Skip to main content

AWS Case Drafter

MCP server,让客户在 AI 对话中自然地完成 AWS Support 工单的起草与提交。

不需要离开对话窗口,不需要手动整理信息 —— 一句"帮我开个工单"即可。

当前支持范围:目前聚焦 AWS 中国区(aws-cn,北京 / 宁夏)。已针对 API Gateway、Lambda、IoT Core 三个服务做了诊断信息收集与工单模板的特别适配;其他服务可用通用模板起草。

解决什么

  • 跳出对话:不再需要切回控制台手动填写工单
  • 重复劳动:对话中已经说过的问题,不用重新组织一遍
  • 反复补充:自动收集 TSE 需要的诊断信息,减少来回追问

MCP 工具

工具 功能 凭证
fetch_lambda_context Lambda 函数 ARN + 最近错误日志 需要
fetch_iot_context IoT Core 诊断信息(V2日志/加密配置/自定义域名/Command/Topic Rule) 需要
fetch_apigw_context API Gateway REST API 日志 + VPC Link/Usage Plan 需要
draft_support_case 根据诊断数据生成结构化工单草稿 不需要
submit_support_case 客户确认后通过 Support API 提交工单 需要 + Business Plan

快速开始

1. 准备 uv 运行环境

多数 AI 客户端已集成 uv。Cherry Studio 在 设置 → MCP 服务器 点"安装"即可(用其内置 uv)。

2. 新建 stdio 类型的 MCP 服务器

在客户端 MCP 配置中添加:

  • 命令:uvx
  • 参数:aws-case-drafter@latest
  • 包管理源:国内建议选清华/阿里云镜像加速

3. 配置环境变量

支持 AWS SDK 标准环境变量:

  • 已配置 AWS CLI 时:AWS_PROFILE(profile 中一般已包含 region)
  • 未配 CLI 时:AWS_ACCESS_KEY_ID + AWS_SECRET_ACCESS_KEY + AWS_REGION

凭证可选 —— 无凭证时退化为仅基于对话历史生成草稿。

Cherry Studio MCP 配置

设计亮点

  • 适配多模型:工具描述简洁直观,适配 DeepSeek、千问等国产模型
  • 自动脱敏:日志中的敏感信息(IP、密钥、邮箱)在进入工单前自动脱敏
  • 日志自动附件:大量错误日志写入临时文件随工单提交,正文保持简洁

技术栈

  • Python 3.10+
  • MCP SDK (FastMCP)
  • boto3
  • 打包:hatchling → PyPI → uvx 运行

兼容客户端

  1. Cherry Studio + DeepSeek/千问 (国内首选)
  2. ChatBox + 任意模型 API
  3. Claude Desktop / Kiro / Cursor

License

Apache-2.0

Metadata

Release files for aws-case-drafter 0.2.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for aws-case-drafter 0.2.2
File Size Uploaded Provenance
aws_case_drafter-0.2.2.tar.gz 263.2 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for aws-case-drafter 0.2.2
File Interpreter ABI Platform
aws_case_drafter-0.2.2-py3-none-any.whl Python 3 none any Details

Total release size: 345.1 kB

Release files / aws_case_drafter-0.2.2.tar.gz

Download URL aws_case_drafter-0.2.2.tar.gz
Size 263.2 kB
Tags Source
SHA-256 checksum
How to use checksums
55d47fc2f46066bb434b39abea75d4e0a8186991e40b6e0ccf492c89ed07308a
BLAKE2b-256 checksum
How to use checksums
d4aaac0358d5ebda2407a4f4b9f2dee630909271f2e59666fff75824f82d2bae
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.2

Release files / aws_case_drafter-0.2.2-py3-none-any.whl

Download URL aws_case_drafter-0.2.2-py3-none-any.whl
Size 82.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
a4f21c2603b3b56e99552704975ab3461d9a1d69d53e4db7e4273411d743f4c7
BLAKE2b-256 checksum
How to use checksums
15e7c40c567bafce0b89ffd16bdaf6f620fe6392fd885188af32575d6d01567d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.2

Security for aws-case-drafter 0.2.2

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page