AlibabaCloud DevOps MCP

[application delivery] List change requests attached to a release

[application delivery] Get machine deployment log

[application delivery] Add host list to host group

[Code Management] Delete a branch from a Codeup repository

[VM Deploy Order Management] Retry VM deploy machine

[Pipeline Management] Create an organization-level variable group for Flow (pipeline).

[Pipeline Management] List organization-level Flow (pipeline) variable groups with pagination.

[Pipeline Management] Get a Flow (pipeline) variable group by numeric id.

Get information about the current user and organization based on the token. In the absence of an explicitly specified organization ID, this result will take precedence.

Get the list of organizations the current user belongs to

Get information about a member in an organization

Get information about a member in an organization by user ID

[Project Management] List work item types in a project space

[Project Management] Get details of a specific work item type

[Pipeline Management] Create a pipeline using structured parameters extracted from user descriptions and environment context. **🔧 Built-in Capabilities:** - ✅ Automatically retrieves default service connection IDs when not specified - ✅ Handles repository and service connection logic internally - ✅ Auto-extracts project name from repository URL (git@host:org/repo.git → repo) - ✅ Supports both IDE detection and explicit parameter specification **📖 Recommended Workflow:** 1. 🎯 PARSE user description for explicit parameters 2. 🔍 DETECT missing info from IDE environment FIRST: - Run `git config --get remote.origin.url` → repoUrl - Run `git branch --show-current` → branch - Auto-extract serviceName from repoUrl - Check project files for tech stack: * pom.xml → buildLanguage='java', buildTool='maven' * build.gradle → buildLanguage='java', buildTool='gradle' * package.json + package-lock.json → buildLanguage='nodejs', buildTool='npm' * package.json + yarn.lock → buildLanguage='nodejs', buildTool='yarn' * requirements.txt → buildLanguage='python', buildTool='pip' * go.mod → buildLanguage='go', buildTool='go' * *.csproj → buildLanguage='dotnet', buildTool='dotnet' 3. 🚀 CALL this tool with collected parameters **⚠️ Important Guidelines:** - DO NOT call list_repositories unless user explicitly asks to choose from available repositories - DO NOT call list_service_connections unless user explicitly asks to choose from available connections - ALWAYS try IDE detection first before making any API calls - If IDE detection fails, THEN consider API calls as fallback **🎯 Parameter Priority:** 1. 👤 USER EXPLICIT (highest) - buildLanguage, buildTool, versions, deployTarget 2. 🔍 IDE DETECTION (preferred) - repoUrl, branch, serviceName, tech stack 3. 🤖 TOOL DEFAULTS (automatic) - serviceConnectionId, organizationId **🔍 IDE Detection Rules (MUST TRY FIRST):** - 📂 Repository: `git config --get remote.origin.url` → repoUrl - 🌿 Branch: `git branch --show-current` → branch - 🏷️ Service Name: Auto-extracted from repoUrl (git@host:org/repo.git → repo) - ☕ Java Maven: pom.xml exists → buildLanguage='java', buildTool='maven' - 🏗️ Java Gradle: build.gradle exists → buildLanguage='java', buildTool='gradle' - 🟢 Node npm: package.json + package-lock.json → buildLanguage='nodejs', buildTool='npm' - 🧶 Node yarn: package.json + yarn.lock → buildLanguage='nodejs', buildTool='yarn' - 🐍 Python: requirements.txt → buildLanguage='python', buildTool='pip' - 🐹 Go: go.mod → buildLanguage='go', buildTool='go' - 💙 .NET: *.csproj → buildLanguage='dotnet', buildTool='dotnet' **📝 Version Detection (from project files):** - ☕ JDK: Read pom.xml <maven.compiler.source> → jdkVersion - 🟢 Node: Read package.json engines.node → nodeVersion - 🐍 Python: Read .python-version, pyproject.toml → pythonVersion - 🐹 Go: Read go.mod go directive → goVersion **🎯 Deployment Parsing:** - '部署到主机/VM/虚拟机' → deployTarget='vm' - '部署到Kubernetes/K8s' → deployTarget='k8s' - '只构建/构建制品' → deployTarget='none' **🔗 Service Connection Strategy (3 scenarios):** 1. **User specifies ID explicitly** (e.g., '使用服务连接ID abc123') → ✅ Pass serviceConnectionId=abc123 directly, NO list_service_connections call needed 2. **User doesn't specify any ID** (most common case) → ✅ Pass serviceConnectionId=null, tool will auto-retrieve default ID internally 3. **User wants to choose from available options** (e.g., '显示可用的服务连接让我选择') → 🔍 Call list_service_connections first, then let user choose, then create pipeline **🤔 When to Use Other Tools:** - User asks to "select from available repositories" → use list_repositories first - User wants to "choose from service connections" → use list_service_connections first - User wants to see options before deciding → gather info first, then create - For quick creation with current repo → directly use IDE detection **✅ Required:** organizationId, name, buildLanguage, buildTool

