AlibabaCloud DevOps MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | The port number for HTTP/SSE mode (default is 3000) | 3000 |
| MCP_TRANSPORT | No | The transport mode for the MCP server (stdio, sse, or http) | stdio |
| DEVOPS_TOOLSETS | No | Comma-separated list of toolsets to enable (base, code-management, organization-management, project-management, pipeline-management, packages-management, application-delivery). If not specified, all tools will be enabled. | |
| YUNXIAO_ACCESS_TOKEN | Yes | Your AlibabaCloud Devops Personal Access Token. Grant read and write permissions to all APIs under organization management, project collaboration, code management, pipeline management, artifact repository management, application delivery and testing management. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_current_organization_infoA | 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_user_organizationsA | Get the list of organizations the current user belongs to |
| get_current_userA | Get information about the current user based on the token. In the absence of an explicitly specified user ID, this result will take precedence. |
| create_branchB | [Code Management] Create a new branch in a Codeup repository |
| get_branchA | [Code Management] Get information about a branch in a Codeup repository |
| delete_branchB | [Code Management] Delete a branch from a Codeup repository |
| list_branchesB | [Code Management] List branches in a Codeup repository |
| get_file_blobsC | [Code Management] Get file content from a Codeup repository |
| create_fileC | [Code Management] Create a new file in a Codeup repository |
| update_fileB | [Code Management] Update an existing file in a Codeup repository |
| delete_fileB | [Code Management] Delete a file from a Codeup repository |
| list_filesC | [Code Management] List file tree from a Codeup repository |
| compareC | [Code Management] Query code to compare content |
| get_repositoryC | [Code Management] Get information about a Codeup repository |
| list_repositoriesA | [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 |
| get_change_requestC | [Code Management] Get information about a change request |
| list_change_requestsC | [Code Management] List change requests |
| create_change_requestC | [Code Management] Create a new change request |
| create_change_request_commentC | [Code Management] Create a comment on a change request |
| list_change_request_commentsC | [Code Management] List comments on a change request |
| list_change_request_patch_setsC | [Code Management] List patch sets for a change request |
| list_commitsB | [Code Management] List commits in a Codeup repository |
| get_commitC | [Code Management] Get information about a commit |
| create_commit_commentB | [Code Management] Create a comment on a commit |
| list_organization_departmentsC | Get the list of departments in an organization |
| get_organization_department_infoC | Get information about a department in an organization |
| get_organization_department_ancestorsB | Get the ancestors of a department in an organization |
| list_organization_membersC | list user members in an organization |
| get_organization_member_infoC | Get information about a member in an organization |
| get_organization_member_info_by_user_idB | Get information about a member in an organization by user ID |
| search_organization_membersC | [Organization Management] Search for organization members |
| list_organization_rolesB | [Organization Management] List organization roles |
| get_organization_roleB | [Organization Management] Get information about an organization role |
| get_projectB | [Project Management] Get information about a Yunxiao project |
| search_projectsC | [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 |
| get_sprintB | [Project Management] Get information about a sprint |
| list_sprintsB | [Project Management] List sprints in a project |
| create_sprintC | [Project Management] Create a new sprint |
| update_sprintC | [Project Management] Update an existing sprint |
| get_work_itemC | [Project Management] Get information about a work item |
| create_work_itemC | [Project Management] Create a work item |
| search_workitemsC | [Project Management] Search work items with various filter conditions |
| get_work_item_typesB | [Project Management] Get the list of work item types for a project |
| update_work_itemC | [Project Management] Update a work item |
| list_all_work_item_typesC | [Project Management] List all work item types in an organization |
| list_work_item_typesB | [Project Management] List work item types in a project space |
| get_work_item_typeC | [Project Management] Get details of a specific work item type |
| list_work_item_relation_work_item_typesB | [Project Management] List work item types that can be related to a specific work item |
| get_work_item_type_field_configC | [Project Management] Get field configuration for a specific work item type |
| get_work_item_workflowC | [Project Management] Get workflow information for a specific work item type |
| list_work_item_commentsB | [Project Management] List comments for a specific work item |
| create_work_item_commentB | [Project Management] Create a comment for a specific work item |
| list_current_user_effort_recordsB | [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 |
| list_effort_recordsC | [Project Management] 获取实际工时明细 |
| create_effort_recordC | [Project Management] 登记实际工时 |
| list_estimated_effortsC | [Project Management] 获取预计工时明细 |
| create_estimated_effortC | [Project Management] 登记预计工时 |
| update_effort_recordC | [Project Management] 更新登记实际工时 |
| update_estimated_effortC | [Project Management] 更新登记预计工时 |
| get_pipelineC | [Pipeline Management] Get details of a specific pipeline in an organization |
| list_pipelinesB | [Pipeline Management] Get a list of pipelines in an organization with filtering options |
| generate_pipeline_yamlA | [Pipeline Management] Generate only the YAML configuration for a pipeline without creating it. 📋 Use Cases:
📖 Recommended Workflow:
💡 Parameter Collection Strategy:
⚡ Built-in capabilities: Handles default service connections internally, auto-extracts project name from repo URL |
| create_pipeline_from_descriptionA | [Pipeline Management] Create a pipeline using structured parameters extracted from user descriptions and environment context. 🔧 Built-in Capabilities:
📖 Recommended Workflow:
⚠️ Important Guidelines:
🎯 Parameter Priority:
🔍 IDE Detection Rules (MUST TRY FIRST):
📝 Version Detection (from project files):
🎯 Deployment Parsing:
🔗 Service Connection Strategy (3 scenarios):
🤔 When to Use Other Tools:
✅ Required: organizationId, name, buildLanguage, buildTool |
| smart_list_pipelinesC | [Pipeline Management] Intelligently search pipelines with natural language time references (e.g., 'today', 'this week') |
| create_pipeline_runC | [Pipeline Management] Run a pipeline with optional parameters |
| get_latest_pipeline_runB | [Pipeline Management] Get information about the latest pipeline run |
| get_pipeline_runC | [Pipeline Management] Get details of a specific pipeline run instance |
| list_pipeline_runsC | [Pipeline Management] Get a list of pipeline run instances with filtering options |
| list_pipeline_jobs_by_categoryB | [Pipeline Management] Get pipeline execution tasks by category. Currently only supports DEPLOY category. |
| list_pipeline_job_historysC | [Pipeline Management] Get the execution history of a pipeline task. Retrieve all execution records for a specific task in a pipeline. |
| execute_pipeline_job_runC | [Pipeline Management] Manually run a pipeline task. Start a specific job in a pipeline run instance. |
| get_pipeline_job_run_logC | [Pipeline Management] Get the execution logs of a pipeline job. Retrieve the log content for a specific job in a pipeline run. |
| update_pipelineC | [Pipeline Management] Update an existing pipeline in Yunxiao by pipelineId. Use this to update pipeline YAML, stages, jobs, etc. |
| list_service_connectionsB | [Service Connection Management] List service connections in an organization with filtering options |
| delete_resource_memberC | [Resource Member Management] Delete a resource member |
| list_resource_membersC | [Resource Member Management] Get a list of resource members |
| update_resource_memberC | [Resource Member Management] Update a resource member |
| create_resource_memberC | [Resource Member Management] Create a resource member |
| update_resource_ownerC | [Resource Member Management] Transfer resource owner |
| stop_vm_deploy_orderC | [VM Deploy Order Management] Stop VM deploy order |
| skip_vm_deploy_machineC | [VM Deploy Order Management] Skip VM deploy machine |
| retry_vm_deploy_machineC | [VM Deploy Order Management] Retry VM deploy machine |
| resume_vm_deploy_orderD | [VM Deploy Order Management] Resume VM deploy order |
| get_vm_deploy_orderC | [VM Deploy Order Management] Get VM deploy order details |
| get_vm_deploy_machine_logC | [VM Deploy Order Management] Get VM deploy machine log |
| list_package_repositoriesC | [Packages Management] List package repositories in an organization with filtering options |
| list_artifactsC | [Packages Management] List artifacts in a package repository with filtering options |
| get_artifactC | [Packages Management] Get information about a single artifact in a package repository |
| list_applicationsC | [application delivery] List applications in an organization with pagination |
| get_applicationC | [application delivery] Get application details by name |
| create_applicationC | [application delivery] Create a new application |
| update_applicationC | [application delivery] Update an existing application |
| create_app_tagC | [application delivery] Create an application tag |
| update_app_tagC | [application delivery] Update an application tag |
| search_app_tagsC | [application delivery] Search application tags |
| update_app_tag_bindB | [application delivery] Update application tag bindings |
| search_app_templatesC | [application delivery] Search application templates |
| create_global_varC | [application delivery] Create a global variable group |
| get_global_varC | [application delivery] Get a global variable group |
| update_global_varC | [application delivery] Update a global variable group |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 130 tools
The tool set covers multiple domains (application delivery, code management, pipeline management, etc.) with generally distinct purposes within each domain, but there is some overlap that could cause confusion. For example, multiple tools involve 'change requests' across different domains (e.g., create_change_request in Code Management vs. create_appstack_change_request in application delivery), and tools like list_change_requests and list_change_request_executions have unclear boundaries. Descriptions help, but the sheer number of tools increases ambiguity risk.
Tool names follow a consistent verb_noun pattern throughout (e.g., create_application, list_repositories, update_work_item), with minor deviations like mixed language descriptions (some in English, some in Chinese) and occasional verbose names (e.g., get_organization_department_ancestors). The naming is predictable and readable, though not perfectly uniform due to these language and length variations.
With 130 tools, the count is excessive for a single MCP server, making it overwhelming and difficult to navigate. While the server covers a broad DevOps scope, the tool surface feels bloated with many specialized or redundant tools (e.g., multiple list and get variants for similar resources). A more focused set of 20-50 tools would be more manageable and appropriate.
The tool set provides comprehensive coverage across its intended domains (application delivery, code management, pipeline management, project management, etc.), with full CRUD operations for most resources (e.g., create, get, list, update, delete for applications, pipelines, work items). There are no obvious gaps; agents can perform end-to-end workflows without dead ends, supported by detailed descriptions and built-in capabilities.