AlibabaCloud DevOps MCP Server
Provides comprehensive integration with Alibaba Cloud's Yunxiao DevOps platform, enabling code repository management, work item tracking, pipeline automation, package management, and application delivery capabilities for enterprise development teams.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@AlibabaCloud DevOps MCP Server show me the latest pipeline runs for project 'mobile-app'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
alibabacloud-devops-mcp-server
AlibabaCloud Devops MCP Server provides AI assistants with the ability to interact with the Yunxiao platform, enabling them to read work item contents in projects, automatically write code after understanding requirements, and submit code merge requests. Enterprise development teams can use it to assist with code reviews, optimize task management, reduce repetitive operations, and thus focus on more important innovation and product delivery.
Features
alibabacloud-devops-mcp-server provides the following capabilities for AI assistants:
Code Repository Management: Query code repositories and their branches, create branches
File Operations: Create, update, delete, and retrieve code file content
Code Review: Create and manage code review processes
Project Management: Search projects, get project details
Pipeline Management: Get pipeline details, get pipeline list, create a pipeline run instance, get the latest pipeline run instance, get pipeline run details, get pipeline run list, Query / Run a pipeline deployment task
Package Management: Get package repository details list, Get artifacts details list, Get single artifact details
Application Delivery: Create and manage deployment orders, applications, orchestrations, variable groups, templates, tags, global variables, and deployment resources
Tools
alibabacloud-devops-mcp-server integrates various tools, including:
Organization Management
get_current_organization_Info: Get current user's organization informationget_user_organizations: Get the list of organizations the current user has joinedget_organization_role: Get information about an organization roleget_organization_departments: Get the list of departments in an organizationget_organization_department_info: Get information about a department in an organizationget_organization_department_ancestors: Get the ancestors of a department in an organizationget_organization_members: Get the list of members in an organizationget_organization_member_info: Get information about a member in an organizationget_organization_member_info_by_user_id: Get information about a member in an organization by user IDsearch_organization_members: Search for organization memberslist_organization_roles: List organization rolesget_organization_role: Get information about an organization role
Code Management Tools
create_branch: Create a branchdelete_branch: Delete a branchget_branch: Get branch informationlist_branches: Get branch listcreate_file: Create a filedelete_file: Delete a fileget_file_blobs: Get file contentlist_files: Query file treeupdate_file: Update file contentcreate_change_request: Create a merge requestcreate_change_request_comment: Create a comment on a merge requestget_change_request: Query merge requestlist_change_request_patch_sets: Query merge request version listlist_change_request: Query merge request listlist_change_request_comments: Query merge request comment listget_compare: Compare codeget_repository: Get repository detailslist_repositories: Get repository list
Project Management Tools
get_project: Get project detailssearch_projects: Search projectsget_sprint: Get sprint detailslist_sprints: List sprints in a projectget_work_item: Get work item detailssearch_workitems: Search work itemsget_work_item_types: get work item typescreate_work_item: create work itemlist_all_work_item_types: List all work item types in an organizationlist_work_item_types: List work item types in a project spaceget_work_item_type: Get details of a specific work item typelist_work_item_relation_work_item_types: List work item types that can be related to a specific work itemget_work_item_type_field_config: Get field configuration for a specific work item typeget_work_item_workflow: Get workflow information for a specific work item typelist_work_item_comments: List comments for a specific work itemcreate_work_item_comment: Create a comment for a specific work itemlist_current_user_effort_records: [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_records: [Project Management] 获取实际工时明细create_effort_record: [Project Management] 登记实际工时list_estimated_efforts: [Project Management] 获取预计工时明细create_estimated_effort: [Project Management] 登记预计工时update_effort_record: [Project Management] 更新登记实际工时update_estimated_effort: [Project Management] 更新登记预计工时
Pipeline Management Tools
get_pipeline: Get pipeline detailslist_pipelines: Get pipeline listsmart_list_pipelines: Smart pipeline search with natural language time referencescreate_pipeline_run: Create a pipeline run instanceget_latest_pipeline_run: Get the latest pipeline run instanceget_pipeline_run: Get pipeline run detailslist_pipeline_runs: Get pipeline run listlist_pipeline_jobs_by_category: Get pipeline execution tasks by categorylist_pipeline_job_historys: Get the execution history of a pipeline taskexecute_pipeline_job_run: Manually run a pipeline taskget_pipeline_job_run_log: Get the execution logs of a pipeline joblist_service_connections: List service connections in organizationcreate_pipeline_from_description: Automatically generates YAML configuration and creates pipelineupdate_pipeline: Update an existing pipeline in Yunxiao by pipelineId. Use this to update pipeline YAML, stages, jobs, etc.
