helpdesk-automation
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseHelpDesk Automation via Rube MCP
通过Rube MCP实现帮助台自动化
Automate HelpDesk ticketing operations through Composio's HelpDesk toolkit via Rube MCP.
通过Composio的HelpDesk工具包,借助Rube MCP自动化帮助台工单操作。
Prerequisites
前提条件
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active HelpDesk connection via with toolkit
RUBE_MANAGE_CONNECTIONShelpdesk - Always call first to get current tool schemas
RUBE_SEARCH_TOOLS
- 必须已连接Rube MCP(需具备RUBE_SEARCH_TOOLS权限)
- 通过激活HelpDesk连接,工具包为
RUBE_MANAGE_CONNECTIONShelpdesk - 请始终先调用以获取最新的工具架构
RUBE_SEARCH_TOOLS
Setup
设置步骤
Get Rube MCP: Add as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.
https://rube.app/mcp- Verify Rube MCP is available by confirming responds
RUBE_SEARCH_TOOLS - Call with toolkit
RUBE_MANAGE_CONNECTIONShelpdesk - If connection is not ACTIVE, follow the returned auth link to complete HelpDesk authentication
- Confirm connection status shows ACTIVE before running any workflows
获取Rube MCP:在客户端配置中添加作为MCP服务器。无需API密钥——只需添加端点即可使用。
https://rube.app/mcp- 通过确认能正常响应,验证Rube MCP是否可用
RUBE_SEARCH_TOOLS - 调用,指定工具包为
RUBE_MANAGE_CONNECTIONShelpdesk - 如果连接未处于ACTIVE状态,请按照返回的认证链接完成HelpDesk认证
- 在运行任何工作流之前,确认连接状态显示为ACTIVE
Core Workflows
核心工作流
1. List and Browse Tickets
1. 列出并浏览工单
When to use: User wants to retrieve, browse, or paginate through support tickets
Tool sequence:
- - List tickets with sorting and pagination [Required]
HELPDESK_LIST_TICKETS
Key parameters:
- : Ticket folder - 'tickets', 'archive', 'trash', or 'spam' (default: 'tickets')
silo - : Sort field - 'createdAt', 'updatedAt', or 'lastMessageAt' (default: 'createdAt')
sortBy - : Sort direction - 'asc' or 'desc' (default: 'desc')
order - : Results per page, 1-100 (default: 20)
pageSize - : Timestamp cursor for forward pagination
next.value - : ID cursor for forward pagination
next.ID - : Timestamp cursor for backward pagination
prev.value - : ID cursor for backward pagination
prev.ID
Pitfalls:
- Pagination uses cursor-based approach with timestamp + ID pairs
- Forward pagination requires both and
next.valuefrom previous responsenext.ID - Backward pagination requires both and
prev.valueprev.ID - determines which folder to list from; default is active tickets
silo - max is 100; default is 20
pageSize - Archived and trashed tickets are in separate silos
适用场景:用户需要检索、浏览或分页查看支持工单
工具流程:
- - 对工单进行排序和分页列出 [必填]
HELPDESK_LIST_TICKETS
关键参数:
- : 工单文件夹 - 'tickets'(工单)、'archive'(归档)、'trash'(垃圾箱)或'spam'(垃圾邮件)(默认值:'tickets')
silo - : 排序字段 - 'createdAt'(创建时间)、'updatedAt'(更新时间)或'lastMessageAt'(最后消息时间)(默认值:'createdAt')
sortBy - : 排序方向 - 'asc'(升序)或'desc'(降序)(默认值:'desc')
order - : 每页结果数,范围1-100(默认值:20)
pageSize - : 用于向前分页的时间戳游标
next.value - : 用于向前分页的ID游标
next.ID - : 用于向后分页的时间戳游标
prev.value - : 用于向后分页的ID游标
prev.ID
注意事项:
- 分页采用基于游标的方式,需同时使用时间戳和ID对
- 向前分页需要上一次响应中的和
next.valuenext.ID - 向后分页需要上一次响应中的和
prev.valueprev.ID - 参数决定从哪个文件夹列出工单;默认是活跃工单
silo - 最大值为100;默认值为20
pageSize - 已归档和已删除的工单存放在单独的silo中
2. Manage Ticket Views
2. 管理工单视图
When to use: User wants to see saved agent views for organizing tickets
Tool sequence:
- - List all agent views [Required]
HELPDESK_LIST_VIEWS
Key parameters: (none required)
Pitfalls:
- Views are predefined saved filters configured by agents in the HelpDesk UI
- View definitions include filter criteria that can be used to understand ticket organization
- Views cannot be created or modified via API; they are managed in the HelpDesk UI
适用场景:用户想要查看已保存的客服视图,用于整理工单
工具流程:
- - 列出所有客服视图 [必填]
HELPDESK_LIST_VIEWS
关键参数:无必填参数
注意事项:
- 视图是客服在HelpDesk界面中配置的预定义筛选器
- 视图定义包含筛选条件,可用于理解工单的分类方式
- 无法通过API创建或修改视图;需在HelpDesk界面中管理
3. Use Canned Responses
3. 使用预设回复
When to use: User wants to list available canned (template) responses for tickets
Tool sequence:
- - Retrieve all predefined reply templates [Required]
HELPDESK_LIST_CANNED_RESPONSES
Key parameters: (none required)
Pitfalls:
- Canned responses are predefined templates for common replies
- They may include placeholder variables that need to be filled in