[application delivery] Get application details by name

[VM Deploy Order Management] Resume VM deploy order

[VM Deploy Order Management] Get VM deploy order details

[VM Deploy Order Management] Get VM deploy machine log

[application delivery] Delete a variable group

[application delivery] Create an application orchestration

[application delivery] Delete an application orchestration

[application delivery] Update an application orchestration. This is a full replacement — include all existing spec fields (componentList, labels, placeholderList, groupNameMap) to avoid data loss. Call get_app_orchestration first to retrieve the current state.

[application delivery] 查询应用下所有发布流程

[application delivery] 查询应用下所有发布流程摘要

[test management] 获取测试用例字段配置

[test management] 获取测试用例评论列表

[Project Management] List attachments for a specific work item. Returns attachment information including file name, size, suffix, download URL, and creator/modifier details.

[test management] 获取测试计划中测试用例的评论列表（与用例库中的用例评论不同，这里是测试计划上下文）

Get information about the current user based on the token. In the absence of an explicitly specified user ID, this result will take precedence.

[test management] 删除测试用例

[Project Management] Search work items with various filter conditions

[Project Management] Get information about a work item

[Pipeline Management] Get information about the latest pipeline run

[Project Management] List work item types that can be related to a specific work item

[Organization Management] List organization roles

[Project Management] Get information about a Yunxiao project

[Project Management] Create a comment for a specific work item

[Pipeline Management] Update an existing pipeline in Yunxiao by pipelineId. Use this to update pipeline YAML, stages, jobs, etc.

[Pipeline Management] Retry a failed pipeline job run.

[application delivery] Get a variable group

[application delivery] 获取发布流程阶段详情

[application delivery] 获取研发阶段流水线运行实例

[test management] 获取测试用例目录列表

[Code Management] Create a new file in a Codeup repository

[Code Management] Get information about a Codeup repository

[Code Management] Get information about a commit

[Code Management] Create a comment on a commit

Get the list of departments in an organization

Get information about a department in an organization

[Project Management] Get field configuration for a specific work item type

[Project Management] Delete a version from a Yunxiao Project. Use Cases: Remove obsolete versions Clean up project versions

[Project Management] List sprints in a project

[Project Management] Create a new sprint

[Project Management] Delete a work item. This operation is irreversible.

[application delivery] 读取部署单使用的物料和工单状态

[Project Management] List activity history for a specific work item. Returns changes including field updates, status transitions, association changes, and attachment changes, with operator and timestamp details.

[Project Management] 获取用户的实际工时明细，结束时间和开始时间的间隔不能大于6个月

[Project Management] 获取实际工时明细

[Pipeline Management] Get details of a specific pipeline in an organization

[Pipeline Management] Intelligently search pipelines with natural language time references (e.g., 'today', 'this week')

[Pipeline Management] Get details of a specific pipeline run instance

[Pipeline Management] Get pipeline execution tasks by category. Currently only supports DEPLOY category.

[Pipeline Management] Get the execution history of a pipeline task. Retrieve all execution records for a specific task in a pipeline.

[Resource Member Management] Delete a resource member

[Resource Member Management] Get a list of resource members

[Resource Member Management] Transfer resource owner

[VM Deploy Order Management] Stop VM deploy order

[VM Deploy Order Management] Skip VM deploy machine

[Pipeline Management] Delete a Flow (pipeline) variable group by numeric id.

[application delivery] Create a new application

[application delivery] Update an existing application

[application delivery] List application sources with pagination

[application delivery] Create an application tag

[application delivery] Search application tags

[test management] 获取测试用例信息

[test management] 获取测试计划用例执行进度统计（通过/失败/延后/待执行）

[application delivery] List global variable groups

[application delivery] Get variable groups for an environment

[application delivery] Get the revision of variable groups for an application

[application delivery] Get the latest orchestration for an environment

[application delivery] Get an application orchestration

[application delivery] Close a change request

[application delivery] Add host list to deploy group

[application delivery] 查看部署单版本列表

[application delivery] 查询发布流程阶段摘要列表

[application delivery] 跳过变更请求的发布流程阶段流水线

[application delivery] 查询研发阶段执行记录集成变更信息

[application delivery] 通过发布流程阶段验证

[application delivery] 拒绝发布流程阶段验证

[Code Management] Get information about a branch in a Codeup repository

[Code Management] Create a new change request (merge request). Supports specifying source/target branches, reviewers, associated work items, and optional AI review trigger.