Resource Member Management Tools
create_resource_member: Create a resource memberdelete_resource_member: Delete a resource memberlist_resource_members: Get a list of resource membersupdate_resource_member: Update a resource memberupdate_resource_owner: Transfer resource owner
Tag Management Tools
create_tag: Create a tagcreate_tag_group: Create a tag grouplist_tag_groups: Get a list of tag groupsdelete_tag_group: Delete a tag groupupdate_tag_group: Update a tag groupget_tag_group: Get a tag groupdelete_tag: Delete a tagupdate_tag: Update a tag
VM Deploy Order Management Tools
stop_vm_deploy_order: Stop VM deploy orderskip_vm_deploy_machine: Skip VM deploy machineretry_vm_deploy_machine: Retry VM deploy machineresume_vm_deploy_order: Resume VM deploy orderget_vm_deploy_order: Get VM deploy order detailsget_vm_deploy_machine_log: Get VM deploy machine log
Packages Management Tools
list_package_repositories: Get package repositories details listlist_artifacts: Get artifacts details listget_artifact: Get single artifact details
Application Delivery Tools
create_change_order: [application delivery] 创建部署单list_change_order_versions: [application delivery] 查看部署单版本列表get_change_order: [application delivery] 读取部署单使用的物料和工单状态list_change_order_job_logs: [application delivery] 查询环境部署单日志find_task_operation_log: [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execute_job_action: [application delivery] 操作环境部署单list_change_orders_by_origin: [application delivery] 根据创建来源查询部署单list_applications: [application delivery] List applications in an organization with paginationget_application: [application delivery] Get application details by namecreate_application: [application delivery] Create a new applicationupdate_application: [application delivery] Update an existing applicationget_latest_orchestration: [application delivery] Get the latest orchestration for an environmentlist_app_orchestration: [application delivery] List application orchestrationscreate_app_orchestration: [application delivery] Create an application orchestrationdelete_app_orchestration: [application delivery] Delete an application orchestrationget_app_orchestration: [application delivery] Get an application orchestrationupdate_app_orchestration: [application delivery] Update an application orchestrationget_env_variable_groups: [application delivery] Get variable groups for an environmentcreate_variable_group: [application delivery] Create a variable groupdelete_variable_group: [application delivery] Delete a variable groupget_variable_group: [application delivery] Get a variable groupupdate_variable_group: [application delivery] Update a variable groupget_app_variable_groups: [application delivery] Get variable groups for an applicationget_app_variable_groups_revision: [application delivery] Get the revision of variable groups for an applicationsearch_app_templates: [application delivery] Search application templatescreate_app_tag: [application delivery] Create an application tagupdate_app_tag: [application delivery] Update an application tagsearch_app_tags: [application delivery] Search application tagsupdate_app_tag_bind: [application delivery] Update application tag bindingscreate_global_var: [application delivery] Create a global variable groupget_global_var: [application delivery] Get a global variable groupupdate_global_var: [application delivery] Update a global variable grouplist_global_vars: [application delivery] List global variable groupsget_machine_deploy_log: [application delivery] Get machine deployment logadd_host_list_to_host_group: [application delivery] Add host list to host groupadd_host_list_to_deploy_group: [application delivery] Add host list to deploy group
Usage
Prerequisites
node version >= 18.0.0
AlibabaCloud Devops Personal Access Token, click here to obtain. 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.

Installing via Smithery
To install AlibabaCloud DevOps Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @aliyun/alibabacloud-devops-mcp-server --client claudeInstall Yunxiao MCP server via MCP marketplace
The MCP market built into Lingma (AlibabaCloud Tongyi Lingma) has already provided the AlibabaCloud Devops MCP service. To install it, simply enter the MCP market in Lingma and search for "Yunxiao DevOps", then click install.

