type | Example |
|---|---|
| Basic Pricing | "What's the price of a D4s_v3 VM in West US 2?" |
| Multi-Node | "Price for 20 Standard_D32s_v6 nodes in East US 2" |
| Comparison | "Compare VM prices between East US and West Europe" |
| Cost Estimate | "Estimate monthly cost for D8s_v5 running 12 hours/day" |
| SKU Discovery | "What App Service plans are available?" |
| Savings Plans | "Show savings plan options for virtual machines" |
| Storage | "What are the blob storage pricing tiers?" |
Sample Response
Standard_D32s_v6 in East US 2:
- Linux On-Demand: $1.613/hour → $23,550/month for 20 nodes
- 1-Year Savings: $1.113/hour → $16,250/month (31% savings)
- 3-Year Savings: $0.742/hour → $10,833/month (54% savings)
🧪 Testing
Verify Installation
# Run the server directly (should start without errors)
python -m azure_pricing_server
# Run tests
python test_mcp_server.py
Test MCP Connection in VS Code
- Open Command Palette → MCP: List Servers
- Verify
azure-pricingshows 6 tools - Open Copilot Chat and ask a pricing question
🤝 Contributing
We welcome contributions! Here's how to get started:
Development Setup
# Fork and clone the repository
git clone https://github.com/YOUR_USERNAME/azure-pricing-mcp.git
cd azure-pricing-mcp
# Create development environment
python -m venv .venv
source .venv/bin/activate
# Install dependencies
pip install -r requirements.txt
# Make your changes
# ...
# Test your changes
python test_mcp_server.py
Contribution Guidelines
- Fork the repository
- Create a branch for your feature (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add amazing feature') - Push to your branch (
git push origin feature/amazing-feature) - Open a Pull Request
Code Style
- Follow PEP 8 guidelines
- Add type hints for function parameters and return values
- Include docstrings for public functions
- Test your changes before submitting
Ideas for Contributions
- [ ] Add support for Azure Reserved Instances pricing
- [ ] Implement caching for frequently requested prices
- [ ] Add more currency support
- [ ] Create unit tests for all tools
- [ ] Add support for Azure Government/China regions
- [ ] Implement price alerts/notifications
📁 Project Structure
azure-pricing-mcp/
├── azure_pricing_server.py # Main MCP server implementation
├── __init__.py # Package initialization
├── __main__.py # Module entry point
├── requirements.txt # Python dependencies
├── setup.py # Automated setup script
├── setup.ps1 # PowerShell setup script
├── test_mcp_server.py # Test suite
├── README.md # This file
├── QUICK_START.md # Quick start guide
├── USAGE_EXAMPLES.md # Detailed usage examples
├── config_examples.json # Example configurations
└── .vscode/
└── mcp.json # VS Code MCP configuration
🔌 API Reference
This server uses the Azure Retail Prices API:
https://prices.azure.com/api/retail/prices
No authentication required - The Azure Retail Prices API is publicly accessible.
📚 Additional Documentation
- QUICK_START.md - Step-by-step setup guide
- USAGE_EXAMPLES.md - Detailed usage examples and API responses
- config_examples.json - Example configurations
⚠️ Troubleshooting
Tools not appearing in VS Code
- Check Python syntax: Ensure no syntax errors in
azure_pricing_server.py - Verify path: Use absolute paths in
.vscode/mcp.json - Restart server: Command Palette → MCP: List Servers → Restart
"No module named 'mcp'"
# Ensure you're in the virtual environment
source .venv/bin/activate
pip install mcp>=1.0.0
Connection errors
- Check your internet connection
- The Azure Pricing API may rate-limit requests (automatic retry is built-in)
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
🙏 Acknowledgments
- Original Author: @charris-msft
- Current Maintainer + Version 2.0: @msftnadavbh
- Model Context Protocol - The protocol that makes this possible
- Azure Retail Prices API - Microsoft's public pricing API
- Contributors and the open-source community
📬 Support
- Issues: GitHub Issues
- Discussions: GitHub Discussions
<p align="center"> Made with ❤️ for the Azure community </p>
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.