AWS Pricing Calculator MCP Server
MCP server that provides tools for automating AWS Pricing Calculator estimate generation.
README
AWS Pricing Calculator MCP Server
MCP server that provides tools for automating AWS Pricing Calculator estimate generation.
Features
- discover_services: Fetch service schemas from AWS Pricing Calculator
- build_estimate: Build complete estimate JSON from specification
- save_estimate: Save estimate to AWS and get shareable URL
- get_region_name: Convert AWS region codes to display names
Installation
Prerequisites
- Python 3.10 or higher
- uv package manager
Install uv
# macOS/Linux
curl -LsSf https://astral.sh/uv/install.sh | sh
# Windows
powershell -c "irm https://astral.sh/uv/install.ps1 | iex"
# Or via pip
pip install uv
Run the MCP Server
The server is designed to be run via uvx directly from GitHub (no installation needed):
uvx --from git+https://github.com/elchanio-76/aws-pricing-calculator-mcp aws-pricing-calculator-mcp
Or install it globally:
uv tool install git+https://github.com/elchanio-76/aws-pricing-calculator-mcp
Once published to PyPI, you can use the simpler form:
uvx aws-pricing-calculator-mcp
Usage with Kiro
This MCP server is designed to work with the AWS Pricing Calculator Power for Kiro.
Configuration
Add to your Kiro MCP configuration (.kiro/settings/mcp.json):
{
"mcpServers": {
"aws-pricing-calculator": {
"command": "uvx",
"args": ["--from", "git+https://github.com/elchanio-76/aws-pricing-calculator-mcp", "aws-pricing-calculator-mcp"],
"disabled": false
}
}
}
Or if published to PyPI:
{
"mcpServers": {
"aws-pricing-calculator": {
"command": "uvx",
"args": ["aws-pricing-calculator-mcp"],
"disabled": false
}
}
}
Or install the Kiro Power which includes this configuration automatically.
Tools
discover_services
Fetch AWS Pricing Calculator service schemas.
Parameters:
service_codes(optional): Array of service codes to discover
Example:
{
"service_codes": ["ec2Enhancement", "amazonS3"]
}
build_estimate
Build complete estimate JSON from specification.
Parameters:
spec(required): Estimate specification with groups and services
Example:
{
"spec": {
"name": "My Estimate",
"groups": [
{
"name": "Production",
"services": [...]
}
]
}
}
save_estimate
Save estimate to AWS and get shareable URL.
Parameters:
estimate(required): Complete estimate JSON from build_estimate
get_region_name
Convert AWS region code to display name.
Parameters:
region_code(required): AWS region code (e.g., "us-east-1")
Development
Setup
# Clone the repository
git clone https://github.com/elchanio-76/aws-pricing-calculator-mcp.git
cd aws-pricing-calculator-mcp
# Install dependencies
uv pip install -e .
Testing
# Run tests
python3 test_mcp_server.py
# Test via stdio
python3 test_mcp_stdio.py
Running Locally
python3 -m mcp_server.server
Architecture
The MCP server wraps existing Python scripts that handle:
- CloudFront API calls for service definitions
- Estimate JSON generation
- AWS Save API integration
All scripts use curl subprocess to avoid Python SSL issues with CloudFront.
License
MIT
Credits
Inspired by aws-pricing-calculator by Ian Qin. Tools have been created by converting scripts from that repo. Power.md and steering docs are based on the original repo with minor changes to make them compatible with Kiro Powers.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。