Run MCP Server via NPX/Cursor/Claude code etc.
{
"mcpServers": {
"yunxiao": {
"command": "npx",
"args": [
"-y",
"alibabacloud-devops-mcp-server"
],
"env": {
"YUNXIAO_ACCESS_TOKEN": "<YOUR_TOKEN>"
}
}
}
}Run MCP Server via Docker Container
Option 1: Use Official Image (Recommended)
You can use the official Docker image without building it yourself:
# Pull the official image
docker pull build-steps-public-registry.cn-beijing.cr.aliyuncs.com/build-steps/alibabacloud-devops-mcp-server:v0.2.0Then use the official image name in your docker run commands instead of alibabacloud/alibabacloud-devops-mcp-server.
Option 2: Build Your Own Image
If you prefer to build the image yourself:
docker build -t alibabacloud/alibabacloud-devops-mcp-server .2. Run the Container
The MCP server supports three modes: stdio mode (default), SSE mode, and HTTP mode (Streamable HTTP).
Stdio Mode (for MCP clients)
Run the container directly (using official image):
docker run -i --rm \
-e YUNXIAO_ACCESS_TOKEN="your_token_here" \
build-steps-public-registry.cn-beijing.cr.aliyuncs.com/build-steps/alibabacloud-devops-mcp-server:v0.2.0Or use an environment file:
# Create .env file with: YUNXIAO_ACCESS_TOKEN=your_token_here
docker run -i --rm \
--env-file .env \
build-steps-public-registry.cn-beijing.cr.aliyuncs.com/build-steps/alibabacloud-devops-mcp-server:v0.2.0Note: If you built your own image, replace the image name with
alibabacloud/alibabacloud-devops-mcp-server.
SSE Mode (for HTTP access)
Run the container in background (using official image):
docker run -d --name yunxiao-mcp \
-p 3000:3000 \
-e YUNXIAO_ACCESS_TOKEN="your_token_here" \
-e PORT=3000 \
-e MCP_TRANSPORT=sse \
build-steps-public-registry.cn-beijing.cr.aliyuncs.com/build-steps/alibabacloud-devops-mcp-server:v0.2.0 \
node dist/index.js --sseNote: If you built your own image, replace the image name with
alibabacloud/alibabacloud-devops-mcp-server.
The server will be available at:
SSE endpoint:
http://localhost:3000/sseMessages endpoint:
http://localhost:3000/messages?sessionId=<session-id>
HTTP Mode (Streamable HTTP for smithery.ai)
Run the container in background (using official image):
docker run -d --name yunxiao-mcp \
-p 3000:3000 \
-e YUNXIAO_ACCESS_TOKEN="your_token_here" \
-e PORT=3000 \
-e MCP_TRANSPORT=http \
build-steps-public-registry.cn-beijing.cr.aliyuncs.com/build-steps/alibabacloud-devops-mcp-server:v0.2.0 \
node dist/index.js --httpOr use npm script:
npm run start:httpNote: If you built your own image, replace the image name with
alibabacloud/alibabacloud-devops-mcp-server.
The server will be available at:
MCP endpoint:
http://localhost:3000/mcp
This mode is compatible with smithery.ai platform deployment requirements.
View logs:
docker logs -f yunxiao-mcpStop the container:
docker stop yunxiao-mcp3. Configure MCP Client (for stdio mode)
If you're using a MCP client (like Claude Desktop, Cursor, etc.), configure it to use Docker:
{
"mcpServers": {
"yunxiao": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"YUNXIAO_ACCESS_TOKEN",
"build-steps-public-registry.cn-beijing.cr.aliyuncs.com/build-steps/alibabacloud-devops-mcp-server:v0.2.0"
],
"env": {
"YUNXIAO_ACCESS_TOKEN": "<YOUR_TOKEN>"
}
}
}
}Note: If you built your own image, replace the image name with
alibabacloud/alibabacloud-devops-mcp-server.
