---
格式版本: 2
标题: "AWS MCP Server adds a serverless capability for AWS Lambda functions"
原文链接: "https://aws.amazon.com/about-aws/whats-new/2026/09/aws-mcp-server-serverless/"
发布日期: "2026-09-04"
发布时间校准状态: "found"
发布时间需复核: "否"
发布时间来源: "llm:local:original_script_field"
发布时间证据: "postDateTime: 2026-09-04T16:31:00Z"
发布时间校准原因: "该候选来自原始脚本字段中的postDateTime，明确标注为发布时间，且与URL路径中的2026/09一致，满足发布时间判定优先级。"
发布时间校准置信度: "1"
发布时间候选数量: 1
发布时间严格候选数量: 0
发布时间原页读取状态: "source template page reused from URL open"
发布时间未找到原因: ""
发布时间校准时间: "2026-09-06T14:13:54+08:00"
发布时间仲裁状态: "confirmed"
发布时间仲裁尝试次数: 1
发布时间仲裁耗时毫秒: 4271
发现时间: "2026-09-06T13:50:01+08:00"
入库时间: "2026-09-06T06:14:00.281Z"
来源平台: "固定入口"
搜索渠道: "fixed_url"
搜索词: "https://aws.amazon.com/new"
匹配关键词:
  - "AI"
  - "latency"
相关厂家:
  - "AWS"
相关专家:
  []
内容类型: "网页"
抓取工具: "Free Fetch + Defuddle"
清洗工具: "Defuddle Markdown + Defuddle/Readability 正文提取"
原始附件:
  []
AI优质: "否"
AI打分: 28
AI分档: "非优质"
AI质检状态: "不通过"
AI打分理由: "正文主线是AWS MCP Server新增serverless能力，用于AI编码代理（Claude Code、Kiro）诊断Lambda函数及相关资源，属于云上应用运维工具更新，不涉及超节点、AI Rack、rack-scale AI或关键基础设施部件。来源为AWS官方新闻，权威性高，但主题相关性极低；技术细节仅限于MCP server诊断功能和API调用，无机架级架构、互连、供电、液冷等可复用机制；无AI机架产品、量产或部署信号；历史知识库无相关对照。命中强否决项'应用与模型效率'，且不满足任何高价值准入通道，必须判false。"
AI质检模型: "zj-deepseek-v4-flash"
AI质检时间: "2026-09-06T14:14:31+08:00"
AI主题相关性: 1
AI来源权威性: 15
AI新颖性: 2
AI技术细节: 3
AI商业部署信号: 0
AI完整性: 7
AI评分提示词版本: "v17-精简生产版"
AI评分提示词SHA256: "48fb9777f386026761b4873eaff30807694fb11e9b352d7c69bf2dfde750cc7d"
AI评分知识库版本: "knowledge_base_v1-20260819+runtime.96"
AI评分知识库SHA256: "0cae74ad2e30b227036c5952745542146844722958bc01868bbd0799ab59eeec"
AI评分知识库检索词: "[\"AWS\",\"https://aws.amazon.com/new\",\"NPO\",\"RAS\",\"MCP\",\"US\",\"API\",\"S3\",\"SNS\",\"SQS\",\"CLI\"]"
AI评分知识库命中: "[{\"id\":\"runtime-bf4039a0342d37545e9459a2\",\"title\":\"Most Neoclouds Suck At Security\",\"sourceType\":\"ai_excellent_article\",\"time\":\"2026-08-30\",\"matchedTerms\":[\"AWS\",\"RAS\",\"US\",\"API\",\"S3\",\"CLI\"],\"rank\":-18.293782273957333},{\"id\":\"runtime-2ce1cbad643d8367d4525b90\",\"title\":\"The Wild Wild West Of LEGO Datacenters\",\"sourceType\":\"ai_excellent_article\",\"time\":\"2026-07-29\",\"matchedTerms\":[\"AWS\",\"NPO\",\"RAS\",\"US\",\"API\",\"S3\",\"CLI\"],\"rank\":-11.428949201130695},{\"id\":\"runtime-d30249a09f7f187ba29fbbde\",\"title\":\"Korea’s Trillion-Dollar Sovereign AI Investment: Nvidia Wins, Hynix Loses\",\"sourceType\":\"ai_excellent_article\",\"time\":\"2026-09-01\",\"matchedTerms\":[\"AWS\",\"RAS\",\"US\",\"API\",\"S3\"],\"rank\":-10.695646428799263},{\"id\":\"runtime-f15ede7e8a5c3e80bd078fbd\",\"title\":\"Ultra-High Interactivity on NVIDIA GPUs? - TileRT InferenceX\",\"sourceType\":\"ai_excellent_article\",\"time\":\"2026-08-10\",\"matchedTerms\":[\"AWS\",\"RAS\",\"MCP\",\"US\",\"API\",\"S3\",\"CLI\"],\"rank\":-10.666604677935055},{\"id\":\"runtime-f189311ea2754e83ede89a96\",\"title\":\"Cerebras's Next Generation CS-4: Fast Just Got Faster\",\"sourceType\":\"ai_excellent_article\",\"time\":\"2026-08-19\",\"matchedTerms\":[\"AWS\",\"RAS\",\"US\",\"S3\"],\"rank\":-9.967694795375541}]"
采集批次: "2026年9月6日14点06分51秒"
采集批次ID: "20260906-140651-0a959a73"
去重键: "https://aws.amazon.com/about-aws/whats-new/2026/09/aws-mcp-server-serverless"
---

Today, [AWS Model Context Protocol Server](https://docs.aws.amazon.com/agent-toolkit/latest/userguide/mcp-server.html) (AWS MCP Server) added a serverless capability so that coding agents such as Claude Code and Kiro can efficiently diagnose issues with your Lambda functions. The serverless capability helps you troubleshoot your running Lambda functions and their connected resources.

The AWS MCP Server, available through the [Agent Toolkit for AWS](https://aws.amazon.com/products/developer-tools/agent-toolkit-for-aws/) or as a standalone installation, is a managed service that gives AI coding agents secure access to AWS services. With the new serverless capability in the AWS MCP Server, your coding agent inspects your Lambda function and its connected resources across Amazon API Gateway, Amazon EventBridge, Amazon S3, Amazon DynamoDB, Amazon SNS, Amazon SQS, and AWS Step Functions. The agent can correlate error signals against a 7-day baseline to pinpoint what changed, surface recurring errors to identify trends, retrieve the deployed configuration of your function and connected resources, provide a timeline of recent changes to track what happened, and analyze service latency across connected resources. As the agent gets comprehensive data in a single call, it consumes fewer tokens compared to orchestrating multiple API calls.

To get started, configure the [Agent toolkit for AWS](https://aws.amazon.com/products/developer-tools/agent-toolkit-for-aws/) by running ‘aws configure agent-toolkit’ from the AWS CLI, or enable the [AWS MCP Server](https://docs.aws.amazon.com/agent-toolkit/latest/userguide/getting-started-aws-mcp-server.html) directly.

The AWS MCP Server can access services in all commercial [AWS Regions](https://aws.amazon.com/about-aws/global-infrastructure/regional-product-services/), while the AWS MCP Server itself runs in the US East (N. Virginia) and Europe (Frankfurt) Regions. The serverless diagnostic capabilities in the AWS MCP Server are available at no additional cost. To learn more, see the [user guide](https://docs.aws.amazon.com/agent-toolkit/latest/userguide/capabilities.html).