publicPublicdnsLocal runtime

aws-cost-explorer-and-amazon-bedrock-model-invocation-logs-mcp-server-and-client

该项目是一个基于Anthropic MCP协议的AWS成本分析工具，通过Claude模型提供自然语言交互界面，可查询AWS Cost Explorer和Bedrock模型调用日志数据，支持本地和远程部署。

article

README

🚀 AWS 成本计算工具说明

该工具借助 FastMCP 搭建了一个基于 AWS 费用数据的费用计算服务。它能通过 API 获取并分析费用数据，做费用预测，支持多维度查询费用信息，还能在费用超阈值时发出警戒通知。

🚀 快速开始

此文档涵盖了 AWS 成本计算工具的详细信息，可帮助你快速了解该工具的功能和使用方法。

✨ 主要特性

费用数据分析：通过 AWS Cost Explorer API 获取并分析费用数据。
费用预测模型：提供基于历史数据的费用预测功能。
多维度查询：支持按标签、资源类型、时间范围等多种维度查询费用信息。
警戒通知系统：当费用超过预设阈值时触发警戒通知。

📄 许可证

本项目采用 MIT 许可证。

👥 项目贡献者

主要开发人员: [your name]
贡献者: [contributor names]

📝 文档生成说明

本 README 文件由以下工具生成：

GitIngest：将项目文本输入 Claude AI 进行整理和总结。
Claude：负责内容的组织和文档的生成。

badge

Publisher / author / owner

person

MCP-MirrorMCP Server

open_in_newSource repository

Detail synced2026-05-20 04:06:11IDmcp-mirror-aarora79-aws-cost-explorer-mcp-server

data_object

Technical config

server_config

{
  "rating": 2,
  "dev_lang": "python",
  "mcp_install": "{\n  \"mcpServers\": {\n    \"aws-cost-explorer\": {\n      \"command\": \"docker\",\n      \"args\": [ \"run\", \"-i\", \"--rm\", \"-e\", \"AWS_ACCESS_KEY_ID\", \"-e\", \"AWS_SECRET_ACCESS_KEY\", \"-e\", \"AWS_REGION\", \"-e\", \"BEDROCK_LOG_GROUP_NAME\", \"-e\", \"MCP_TRANSPORT\", \"aws-cost-explorer-mcp:latest\" ],\n      \"env\": {\n        \"AWS_ACCESS_KEY_ID\": \"YOUR_ACCESS_KEY_ID\",\n        \"AWS_SECRET_ACCESS_KEY\": \"YOUR_SECRET_ACCESS_KEY\",\n        \"AWS_REGION\": \"us-east-1\",\n        \"BEDROCK_LOG_GROUP_NAME\": \"YOUR_CLOUDWATCH_BEDROCK_MODEL_INVOCATION_LOG_GROUP_NAME\",\n        \"MCP_TRANSPORT\": \"stdio\"\n      }\n    }\n  }\n}\n\n{\n  \"mcpServers\": {\n    \"aws_cost_explorer\": {\n      \"command\": \"uv\",\n      \"args\": [\n          \"--directory\",\n          \"/path/to/aws-cost-explorer-mcp-server\",\n          \"run\",\n          \"server.py\"\n      ],\n      \"env\": {\n        \"AWS_ACCESS_KEY_ID\": \"YOUR_ACCESS_KEY_ID\",\n        \"AWS_SECRET_ACCESS_KEY\": \"YOUR_SECRET_ACCESS_KEY\",\n        \"AWS_REGION\": \"us-east-1\",\n        \"BEDROCK_LOG_GROUP_NAME\": \"YOUR_CLOUDWATCH_BEDROCK_MODEL_INVOCATION_LOG_GROUP_NAME\",\n        \"MCP_TRANSPORT\": \"stdio\"\n      }\n    }\n  }\n}"
}

Discovery labels

Categories

Infra & Security

Tags

AWS成本分析MCP协议自然语言交互Bedrock监控

Locales

zh_cn

help

Runtime guide

cloud

Hosted runtime

Hosted servers run from a provider-managed environment. You usually connect the MCP client to the hosted endpoint or follow the provider's authorization flow, without keeping a local process alive

Open provider connection page
Authorize or copy endpoint
Connect from your MCP client

terminal

Local runtime / other methods

Local servers run on your own machine or infrastructure. You normally copy the server_config into your MCP client, install the required package, and provide env variables from env_schema when needed

Copy server_config
Install required package
Fill env variables and restart client