Run MCP Server via Docker Compose
Environment Setup
cd alibabacloud-devops-mcp-server
cp .env.exampleRunning the Services:
docker compose up -dConfigure MCP Server
{
"mcpServers": {
"yunxiao": {
"url":"http://localhost:3000/sse"
}
}
}HTTP/SSE Mode with Custom Tokens
When running in HTTP or SSE mode, each user can use their own token by passing it as a query parameter or request header:
Via query parameter:
# For SSE mode
http://localhost:3000/sse?yunxiao_access_token=USER_SPECIFIC_TOKEN
# For HTTP mode
http://localhost:3000/mcp?yunxiao_access_token=USER_SPECIFIC_TOKENVia request header:
x-yunxiao-token: USER_SPECIFIC_TOKENThis allows multiple users to share the same service while using their own individual tokens for authentication.
Toolsets
The server now supports toolsets, allowing you to enable only the tools you need. This can reduce the number of tools presented to the AI assistant and improve performance.
Available toolsets:
base: Base tools that are always loaded (get_current_user, get_current_organization_info, get_user_organizations)code-management: Code repository management tools (includes commit management tools)organization-management: Organization management tools (excluding base tools)project-management: Project management tools (includes effort management tools)pipeline-management: Pipeline management tools (includes service connections, resource member, and VM deploy order tools)packages-management: Package repository management toolsapplication-delivery: Application delivery tools
To use toolsets, you can specify them via command line arguments or environment variables:
Via command line argument:
npx -y alibabacloud-devops-mcp-server --toolsets=code-management,project-managementVia environment variable:
DEVOPS_TOOLSETS=code-management,project-management npx -y alibabacloud-devops-mcp-serverIf no toolsets are specified, all tools will be enabled by default.
Contact Us
Contact Us
If you have any questions, please join the Alibaba Cloud Devops discussion group (134400004101) for discussion.

Related Links
Available Tools
130 toolsadd_host_list_to_deploy_groupC
[application delivery] Add host list to deploy group
Inputs: organizationId (required), instanceName (required), groupName (required), hostSns (required).
add_host_list_to_host_groupC
[application delivery] Add host list to host group
Inputs: organizationId (required), instanceName (required), hostSns (required).
cancel_change_requestC
[application delivery] Cancel a change request
Inputs: organizationId (required), appName (required), sn (required).
close_change_requestC
[application delivery] Close a change request
Inputs: organizationId (required), appName (required), sn (required).
compareC
[Code Management] Query code to compare content
Inputs: organizationId (required), repositoryId (required), from (required), to (required), +3 more.
create_applicationC
[application delivery] Create a new application
Inputs: organizationId (required), name (required), appTemplateName, description, +2 more.
create_app_orchestrationC
[application delivery] Create an application orchestration
Inputs: organizationId (required), appName (required), templateId (required), templateType (required).
create_appstack_change_requestC
[application delivery] Create a change request
Inputs: organizationId (required), appName (required), appCodeRepoSn (required), autoDeleteBranchWhenEnd (required), +5 more.
create_app_tagC
[application delivery] Create an application tag
Inputs: organizationId (required), name (required), color (required).
create_branchB
[Code Management] Create a new branch in a Codeup repository
Inputs: organizationId (required), repositoryId (required), branch (required), ref.
create_change_orderC
[application delivery] 创建部署单
Inputs: organizationId (required), appName (required), changeOrder (required).
create_change_requestC
[Code Management] Create a new change request
Inputs: organizationId (required), repositoryId (required), title (required), sourceBranch (required), +7 more.
create_change_request_commentC
[Code Management] Create a comment on a change request
Inputs: organizationId (required), repositoryId (required), localId (required), content (required), +9 more.
create_commit_commentB
[Code Management] Create a comment on a commit
Inputs: organizationId (required), repositoryId (required), sha (required), content (required).
create_effort_recordC
[Project Management] 登记实际工时
Inputs: id (required), organizationId (required), actualTime (required), gmtEnd (required), +4 more.
create_estimated_effortC
[Project Management] 登记预计工时
Inputs: id (required), organizationId (required), owner (required), spentTime (required), +3 more.
create_fileC
[Code Management] Create a new file in a Codeup repository
Inputs: organizationId (required), repositoryId (required), filePath (required), content (required), +3 more.
