本文属于机器翻译版本。若本译文内容与英语原文存在差异，则一律以英文原文为准。 # 故障排除代理的设置 **注意** Apache Spark 故障排除代理使用跨区域推理来处理自然语言请求并生成响应。欲了解更多详情，请参阅[Apache Spark 故障排除代理的跨区域处理](spark-troubleshooting-cross-region-processing.md)。Amazon SageMaker Unified Studio MCP 服务器处于预览状态，可能会发生变化。 ## 先决条件 在我们开始与 Kiro CLI 集成的设置过程之前，请确保在您的工作站上安装了以下内容： + [安装 Amazon CLI](https://docs.amazonaws.cn/cli/latest/userguide/getting-started-install.html) + [安装 Python 3.10\$1](https://www.python.org/downloads/release/python-3100/) + [安装适用于 [MCP 代理](https://github.com/aws/mcp-proxy-for-aws?tab=readme-ov-file)的`uv`软件包管理器](https://docs.astral.sh/uv/getting-started/installation/) Amazon + [安装 Kiro CLI](https://kiro.dev/docs/cli/) + Amazon 配置的本地证书（通过 [Amazon CLI](https://docs.amazonaws.cn/cli/latest/userguide/cli-chap-configure.html)、环境变量或 IAM 角色）-用于本地操作，例如上传升级后的作业工件以执行 EMR 验证任务。 ## 安装资源 您可以使用 Amazon CloudFormation 模板为 MCP 服务器设置资源。这些模板是您应修改以满足要求的示例。该模板为故障排除过程创建了以下资源： 1. IAM 角色，该角色具有调用 MCP 服务器的权限以及所选平台的故障排除过程所需的权限。 选择下表中的 **Launch Stack (启动堆栈)** 按钮之一。这将在相应区域的主 Amazon CloudFormation 机上启动堆栈。 | Region | 启动 | | --- | --- | | 美国东部（俄亥俄州） | [https://console.amazonaws.cn/cloudformation/home?region=us-east-2#/stacks/new?templateURL=https%3A%2F%2Fsmus-mcp-cfn-template-prod-us-east-2.s3.us-east-2.amazonaws.com%2Fcloudformation%2Fspark-troubleshooting-mcp-setup.yaml&stackName=spark-troubleshooting-mcp-setup](https://console.amazonaws.cn/cloudformation/home?region=us-east-2#/stacks/new?templateURL=https%3A%2F%2Fsmus-mcp-cfn-template-prod-us-east-2.s3.us-east-2.amazonaws.com%2Fcloudformation%2Fspark-troubleshooting-mcp-setup.yaml&stackName=spark-troubleshooting-mcp-setup) | | 美国东部（弗吉尼亚州北部） | [https://console.amazonaws.cn/cloudformation/home?region=us-east-1#/stacks/new?templateURL=https%3A%2F%2Fsmus-mcp-cfn-template-prod-us-east-1.s3.us-east-1.amazonaws.com%2Fcloudformation%2Fspark-troubleshooting-mcp-setup.yaml&stackName=spark-troubleshooting-mcp-setup](https://console.amazonaws.cn/cloudformation/home?region=us-east-1#/stacks/new?templateURL=https%3A%2F%2Fsmus-mcp-cfn-template-prod-us-east-1.s3.us-east-1.amazonaws.com%2Fcloudformation%2Fspark-troubleshooting-mcp-setup.yaml&stackName=spark-troubleshooting-mcp-setup) | | 美国西部（俄勒冈） | [https://console.amazonaws.cn/cloudformation/home?region=us-west-2#/stacks/new?templateURL=https%3A%2F%2Fsmus-mcp-cfn-template-prod-us-west-2.s3.us-west-2.amazonaws.com%2Fcloudformation%2Fspark-troubleshooting-mcp-setup.yaml&stackName=spark-troubleshooting-mcp-setup](https://console.amazonaws.cn/cloudformation/home?region=us-west-2#/stacks/new?templateURL=https%3A%2F%2Fsmus-mcp-cfn-template-prod-us-west-2.s3.us-west-2.amazonaws.com%2Fcloudformation%2Fspark-troubleshooting-mcp-setup.yaml&stackName=spark-troubleshooting-mcp-setup) | | 亚太地区（东京） | [https://console.amazonaws.cn/cloudformation/home?region=ap-northeast-1#/stacks/new?templateURL=https%3A%2F%2Fsmus-mcp-cfn-template-prod-ap-northeast-1.s3.ap-northeast-1.amazonaws.com%2Fcloudformation%2Fspark-troubleshooting-mcp-setup.yaml&stackName=spark-troubleshooting-mcp-setup](https://console.amazonaws.cn/cloudformation/home?region=ap-northeast-1#/stacks/new?templateURL=https%3A%2F%2Fsmus-mcp-cfn-template-prod-ap-northeast-1.s3.ap-northeast-1.amazonaws.com%2Fcloudformation%2Fspark-troubleshooting-mcp-setup.yaml&stackName=spark-troubleshooting-mcp-setup) | | 