[Resource Member Management] Create a resource member

[Project Management] Update a work item. 调用参数结构：除 organizationId / workItemId 外，所有要更新的字段必须放在 updateWorkItemFields 对象中（包括 subject / description / formatType / status / assignedTo / priority / labels / sprint / trackers / verifier / participants / versions / customFieldValues）。 描述中插入图片：先调 create_workitem_attachment 拿到返回值的 embedMarkdown（formatType="MARKDOWN"）或 embedHtml（formatType="RICHTEXT"），拼进 updateWorkItemFields.description，同时 updateWorkItemFields.formatType 设为对应值。⚠️ 不要把 create_workitem_attachment 返回的 url 嵌入 description，那是 30 秒过期的 OSS 临时签名。 受控字段提醒：实际工时（fieldId 101587）与预计工时（fieldId 101586）为云效受控系统字段，不能通过 updateWorkItemFields.customFieldValues 修改；请改用 `create_effort_record`/`update_effort_record` 与 `create_estimated_effort`/`update_estimated_effort`。

[Project Management] Get workflow information for a specific work item type

[Project Management] Get file information for a specific work item. Supports both file IDs (long hex for description-embedded images) and attachment IDs (numeric like 62487031). Returns file details including name, size, suffix, and a temporary download URL.

[Packages Management] List package repositories in an organization with filtering options

[Packages Management] List artifacts in a package repository with filtering options

[application delivery] Create a variable group

[application delivery] Get audit items for a change request

[application delivery] 取消发布流程阶段执行

[Code Management] Get file content from a Codeup repository

[Code Management] Update an existing file in a Codeup repository

[Code Management] List file tree from a Codeup repository

[Code Management] Query code to compare content

[Code Management] Get the CodeUp Repository List. A Repository serves as a unit for managing source code and is distinct from a Project. Use Case: View my repositories

[Code Management] Get detailed information about a specific change request (merge request) by its local ID.

[Code Management] Create a comment on a change request. Supports two types: GLOBAL_COMMENT (global comment on the entire merge request) and INLINE_COMMENT (inline comment on specific code lines). For INLINE_COMMENT, you must provide file_path, line_number, from_patchset_biz_id, and to_patchset_biz_id parameters.

[Code Management] Update a comment on a change request. Can update the comment content and/or resolved status.

[Code Management] List patch sets (versions) for a change request. Patch sets represent different versions of the merge request as it evolves.

Get the ancestors of a department in an organization

list user members in an organization

[Organization Management] Get information about an organization role

[Project Management] List versions for a Yunxiao Project or Program. Versions are used to manage release plans and track delivery progress. Use Cases: List all versions in a project Filter versions by status (TODO, DOING, ARCHIVED) Search versions by name

[Project Management] Get information about a sprint

[Project Management] Update an existing sprint

[Project Management] Get the list of work item types for a project

[Project Management] List all work item types in an organization

[Project Management] List comments for a specific work item

[Pipeline Management] Update a Flow (pipeline) variable group by numeric id.

[Project Management] Upload a local file as an attachment to a work item via multipart/form-data. MCP Server reads the file at the given absolute path and uploads it. Supports any file type (单文件 ≤ 10MB，云效不支持 svg/tiff)。 返回 WorkitemFile 含以下关键字段： - `id`/`name`/`size`/`suffix`：文件基础信息 - `url`：OSS 临时下载地址，约 30 秒过期。⚠️ 仅用于下载，不要嵌入工作项描述/评论 - `embedUrl`：永久代理 URL，适用于在工作项描述/评论中嵌入图片 - `embedMarkdown`：预拼好的 Markdown 图片标签，formatType=MARKDOWN 时拼接进 description 即可 - `embedHtml`：预拼好的 HTML <img> 标签，formatType=RICHTEXT 时拼接进 description 即可 在工作项描述中插入图片的标准三步法：① 创建工作项（如已有则跳过）；② 调本工具上传图片、读出 embedMarkdown / embedHtml；③ 调 update_work_item，在 updateWorkItemFields.description 中拼入该 embed* 字段，同时设置 updateWorkItemFields.formatType 为 "MARKDOWN" 或 "RICHTEXT"。 应用 token 场景必传 operatorId，个人 token 必传可省略。