create_global_varC
[application delivery] Create a global variable group
Inputs: organizationId (required), displayName (required), name (required), content, +2 more.
create_pipeline_from_descriptionA
[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:
🎯 PARSE user description for explicit parameters
🔍 DETECT missing info from IDE environment FIRST:
Run
git config --get remote.origin.url→ repoUrlRun
git branch --show-current→ branchAuto-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'
🚀 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:
👤 USER EXPLICIT (highest) - buildLanguage, buildTool, versions, deployTarget
🔍 IDE DETECTION (preferred) - repoUrl, branch, serviceName, tech stack
🤖 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):
User specifies ID explicitly (e.g., '使用服务连接ID abc123') → ✅ Pass serviceConnectionId=abc123 directly, NO list_service_connections call needed
User doesn't specify any ID (most common case) → ✅ Pass serviceConnectionId=null, tool will auto-retrieve default ID internally
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
Inputs: organizationId (required), name (required), buildLanguage (required), buildTool (required), +29 more.
create_pipeline_runC
[Pipeline Management] Run a pipeline with optional parameters
Inputs: organizationId (required), pipelineId (required), params, description, +6 more.
create_resource_memberC
[Resource Member Management] Create a resource member
Inputs: organizationId (required), resourceType (required), resourceId (required), roleName (required), +1 more.
create_sprintC
[Project Management] Create a new sprint
Inputs: organizationId (required), projectId (required), name (required), owners (required), +4 more.
create_variable_groupC
[application delivery] Create a variable group
Inputs: organizationId (required), appName (required), fromRevisionSha (required), branchName, +4 more.
create_work_itemC
[Project Management] Create a work item
Inputs: organizationId (required), spaceId (required), subject (required), workitemTypeId (required), +10 more.
create_work_item_commentB
[Project Management] Create a comment for a specific work item
Inputs: organizationId (required), workItemId (required), content (required).
delete_app_orchestrationC
[application delivery] Delete an application orchestration
Inputs: organizationId (required), appName (required), sn (required).
delete_branchB
[Code Management] Delete a branch from a Codeup repository
Inputs: organizationId (required), repositoryId (required), branchName (required).
delete_fileB
[Code Management] Delete a file from a Codeup repository
Inputs: organizationId (required), repositoryId (required), filePath (required), commitMessage (required), +1 more.
delete_resource_memberC
[Resource Member Management] Delete a resource member
Inputs: organizationId (required), resourceType (required), resourceId (required), userId (required).
delete_variable_groupC
[application delivery] Delete a variable group
Inputs: organizationId (required), appName (required), variableGroupName (required).
execute_job_actionC
[application delivery] 操作环境部署单
Inputs: organizationId (required), appName (required), changeOrderSn (required), jobSn (required), +1 more.
execute_pipeline_job_runC
[Pipeline Management] Manually run a pipeline task. Start a specific job in a pipeline run instance.
Inputs: organizationId (required), pipelineId (required), pipelineRunId (required), jobId (required).
find_task_operation_logC
[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
Inputs: organizationId (required), appName (required), changeOrderSn (required), jobSn (required), +2 more.
generate_pipeline_yamlA
[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:
🎯 Parse user description for explicit parameters
🔍 If missing context, prefer IDE detection (terminal + file reading) over API calls
🚀 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
Inputs: organizationId (required), name (required), buildLanguage (required), buildTool (required), +29 more.
get_applicationC
[application delivery] Get application details by name
Inputs: organizationId (required), appName (required).
get_app_orchestrationC
[application delivery] Get an application orchestration
Inputs: organizationId (required), appName (required), sn (required), tagName, +1 more.
get_app_variable_groupsC
[application delivery] Get variable groups for an application
Inputs: organizationId (required), appName (required).
get_app_variable_groups_revisionC
[application delivery] Get the revision of variable groups for an application
Inputs: organizationId (required), appName (required).
get_artifactC
[Packages Management] Get information about a single artifact in a package repository
Inputs: organizationId (required), repoId (required), id (required), repoType (required).
get_branchA
[Code Management] Get information about a branch in a Codeup repository
Inputs: organizationId (required), repositoryId (required), branchName (required).
get_change_orderC
[application delivery] 读取部署单使用的物料和工单状态
Inputs: organizationId (required), appName (required), changeOrderSn (required).
get_change_requestC
[Code Management] Get information about a change request
Inputs: organizationId (required), repositoryId (required), localId (required).
get_change_request_audit_itemsB
[application delivery] Get audit items for a change request
Inputs: organizationId (required), appName (required), sn (required), refType (required).
get_commitC
[Code Management] Get information about a commit
Inputs: organizationId (required), repositoryId (required), sha (required).