欧洲地区（爱尔兰） | [https://console.amazonaws.cn/cloudformation/home?region=eu-west-1#/stacks/new?templateURL=https%3A%2F%2Fsmus-mcp-cfn-template-prod-eu-west-1.s3.eu-west-1.amazonaws.com%2Fcloudformation%2Fspark-troubleshooting-mcp-setup.yaml&stackName=spark-troubleshooting-mcp-setup](https://console.amazonaws.cn/cloudformation/home?region=eu-west-1#/stacks/new?templateURL=https%3A%2F%2Fsmus-mcp-cfn-template-prod-eu-west-1.s3.eu-west-1.amazonaws.com%2Fcloudformation%2Fspark-troubleshooting-mcp-setup.yaml&stackName=spark-troubleshooting-mcp-setup) | | 亚太地区（新加坡） | [https://console.amazonaws.cn/cloudformation/home?region=ap-southeast-1#/stacks/new?templateURL=https%3A%2F%2Fsmus-mcp-cfn-template-prod-ap-southeast-1.s3.ap-southeast-1.amazonaws.com%2Fcloudformation%2Fspark-troubleshooting-mcp-setup.yaml&stackName=spark-troubleshooting-mcp-setup](https://console.amazonaws.cn/cloudformation/home?region=ap-southeast-1#/stacks/new?templateURL=https%3A%2F%2Fsmus-mcp-cfn-template-prod-ap-southeast-1.s3.ap-southeast-1.amazonaws.com%2Fcloudformation%2Fspark-troubleshooting-mcp-setup.yaml&stackName=spark-troubleshooting-mcp-setup) | | 亚太地区（悉尼） | [https://console.amazonaws.cn/cloudformation/home?region=ap-southeast-2#/stacks/new?templateURL=https%3A%2F%2Fsmus-mcp-cfn-template-prod-ap-southeast-2.s3.ap-southeast-2.amazonaws.com%2Fcloudformation%2Fspark-troubleshooting-mcp-setup.yaml&stackName=spark-troubleshooting-mcp-setup](https://console.amazonaws.cn/cloudformation/home?region=ap-southeast-2#/stacks/new?templateURL=https%3A%2F%2Fsmus-mcp-cfn-template-prod-ap-southeast-2.s3.ap-southeast-2.amazonaws.com%2Fcloudformation%2Fspark-troubleshooting-mcp-setup.yaml&stackName=spark-troubleshooting-mcp-setup) | | 加拿大（中部） | [https://console.amazonaws.cn/cloudformation/home?region=ca-central-1#/stacks/new?templateURL=https%3A%2F%2Fsmus-mcp-cfn-template-prod-ca-central-1.s3.ca-central-1.amazonaws.com%2Fcloudformation%2Fspark-troubleshooting-mcp-setup.yaml&stackName=spark-troubleshooting-mcp-setup](https://console.amazonaws.cn/cloudformation/home?region=ca-central-1#/stacks/new?templateURL=https%3A%2F%2Fsmus-mcp-cfn-template-prod-ca-central-1.s3.ca-central-1.amazonaws.com%2Fcloudformation%2Fspark-troubleshooting-mcp-setup.yaml&stackName=spark-troubleshooting-mcp-setup) | | 南美洲（圣保罗） | [https://console.amazonaws.cn/cloudformation/home?region=sa-east-1#/stacks/new?templateURL=https%3A%2F%2Fsmus-mcp-cfn-template-prod-sa-east-1.s3.sa-east-1.amazonaws.com%2Fcloudformation%2Fspark-troubleshooting-mcp-setup.yaml&stackName=spark-troubleshooting-mcp-setup](https://console.amazonaws.cn/cloudformation/home?region=sa-east-1#/stacks/new?templateURL=https%3A%2F%2Fsmus-mcp-cfn-template-prod-sa-east-1.s3.sa-east-1.amazonaws.com%2Fcloudformation%2Fspark-troubleshooting-mcp-setup.yaml&stackName=spark-troubleshooting-mcp-setup) | | 欧洲地区（法兰克福） | [https://console.amazonaws.cn/cloudformation/home?region=eu-central-1#/stacks/new?templateURL=https%3A%2F%2Fsmus-mcp-cfn-template-prod-eu-central-1.s3.eu-central-1.amazonaws.com%2Fcloudformation%2Fspark-troubleshooting-mcp-setup.yaml&stackName=spark-troubleshooting-mcp-setup](https://console.amazonaws.cn/cloudformation/home?region=eu-central-1#/stacks/new?templateURL=https%3A%2F%2Fsmus-mcp-cfn-template-prod-eu-central-1.s3.eu-central-1.amazonaws.com%2Fcloudformation%2Fspark-troubleshooting-mcp-setup.yaml&stackName=spark-troubleshooting-mcp-setup) | | 