[Pipeline Management] Generate only the YAML configuration for a pipeline without creating it. **📋 Use Cases:** - Preview YAML before creating pipeline - Generate YAML for manual deployment - Debug pipeline configuration **📖 Recommended Workflow:** 1. 🎯 Parse user description for explicit parameters 2. 🔍 If missing context, prefer IDE detection (terminal + file reading) over API calls 3. 🚀 Call this tool with collected parameters **💡 Parameter Collection Strategy:** - For QUICK pipeline creation: Use IDE detection (git config, file reading) - For PRECISE parameter selection: Consider list_repositories, list_service_connections when needed - Balance efficiency vs. accuracy based on user intent **⚡ Built-in capabilities:** Handles default service connections internally, auto-extracts project name from repo URL

[Packages Management] Get information about a single artifact in a package repository

[Pipeline Management] Manually run a pipeline task. Start a specific job in a pipeline run instance.

[Pipeline Management] Get the execution logs of a pipeline job. Retrieve the log content for a specific job in a pipeline run.

[Pipeline Management] Rerun a pipeline job. Only deploy-type jobs are supported. You can set a job as deploy type in its configuration.

[Pipeline Management] Skip a pipeline job run.

[Pipeline Management] Execute a subsequent action of a pipeline job.

[Pipeline Management] Get the list of steps for a pipeline job. Returns step details including stepIndex and buildId needed for log retrieval.

[application delivery] Update an application tag

[application delivery] Update application tag bindings

[application delivery] Create a global variable group

[application delivery] Get a global variable group

[application delivery] Update a global variable group

[application delivery] Get variable groups for an application

[application delivery] List application orchestrations

[application delivery] List change request executions

[application delivery] List work items for a change request

[application delivery] Cancel a change request

[application delivery] Search change requests in an application with pagination and filtering

[test management] 创建测试用例目录

[test management] 获取测试计划列表

[test management] 更新测试结果

[test management] 获取测试计划结果目录列表，按用例库分组返回目录树及每个目录下的用例数量

[test management] 获取测试用例库标签列表，支持分页与按名称关键词过滤

[Project Management] 更新已登记的实际工时（云效实际工时受控字段，不能走 update_work_item.customFieldValues）。

[application delivery] 查询环境部署单日志

[application delivery] 查询部署任务执行日志，其中通常包含下游部署引擎的调度细节信息

[application delivery] 根据创建来源查询部署单

[test management] 搜索测试用例

[test management] 获取用例库列表，支持分页与按名称模糊筛选

[test management] 创建测试计划中测试用例的评论，支持回复（通过parentId）。与用例库中的用例评论不同，这里是测试计划上下文

[Code Management] Create a new branch in a Codeup repository

[Code Management] List branches in a Codeup repository

[Code Management] Delete a file from a Codeup repository

[Code Management] Create a new Codeup repository. Creates an empty code repository that can then be pushed to via git. Use Cases: Create a new repository for a project

[Project Management] Update an existing version in a Yunxiao Project. Can update version name, owners, start date, and publish date. Use Cases: Update version name Change version owners Modify version dates

[Code Management] List change requests with multi-condition filtering, pagination and sorting. Supports filtering by repository, author, reviewer, state (opened/merged/closed), search keywords, and creation time range.

[Code Management] List commits in a Codeup repository

[Organization Management] Search for organization members

[Project Management] Search for Yunxiao Project List. A Project is a project management unit that includes work items and sprints, and it is different from a code repository (Repository). Use Cases: Query projects I am involved in Query projects I have created

[Project Management] Create a new version in a Yunxiao Project. Versions are used to manage release plans and track delivery progress. Use Cases: Create a new release version Plan project milestones Set version owners and dates

[Project Management] Create a work item. 描述字段使用提示： - description 支持 Markdown / 富文本，需配合 formatType（"MARKDOWN" 或 "RICHTEXT"）。 - 描述中插入图片三步法：① 先建工作项（本工具， description 可先为空或占位）；② 调 create_workitem_attachment 上传图片拿到返回值中的 embedMarkdown 或 embedHtml；③ 调 update_work_item 把拼好的 description 写回。✅ 报错点：不要使用 create_workitem_attachment 返回的 url 字段，那是 30 秒过期的 OSS 临时签名。 - 实际工时（fieldId 101587）与预计工时（fieldId 101586）为云效受控系统字段，不能通过本工具的 customFieldValues 修改；请改用 `create_effort_record` / `create_estimated_effort` 。

[Project Management] 登记实际工时。云效中实际工时（fieldId 101587）为受控字段，不能通过 update_work_item 的 customFieldValues 修改，必须调用本工具。