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.
Inputs: no named parameters.
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.
Inputs: no named parameters.
get_env_variable_groupsC
[application delivery] Get variable groups for an environment
Inputs: organizationId (required), appName (required), envName (required).
get_file_blobsC
[Code Management] Get file content from a Codeup repository
Inputs: organizationId (required), repositoryId (required), filePath (required), ref (required).
get_global_varC
[application delivery] Get a global variable group
Inputs: organizationId (required), name (required), revisionSha.
get_latest_orchestrationC
[application delivery] Get the latest orchestration for an environment
Inputs: organizationId (required), appName (required), envName (required).
get_latest_pipeline_runB
[Pipeline Management] Get information about the latest pipeline run
Inputs: organizationId (required), pipelineId (required).
get_machine_deploy_logC
[application delivery] Get machine deployment log
Inputs: organizationId (required), tunnelId (required), machineSn (required).
get_organization_department_ancestorsB
Get the ancestors of a department in an organization
Inputs: organizationId (required), id (required).
get_organization_department_infoC
Get information about a department in an organization
Inputs: organizationId (required), id (required).
get_organization_member_infoC
Get information about a member in an organization
Inputs: organizationId (required), memberId (required).
get_organization_member_info_by_user_idB
Get information about a member in an organization by user ID
Inputs: organizationId (required), userId (required).
get_organization_roleB
[Organization Management] Get information about an organization role
Inputs: organizationId (required), roleId (required).
get_pipelineC
[Pipeline Management] Get details of a specific pipeline in an organization
Inputs: organizationId (required), pipelineId (required).
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.
Inputs: organizationId (required), pipelineId (required), pipelineRunId (required), jobId (required).
get_pipeline_runC
[Pipeline Management] Get details of a specific pipeline run instance
Inputs: organizationId (required), pipelineId (required), pipelineRunId (required).
get_projectB
[Project Management] Get information about a Yunxiao project
Inputs: organizationId (required), id (required).
get_repositoryC
[Code Management] Get information about a Codeup repository
Inputs: organizationId (required), repositoryId (required).
get_sprintB
[Project Management] Get information about a sprint
Inputs: organizationId (required), projectId (required), id (required).
get_user_organizationsA
Get the list of organizations the current user belongs to
Inputs: no named parameters.
get_variable_groupC
[application delivery] Get a variable group
Inputs: organizationId (required), appName (required), variableGroupName (required).
get_vm_deploy_machine_logC
[VM Deploy Order Management] Get VM deploy machine log
Inputs: organizationId (required), pipelineId (required), deployOrderId (required), machineSn (required).
get_vm_deploy_orderC
[VM Deploy Order Management] Get VM deploy order details
Inputs: organizationId (required), pipelineId (required), deployOrderId (required).
get_work_itemC
[Project Management] Get information about a work item
Inputs: organizationId (required), workItemId (required).
get_work_item_typeC
[Project Management] Get details of a specific work item type
Inputs: organizationId (required), id (required).
get_work_item_type_field_configC
[Project Management] Get field configuration for a specific work item type
Inputs: organizationId (required), projectId (required), workItemTypeId (required).
get_work_item_typesB
[Project Management] Get the list of work item types for a project
Inputs: organizationId (required), id (required), category (required).
get_work_item_workflowC
[Project Management] Get workflow information for a specific work item type
Inputs: organizationId (required), projectId (required), workItemTypeId (required).
list_all_work_item_typesC
[Project Management] List all work item types in an organization
Inputs: organizationId (required).
list_applicationsC
[application delivery] List applications in an organization with pagination
Inputs: organizationId (required), pagination, perPage, orderBy, +2 more.