欧洲地区（斯德哥尔摩） | [https://console.amazonaws.cn/cloudformation/home?region=eu-north-1#/stacks/new?templateURL=https%3A%2F%2Fsmus-mcp-cfn-template-prod-eu-north-1.s3.eu-north-1.amazonaws.com%2Fcloudformation%2Fspark-troubleshooting-mcp-setup.yaml&stackName=spark-troubleshooting-mcp-setup](https://console.amazonaws.cn/cloudformation/home?region=eu-north-1#/stacks/new?templateURL=https%3A%2F%2Fsmus-mcp-cfn-template-prod-eu-north-1.s3.eu-north-1.amazonaws.com%2Fcloudformation%2Fspark-troubleshooting-mcp-setup.yaml&stackName=spark-troubleshooting-mcp-setup) | | 欧洲地区（伦敦） | [https://console.amazonaws.cn/cloudformation/home?region=eu-west-2#/stacks/new?templateURL=https%3A%2F%2Fsmus-mcp-cfn-template-prod-eu-west-2.s3.eu-west-2.amazonaws.com%2Fcloudformation%2Fspark-troubleshooting-mcp-setup.yaml&stackName=spark-troubleshooting-mcp-setup](https://console.amazonaws.cn/cloudformation/home?region=eu-west-2#/stacks/new?templateURL=https%3A%2F%2Fsmus-mcp-cfn-template-prod-eu-west-2.s3.eu-west-2.amazonaws.com%2Fcloudformation%2Fspark-troubleshooting-mcp-setup.yaml&stackName=spark-troubleshooting-mcp-setup) | | Europe (Paris) | [https://console.amazonaws.cn/cloudformation/home?region=eu-west-3#/stacks/new?templateURL=https%3A%2F%2Fsmus-mcp-cfn-template-prod-eu-west-3.s3.eu-west-3.amazonaws.com%2Fcloudformation%2Fspark-troubleshooting-mcp-setup.yaml&stackName=spark-troubleshooting-mcp-setup](https://console.amazonaws.cn/cloudformation/home?region=eu-west-3#/stacks/new?templateURL=https%3A%2F%2Fsmus-mcp-cfn-template-prod-eu-west-3.s3.eu-west-3.amazonaws.com%2Fcloudformation%2Fspark-troubleshooting-mcp-setup.yaml&stackName=spark-troubleshooting-mcp-setup) | | 亚太地区（首尔） | [https://console.amazonaws.cn/cloudformation/home?region=ap-northeast-2#/stacks/new?templateURL=https%3A%2F%2Fsmus-mcp-cfn-template-prod-ap-northeast-2.s3.ap-northeast-2.amazonaws.com%2Fcloudformation%2Fspark-troubleshooting-mcp-setup.yaml&stackName=spark-troubleshooting-mcp-setup](https://console.amazonaws.cn/cloudformation/home?region=ap-northeast-2#/stacks/new?templateURL=https%3A%2F%2Fsmus-mcp-cfn-template-prod-ap-northeast-2.s3.ap-northeast-2.amazonaws.com%2Fcloudformation%2Fspark-troubleshooting-mcp-setup.yaml&stackName=spark-troubleshooting-mcp-setup) | | 亚太地区（孟买） | [https://console.amazonaws.cn/cloudformation/home?region=ap-south-1#/stacks/new?templateURL=https%3A%2F%2Fsmus-mcp-cfn-template-prod-ap-south-1.s3.ap-south-1.amazonaws.com%2Fcloudformation%2Fspark-troubleshooting-mcp-setup.yaml&stackName=spark-troubleshooting-mcp-setup](https://console.amazonaws.cn/cloudformation/home?region=ap-south-1#/stacks/new?templateURL=https%3A%2F%2Fsmus-mcp-cfn-template-prod-ap-south-1.s3.ap-south-1.amazonaws.com%2Fcloudformation%2Fspark-troubleshooting-mcp-setup.yaml&stackName=spark-troubleshooting-mcp-setup) | 进入**指定堆栈详细信息**页面，输入**堆栈名称**。在 **Parameters**（参数）下输入其他信息。提供以下信息，然后继续创建堆栈。 + **TroubleshootingRoleName**-要为故障排除操作创建的 IAM 角色的名称 + **启用 EMREC2**-启用 EMR-EC2 故障排除权限（默认值：true） + **启用 EMRServerless**-启用 EMR 无服务器故障排除权限（默认值：true） + **EnableGlue**-启用 Glue 疑难解答权限（默认值：true） + **CloudWatchKmsKeyArn**-（可选）用于 CloudWatch 日志加密的现有 KMS 密钥的 ARN（仅限 EMR Serverless，默认加密时留空） 您也可以下载并查看[ CloudFormation 模板](https://github.com/aws-samples/aws-emr-utilities/blob/03c20fece616de23ec0ea5389f0113a5bc65fc3a/utilities/apache-spark-agents/spark-troubleshooting-agent-cloudformation/spark-troubleshooting-mcp-setup.yaml)，指定上述选项，然后 CloudFormation 使用 CLI 命令自行启动模板，示例见下文： ``` # deploy the stack with CloudFormation CLI commands aws cloudformation deploy \ --template-file spark-troubleshooting-mcp-setup.yaml \ --stack-name spark-troubleshooting-mcp-setup \ --region \ --capabilities CAPABILITY_NAMED_IAM \ --parameter-overrides \ TroubleshootingRoleName=spark-troubleshooting-role # retrieve the 1-line instruction to set the local environment variables, which will be used for the following MCP server configuration aws cloudformation describe-stacks \ --stack-name spark-troubleshooting-mcp-setup \ --region \ --query "Stacks[0].Outputs[?OutputKey=='ExportCommand'].OutputValue" \ --output text ``` 打开 “输出” 选项卡（或从上面的 desc CloudFormation ribe-stacks CLI 命令中检索），从输出中复制单行指令以设置环境变量，然后 Amazon CloudFormation 在本地环境中执行该指令。单行指令示例： ``` export SMUS_MCP_REGION= && export IAM_ROLE=arn:aws:iam::111122223333:role/spark-troubleshooting-role-xxxxxx ``` 然后在本地运行以下命令来设置 IAM 配置文件和 MCP 服务器配置： ``` # Step 1: Configure AWS CLI Profile aws configure set profile.smus-mcp-profile.role_arn ${IAM_ROLE} aws configure set profile.smus-mcp-profile.source_profile aws configure set profile.smus-mcp-profile.region ${SMUS_MCP_REGION} # Step 2: if you are using kiro CLI, use the following command to add the MCP configuration # Add Spark Troubleshooting MCP Server kiro-cli-chat mcp add \ --name "sagemaker-unified-studio-mcp-troubleshooting" \ --command "uvx" \ --args "[\"mcp-proxy-for-aws@latest\",\"https://sagemaker-unified-studio-mcp.${SMUS_MCP_REGION}.api.aws/spark-troubleshooting/mcp\", \"--service\", \"sagemaker-unified-studio-mcp\", \"--profile\", \"smus-mcp-profile\", \"--region\", \"${SMUS_MCP_REGION}\", \"--read-timeout\", \"180\"]" \ --timeout 180000 \ --scope global # Add Spark Code Recommendation MCP Server kiro-cli-chat mcp add \ --name "sagemaker-unified-studio-mcp-code-rec" \ --command "uvx" \ --args "[\"mcp-proxy-for-aws@latest\",\"https://sagemaker-unified-studio-mcp.${SMUS_MCP_REGION}.api.aws/spark-code-recommendation/mcp\", \"--service\", \"sagemaker-unified-studio-mcp\", \"--profile\", \"smus-mcp-profile\", \"--region\", \"${SMUS_MCP_REGION}\", \"--read-timeout\", \"180\"]" \ --timeout 180000 \ --scope global ``` 这应该`~/.kiro/settings/mcp.json`会更新以包括下面的 MCP 服务器配置。 ``` { "mcpServers": { "sagemaker-unified-studio-mcp-troubleshooting": { "type": "stdio", "command": "uvx", "args": [ "mcp-proxy-for-aws@latest", "https://sagemaker-unified-studio-mcp.us-east-1.api.aws/spark-troubleshooting/mcp", "--service", "sagemaker-unified-studio-mcp", "--profile", "smus-mcp-profile", "--region", "us-east-1", "--read-timeout", "180" ], "timeout": 180000, "disabled": false }, "sagemaker-unified-studio-mcp-code-rec": { "type": "stdio", "command": "uvx", "args": [ "mcp-proxy-for-aws@latest", "https://sagemaker-unified-studio-mcp.us-east-1.api.aws/spark-code-recommendation/mcp", "--service", "sagemaker-unified-studio-mcp", "--profile", "smus-mcp-profile", "--region", "us-east-1", "--read-timeout", "180" ], "timeout": 180000, "disabled": false } } } ``` 有关不同 MCP 客户端（例如 Kiro、Cline 和）的配置指南，请参阅[支持的接口](spark-troubleshooting-using-troubleshooting-agent.md#supported-interfaces)。 GitHub CoPilot