- Canned responses are managed through the HelpDesk UI
- Response content may include HTML formatting
适用场景:用户想要查看工单可用的预设回复(模板)
工具流程:
- - 获取所有预定义回复模板 [必填]
HELPDESK_LIST_CANNED_RESPONSES
关键参数:无必填参数
注意事项:
- 预设回复是针对常见回复场景的预定义模板
- 模板中可能包含需要填充的占位符变量
- 预设回复需通过HelpDesk界面进行管理
- 回复内容可能包含HTML格式
4. Inspect Custom Fields
4. 查看自定义字段
When to use: User wants to view custom field definitions for the account
Tool sequence:
- - List all custom field definitions [Required]
HELPDESK_LIST_CUSTOM_FIELDS
Key parameters: (none required)
Pitfalls:
- Custom fields extend the default ticket schema with organization-specific data
- Field definitions include field type, name, and validation rules
- Custom fields are configured in the HelpDesk admin panel
- Field values appear on tickets when the field has been populated
适用场景:用户想要查看账户的自定义字段定义
工具流程:
- - 列出所有自定义字段定义 [必填]
HELPDESK_LIST_CUSTOM_FIELDS
关键参数:无必填参数
注意事项:
- 自定义字段通过组织特定的数据扩展了默认的工单架构
- 字段定义包含字段类型、名称和验证规则
- 自定义字段在HelpDesk管理面板中配置
- 当字段已填充内容时,工单上会显示字段值
Common Patterns
常见模式
Ticket Browsing Pattern
工单浏览模式
1. Call HELPDESK_LIST_TICKETS with desired silo and sortBy
2. Process the returned page of tickets
3. Extract next.value and next.ID from the response
4. Call HELPDESK_LIST_TICKETS with those cursor values for next page
5. Continue until no more cursor values are returned1. 使用指定的silo和sortBy调用HELPDESK_LIST_TICKETS
2. 处理返回的工单页面
3. 从响应中提取next.value和next.ID
4. 使用这些游标值调用HELPDESK_LIST_TICKETS以获取下一页
5. 持续调用直到没有更多游标值返回Ticket Folder Navigation
工单文件夹导航
Active tickets: silo='tickets'
Archived: silo='archive'
Trashed: silo='trash'
Spam: silo='spam'活跃工单: silo='tickets'
已归档: silo='archive'
已删除: silo='trash'
垃圾邮件: silo='spam'Cursor-Based Pagination
基于游标的分页
Forward pagination:
- Use next.value (timestamp) and next.ID from response
- Pass as next.value and next.ID parameters in next call
Backward pagination:
- Use prev.value (timestamp) and prev.ID from response
- Pass as prev.value and prev.ID parameters in next call向前分页:
- 使用响应中的next.value(时间戳)和next.ID
- 在下次调用中作为next.value和next.ID参数传入
向后分页:
- 使用响应中的prev.value(时间戳)和prev.ID
- 在下次调用中作为prev.value和prev.ID参数传入Known Pitfalls
已知注意事项
Cursor Pagination:
- Both timestamp and ID are required for cursor navigation
- Cursor values are timestamps in ISO 8601 date-time format
- Mixing forward and backward cursors in the same request is undefined behavior
Silo Filtering:
- Tickets are physically separated into silos (folders)
- Moving tickets between silos is done in the HelpDesk UI
- Each silo query is independent; there is no cross-silo search
Read-Only Operations:
- Current Composio toolkit provides list/read operations
- Ticket creation, update, and reply operations may require additional tools
- Check RUBE_SEARCH_TOOLS for any newly available tools
Rate Limits:
- HelpDesk API has per-account rate limits
- Implement backoff on 429 responses
- Keep page sizes reasonable to avoid timeouts
Response Parsing:
- Response data may be nested under or
datadata.data - Parse defensively with fallback patterns
- Ticket IDs are strings
游标分页:
- 游标导航必须同时使用时间戳和ID
- 游标值为ISO 8601日期时间格式的时间戳
- 在同一请求中混合使用向前和向后游标会导致未定义行为
Silo筛选:
- 工单被物理分隔到不同的silo(文件夹)中
- 工单在silo之间的移动需在HelpDesk界面中完成
- 每个silo的查询是独立的;不支持跨silo搜索
只读操作:
- 当前Composio工具包仅提供列出/读取操作
- 工单创建、更新和回复操作可能需要额外的工具
- 请检查RUBE_SEARCH_TOOLS以获取任何新增的可用工具
速率限制:
- HelpDesk API针对每个账户设有速率限制
- 收到429响应时请实现退避机制
- 保持合理的页面大小以避免超时
响应解析:
- 响应数据可能嵌套在或
data下data.data - 请采用防御性解析方式,设置回退模式
- 工单ID为字符串类型
Quick Reference
快速参考
| Task | Tool Slug | Key Params |
|---|---|---|
| List tickets | HELPDESK_LIST_TICKETS | silo, sortBy, order, pageSize |
| List views | HELPDESK_LIST_VIEWS | (none) |
| List canned responses | HELPDESK_LIST_CANNED_RESPONSES | (none) |
| List custom fields | HELPDESK_LIST_CUSTOM_FIELDS | (none) |
| 任务 | 工具标识 | 关键参数 |
|---|---|---|
| 列出工单 | HELPDESK_LIST_TICKETS | silo, sortBy, order, pageSize |
| 列出视图 | HELPDESK_LIST_VIEWS | 无 |
| 列出预设回复 | HELPDESK_LIST_CANNED_RESPONSES | 无 |
| 列出自定义字段 | HELPDESK_LIST_CUSTOM_FIELDS | 无 |