list_app_orchestrationC
[application delivery] List application orchestrations
Inputs: organizationId (required), appName (required).
list_artifactsC
[Packages Management] List artifacts in a package repository with filtering options
Inputs: organizationId (required), repoId (required), repoType (required), page, +4 more.
list_branchesB
[Code Management] List branches in a Codeup repository
Inputs: organizationId (required), repositoryId (required), page, perPage, +2 more.
list_change_order_job_logsC
[application delivery] 查询环境部署单日志
Inputs: organizationId (required), appName (required), changeOrderSn (required), jobSn (required), +2 more.
list_change_orders_by_originC
[application delivery] 根据创建来源查询部署单
Inputs: organizationId (required), originType (required), originId (required), appName, +1 more.
list_change_order_versionsC
[application delivery] 查看部署单版本列表
Inputs: organizationId (required), appName (required), envNames, creators, +2 more.
list_change_request_commentsC
[Code Management] List comments on a change request
Inputs: organizationId (required), repositoryId (required), localId (required), patchSetBizIds, +4 more.
list_change_request_executionsC
[application delivery] List change request executions
Inputs: organizationId (required), appName (required), sn (required), releaseWorkflowSn (required), +5 more.
list_change_request_patch_setsC
[Code Management] List patch sets for a change request
Inputs: organizationId (required), repositoryId (required), localId (required).
list_change_requestsC
[Code Management] List change requests
Inputs: organizationId (required), page, perPage, projectIds, +8 more.
list_change_request_work_itemsC
[application delivery] List work items for a change request
Inputs: organizationId (required), appName (required), sn (required).
list_commitsB
[Code Management] List commits in a Codeup repository
Inputs: organizationId (required), repositoryId (required), refName (required), since, +7 more.
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
Inputs: organizationId (required), startDate (required), endDate (required).
list_effort_recordsC
[Project Management] 获取实际工时明细
Inputs: id (required), organizationId (required).
list_estimated_effortsC
[Project Management] 获取预计工时明细
Inputs: id (required), organizationId (required).
list_filesC
[Code Management] List file tree from a Codeup repository
Inputs: organizationId (required), repositoryId (required), path, ref, +1 more.
list_global_varsC
[application delivery] List global variable groups
Inputs: organizationId (required), current (required), pageSize (required), search.
list_organization_departmentsC
Get the list of departments in an organization
Inputs: organizationId (required), parentId.
list_organization_membersC
list user members in an organization
Inputs: organizationId (required), page, perPage.
list_organization_rolesB
[Organization Management] List organization roles
Inputs: organizationId (required).
list_package_repositoriesC
[Packages Management] List package repositories in an organization with filtering options
Inputs: organizationId (required), repoTypes, repoCategories, perPage, +1 more.
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.
Inputs: organizationId (required), pipelineId (required), category (required), identifier (required), +2 more.
list_pipeline_jobs_by_categoryB
[Pipeline Management] Get pipeline execution tasks by category. Currently only supports DEPLOY category.
Inputs: organizationId (required), pipelineId (required), category (required).
list_pipeline_runsC
[Pipeline Management] Get a list of pipeline run instances with filtering options
Inputs: organizationId (required), pipelineId (required), perPage, page, +4 more.
list_pipelinesB
[Pipeline Management] Get a list of pipelines in an organization with filtering options
Inputs: organizationId (required), createStartTime, createEndTime, executeStartTime, +5 more.
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
Inputs: organizationId (required), page, perPage, orderBy, +3 more.
list_resource_membersC
[Resource Member Management] Get a list of resource members
Inputs: organizationId (required), resourceType (required), resourceId (required).
list_service_connectionsB
[Service Connection Management] List service connections in an organization with filtering options
Inputs: organizationId (required), serviceConnectionType (required).
list_sprintsB
[Project Management] List sprints in a project
Inputs: organizationId (required), id (required), status, page, +1 more.
list_work_item_commentsB
[Project Management] List comments for a specific work item
Inputs: organizationId (required), workItemId (required), page, perPage.
list_work_item_relation_work_item_typesB
[Project Management] List work item types that can be related to a specific work item
Inputs: organizationId (required), workItemTypeId (required), relationType.