[Project Management] 获取预计工时明细

[Project Management] 登记预计工时。云效中预计工时（fieldId 101586）为受控字段，不能通过 update_work_item 的 customFieldValues 修改，必须调用本工具。

[Project Management] 更新已登记的预计工时（云效预计工时受控字段，不能走 update_work_item.customFieldValues）。

[Pipeline Management] Get a list of pipelines in an organization with filtering options

[Pipeline Management] Run a pipeline with flexible parameters. **⚠️ IMPORTANT: DO NOT provide 'params' parameter unless user explicitly provides a JSON string. Use simplified parameters instead!** **🎯 Most Common Use Cases:** 1. 🌿 Run with specific branch: Use 'branch' parameter - User: 'Run pipeline with dev branch' → { branch: 'dev' } - User: '用master分支运行流水线' → { branch: 'master' } - System will automatically fetch repository URLs from pipeline config 2. 🏷️ Run with specific tag: Use 'tag' parameter - User: 'Run pipeline with v1.0 tag' → { tag: 'v1.0' } - User: '用v2.0标签运行流水线' → { tag: 'v2.0' } - System will automatically fetch repository URLs from pipeline config 3. 🔄 Run with multiple branches: Use 'branches' parameter - User: 'Run pipeline with main and dev branches' → { branches: ['main', 'dev'] } 4. 🏛️ Run with specific repo branch/tag: Use 'repositories' parameter - { repositories: [{ url: 'https://codeup.aliyun.com/org/repo.git', branch: 'feature-x' }] } - { repositories: [{ url: 'https://codeup.aliyun.com/org/repo.git', tag: 'v1.0' }] } 5. 📦 Run with environment variables: Use 'environmentVariables' parameter - { environmentVariables: { 'ENV': 'production', 'VERSION': '1.0.0' } } **📝 Parameter Guide:** - 🌿 branch: Single branch name (most common) - 🏷️ tag: Single tag name (for release versions) - 🔄 branches: Multiple branches for branch mode - 🏛️ repositories: Specific branch/tag per repository - 📦 environmentVariables: Key-value pairs for pipeline variables - 📝 comment: Add a note for this run - 🔧 params: [Advanced] ONLY use if user provides raw JSON string **⚡ Smart Behavior:** - If only 'branch' or 'tag' is provided → automatically fetches repo URLs from pipeline and generates runningBranchs/runningTags - If 'branches' is provided → automatically enables branch mode - If 'params' is provided → all other parameters are ignored **❌ DO NOT:** - Generate 'params' parameter yourself - Convert simplified parameters to 'params' JSON - The system will handle param generation automatically

[Pipeline Management] Approve/pass a manual checkpoint (human validation gate) in a pipeline run.

[Pipeline Management] Get the log content for a specific step of a pipeline job. Use GetPipelineJobSteps first to get stepIndex and buildId.

[Pipeline Management] Get the download URL for a pipeline job step log. Use GetPipelineJobSteps first to get stepIndex and buildId.

[Service Connection Management] List service connections in an organization with filtering options

[Resource Member Management] Update a resource member

[application delivery] List applications in an organization with pagination

[application delivery] Search application templates

[application delivery] Update a variable group

[application delivery] Create a change request

[application delivery] 重试变更请求的发布流程阶段流水线

[application delivery] 创建部署单

[application delivery] 操作环境部署单

[application delivery] 更新应用发布流程阶段

[application delivery] 查询发布流程阶段执行记录列表

[application delivery] 执行变更请求的发布流程阶段

[application delivery] 查询研发阶段流水线任务运行日志

[test management] 创建测试用例

[test management] 获取测试计划中测试用例列表

[test management] 创建测试用例评论，支持回复（通过parentId）

[Pipeline Management] Refuse/reject a manual checkpoint (human validation gate) in a pipeline run.

[Pipeline Management] Stop/terminate a running pipeline job.

[Code Management] List comments on a change request. Supports filtering by comment type (GLOBAL_COMMENT or INLINE_COMMENT), state (OPENED or DRAFT), resolved status, and file path (for inline comments).

[Project Management] Search for Yunxiao Program (Project Set) List. A Program is a collection of multiple related projects, used for unified management and coordination of large projects. Use Cases: Query programs by name Query programs by status Query programs by creator

[Project Management] List versions for a Yunxiao Program (Project Set). Versions are used to manage release plans and track delivery progress. Use Cases: List all versions in a program Filter versions by status (TODO, DOING, ARCHIVED) Search versions by name

[Pipeline Management] Get a list of pipeline run instances with filtering options