rotacloud-mcp-node
MCP server exposing the RotaCloud API to Claude and other MCP clients, covering all 129 documented v1 operations across 36 resources including shifts, attendance, leave, users, locations, roles, and timesheets.
README
rotacloud-mcp-node
An MCP server exposing the RotaCloud API to Claude and other MCP clients. It covers all 129 documented v1 operations across 36 resources — shifts, attendance, leave, users, locations, roles, timesheets and the rest.
Tools are generated from RotaCloud's published OpenAPI specification (vendor/openapi.json), so parameter names, types and descriptions come straight from the documentation.
Installation
As a Claude Desktop extension
Download rotacloud-mcp-node.mcpb and open it with Claude Desktop. You will be prompted for your RotaCloud API key, which you can generate from within your RotaCloud account.
Manual / development
npm install
export ROTACLOUD_API_KEY="your-api-key-here"
node server/index.js
Add it to claude_desktop_config.json:
{
"mcpServers": {
"rotacloud": {
"command": "node",
"args": ["/absolute/path/to/rotacloud-mcp-node/server/index.js"],
"env": {
"ROTACLOUD_API_KEY": "your-api-key-here"
}
}
}
}
Configuration
| Variable | Required | Purpose |
|---|---|---|
ROTACLOUD_API_KEY |
yes | API key generated from your RotaCloud account |
ROTACLOUD_USER_ID |
no | Act on behalf of this user by default (sends the User header) |
By default requests are made as an anonymous user with administrative permissions. Setting ROTACLOUD_USER_ID makes every request act as that user instead. Tools whose behaviour depends on the acting user — me_*, messages_*, leave_requests_*, swap_requests_* and unavailability_requests_* — also accept an as_user argument to override it per call.
Tools
Tools are named {resource}_{action}, e.g. shifts_list, shifts_create, users_retrieve, leave_requests_approve.
Names are derived from each operation's summary in the API documentation rather than from its HTTP method, because in this API the two often disagree — DELETE /users_clocked_in/{id} clocks a user out, and POST /swap_requests/{id} denies a swap. The tool names reflect what the operation actually does: users_clocked_in_clock_out, swap_requests_deny_shift_admin.
Dates and times
RotaCloud mixes three formats, and the tools follow the API exactly:
- Unix epoch seconds for shift and attendance times (
start_time,in_time, and thestart/endrange filters on/shifts,/attendance,/availability,/pay_periods…). These tools also accept an ISO 8601 string and convert it for you. YYYY-MM-DDstrings for leave, day notes, TOIL and user dates (start_date,end_date,dob…).HH:MMstrings for logbook event times and availability windows.
Pagination
List endpoints accept limit and offset. Responses that are paginated are returned as:
{
"meta": { "total_count": 137, "links": { "next": "…", "last": "…" } },
"data": [ … ]
}
Results are not auto-paginated — each call returns one page, so a wide date range cannot flood the context. Follow meta.links.next or increment offset to page through.
Request bodies
Write tools list every field documented for that endpoint, but accept unknown fields too. RotaCloud's published body schemas are derived from example payloads and under-describe reality (for instance role_rates is documented with the example's literal role IDs as keys), so rejecting undocumented fields would block valid writes. Each write tool's description includes the documented example payload.
Resources
accounts(1)attendance(5)attendance_approved(2)availability(2)day_notes(5)days_off(3)days_off_patterns(5)documents(6)groups(5)holiday_allowances(2)holiday_allowances_custom(3)leave(5)leave_embargoes(5)leave_requests(6)leave_types(1)locations(5)logbook_categories(5)logbook_events(5)me(2)messages(2)pay_periods(3)pins(1)roles(5)settings(1)shifts(5)shifts_acknowledged(1)shifts_published(2)swap_requests(5)terminals(5)terminals_active(3)timezones(2)toil_accruals(4)toil_allowance(1)unavailability_requests(6)users(5)users_clocked_in(5)
Scope
This server covers the v1 API as published at https://rotacloud-api-docs.netlify.app/. RotaCloud's official Node SDK exposes some additional v2 endpoints (invoices, v2 logbook, user onboarding) which are not part of the public documentation and are not included here.
Regenerating
server/tools.js is generated and committed. To pick up a newer version of the API:
curl -o vendor/openapi.json https://rotacloud-api-docs.netlify.app/openapi.json
npm run generate
The generator fails loudly if two operations would produce the same tool name.
Building
npm run build # mcpb pack
Check the contents of the resulting .mcpb before distributing it — mcpb pack sweeps local dotfiles into the bundle.
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。