list_work_item_typesB
[Project Management] List work item types in a project space
Inputs: organizationId (required), projectId (required), category.
resume_vm_deploy_orderD
[VM Deploy Order Management] Resume VM deploy order
Inputs: organizationId (required), pipelineId (required), deployOrderId (required).
retry_vm_deploy_machineC
[VM Deploy Order Management] Retry VM deploy machine
Inputs: organizationId (required), pipelineId (required), deployOrderId (required), machineSn (required).
search_app_tagsC
[application delivery] Search application tags
Inputs: organizationId (required), current, pageSize, orderBy, +2 more.
search_app_templatesC
[application delivery] Search application templates
Inputs: organizationId (required), pagination, perPage, orderBy, +4 more.
search_organization_membersC
[Organization Management] Search for organization members
Inputs: organizationId (required), deptIds, query, includeChildren, +5 more.
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
Inputs: organizationId (required), name, status, createdAfter, +12 more.
search_workitemsC
[Project Management] Search work items with various filter conditions
Inputs: organizationId (required), category (required), spaceId (required), subject, +10 more.
skip_vm_deploy_machineC
[VM Deploy Order Management] Skip VM deploy machine
Inputs: organizationId (required), pipelineId (required), deployOrderId (required), machineSn (required).
smart_list_pipelinesC
[Pipeline Management] Intelligently search pipelines with natural language time references (e.g., 'today', 'this week')
Inputs: organizationId (required), timeReference, pipelineName, statusList, +2 more.
stop_vm_deploy_orderC
[VM Deploy Order Management] Stop VM deploy order
Inputs: organizationId (required), pipelineId (required), deployOrderId (required).
update_applicationC
[application delivery] Update an existing application
Inputs: organizationId (required), appName (required), ownerId.
update_app_orchestrationC
[application delivery] Update an application orchestration
Inputs: organizationId (required), appName (required), sn (required), name (required), +5 more.
update_app_tagC
[application delivery] Update an application tag
Inputs: organizationId (required), name (required), newName (required), color.
update_app_tag_bindB
[application delivery] Update application tag bindings
Inputs: organizationId (required), appName (required), tagNames (required).
update_effort_recordC
[Project Management] 更新登记实际工时
Inputs: organizationId (required), workitemId (required), id (required), actualTime (required), +5 more.
update_estimated_effortC
[Project Management] 更新登记预计工时
Inputs: organizationId (required), workitemId (required), id (required), owner (required), +4 more.
update_fileB
[Code Management] Update an existing file in a Codeup repository
Inputs: organizationId (required), repositoryId (required), filePath (required), content (required), +3 more.
update_global_varC
[application delivery] Update a global variable group
Inputs: organizationId (required), name (required), content (required), fromRevisionSha (required), +1 more.
update_pipelineC
[Pipeline Management] Update an existing pipeline in Yunxiao by pipelineId. Use this to update pipeline YAML, stages, jobs, etc.
Inputs: organizationId (required), pipelineId (required), content (required), name (required).
update_resource_memberC
[Resource Member Management] Update a resource member
Inputs: organizationId (required), resourceType (required), resourceId (required), roleName (required), +1 more.
update_resource_ownerC
[Resource Member Management] Transfer resource owner
Inputs: organizationId (required), resourceType (required), resourceId (required), newOwnerId (required).
update_sprintC
[Project Management] Update an existing sprint
Inputs: organizationId (required), projectId (required), id (required), name (required), +5 more.
update_variable_groupC
[application delivery] Update a variable group
Inputs: organizationId (required), appName (required), variableGroupName (required), fromRevisionSha (required), +5 more.
update_work_itemC
[Project Management] Update a work item
Inputs: organizationId (required), workItemId (required), updateWorkItemFields (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
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.
Related MCP Connectors
AI-native git hosting — repos, PRs, issues, CI gates, and AI code review over MCP (60 tools).
Plan Salesforce deploys, open pull requests and trigger pipelines from your AI client.
Deploy and manage Jade Hosting projects from AI clients. Jade account and OAuth required.
Operate GitHub from your AI assistant: repos, PRs, issues, Actions. Previews and read-only mode.