Azure Pricing MCP Server
Enables AI assistants to query Azure retail pricing, compare costs, estimate bills, and analyze reserved instances, with additional tools for spot VMs, orphaned resources, PTU sizing, Databricks DBU, and GitHub pricing.
README
Azure Pricing MCP Server π°
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 SKUsβall through natural language.
π Quick Start
# Clone and setup
git clone https://github.com/alexwoods711/AzureMCPPricing.git
cd AzureMCPPricing
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install -r requirements.txt
# Test the server
python -m azure_pricing_mcp
Then configure your AI assistant. See Integrations.
β¨ Features
- Price Search - Query Azure prices with flexible filters
- Price Comparison - Compare costs across regions or SKUs
- Cost Estimation - Calculate monthly/yearly costs
- Reserved Instances - Compare RI pricing with break-even analysis
- Region Recommendations - Find the cheapest regions for any SKU
- SKU Discovery - Fuzzy matching for service names
- Retirement Warnings - Alerts for retiring VM SKUs
- Spot VM Intelligence - Eviction rates and price history (requires Azure auth)
- Orphaned Resources - Detect unused resources with real cost calculation (requires Azure auth)
- PTU Sizing - Estimate Provisioned Throughput Units for Azure OpenAI deployments
- Databricks DBU Pricing - Search DBU rates, estimate costs, compare workloads
- GitHub Pricing - Full GitHub pricing catalog + cost estimation (Plans, Copilot, Actions, Security)
π οΈ Tools
19 tools available for AI assistants:
azure_price_search- Search retail pricesazure_price_compare- Compare across regions/SKUsazure_ri_pricing- Reserved Instance pricingazure_cost_estimate- Usage-based cost estimationazure_region_recommend- Find cheapest regionsazure_discover_skus/azure_sku_discovery- SKU lookupget_customer_discount- Customer discount informationspot_eviction_rates/spot_price_history/simulate_eviction- Spot VM toolsfind_orphaned_resources- Detect orphaned resources with cost analysisazure_ptu_sizing- Estimate PTUs for Azure OpenAI deploymentsazure_network_cost_estimate- Network cost planner (bandwidth tiers, NAT Gateway, Private Link)databricks_dbu_pricing/databricks_cost_estimate/databricks_compare_workloads- Databricks DBU pricinggithub_pricing/github_cost_estimate- GitHub pricing catalog and cost estimation
π Installation
Docker (Easiest):
docker build -t azure-pricing-mcp .
docker run -i azure-pricing-mcp
Python:
pip install -r requirements.txt
π Full installation guide β
π Integrations
Works with any MCP-compatible AI assistant:
- VS Code with GitHub Copilot
- Claude Desktop
π Project Structure
AzureMCPPricing/
βββ src/azure_pricing_mcp/ # Main package
β βββ server.py # MCP server
β βββ handlers.py # Tool handlers
β βββ client.py # Azure API client
β βββ config.py # Pricing data & constants
β βββ tools.py # Core tool definitions
β βββ formatters.py # Response formatters
β βββ models.py # Data models
β βββ services/ # Business logic
β βββ databricks/ # Databricks DBU tools
β βββ github_pricing/ # GitHub pricing tools
βββ tests/ # Test suite (9 files, 236+ tests)
βββ docs/ # Documentation
βββ scripts/ # Setup & debug scripts
π 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.
π€ Contributing
We welcome contributions! See CONTRIBUTING.md for setup instructions, code style, and PR process.
π Documentation
| Document | Description |
|---|---|
| INSTALL.md | Installation guide |
| docs/FEATURES.md | Feature details |
| docs/TOOLS.md | Tool documentation |
| docs/INTEGRATIONS.md | VS Code & Claude setup |
| docs/USAGE_EXAMPLES.md | Detailed examples |
| docs/ORPHANED_RESOURCES.md | Orphaned resources guide |
| CHANGELOG.md | Version history |
π License
MIT License - see LICENSE for details.
π Acknowledgments
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.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
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.