kimai-mcp-server
MCP server for Kimai time-tracking that provides read access to the full API and guarded write tools for timesheets, with explicit authorization and backups.
README
@nightsquawktech/kimai-mcp-server
Model Context Protocol server for Kimai time-tracking instances. Read tools cover the full Kimai API surface; timesheet write tools exist but are guarded behind explicit authorization.
API Notes
Kimai exposes a JSON API under /api. Current Kimai documentation uses bearer-token authentication:
Authorization: Bearer <api-token>
The base URL should be the browser URL without a trailing slash, for example https://demo.kimai.org, not https://demo.kimai.org/. Kimai's current API docs are available at your own instance under /api/doc, and official docs note that the OpenAPI export is available from that UI.
Pagination uses page and size query parameters. Kimai defaults to 50 records per page and documents 500 as the maximum page size. Paginated responses may include X-Page, X-Total-Count, X-Total-Pages, and X-Per-Page headers.
Read tools are safe to call without changing Kimai. Write tools are intentionally guarded because Kimai timekeeping data is sensitive:
- Every write tool requires
authorization_confirmed: true. - Every write tool requires an
authorization_notedescribing the user's explicit approval. - Every write tool writes a JSON backup under the system temp directory before or immediately after mutation.
- Update/state-change tools save the previous Kimai record before calling the mutation endpoint.
- Create/duplicate tools save the request/source and created record so the created ID can be audited and reverted manually if needed.
- Delete tools are intentionally not exposed.
References:
- https://www.kimai.org/documentation/rest-api.html
- https://www.kimai.org/documentation/user-api.html
- https://www.kimai.org/documentation/api-pagination.html
Tools
kimai_get_server_inforeads/api/ping,/api/version,/api/plugins, and/api/config/timesheet.kimai_get_current_userreads/api/users/me.kimai_list_usersandkimai_get_userread users.kimai_list_customersandkimai_get_customerread customers.kimai_list_projectsandkimai_get_projectread projects.kimai_list_activitiesandkimai_get_activityread activities.kimai_list_tagsreads tags.kimai_list_timesheets,kimai_get_timesheet,kimai_list_active_timesheets, andkimai_list_recent_timesheetsread time entries.kimai_create_timesheetcreates a time entry after explicit authorization and stores a temp backup.kimai_update_timesheetupdates a time entry after explicit authorization and stores the previous record in a temp backup.kimai_stop_timesheetstops an active time entry after explicit authorization and stores the previous record in a temp backup.kimai_restart_timesheetrestarts a stopped time entry after explicit authorization and stores the previous record in a temp backup.kimai_duplicate_timesheetduplicates a time entry after explicit authorization and stores source/created records in a temp backup.kimai_list_teamsandkimai_get_teamread teams.kimai_list_invoicesandkimai_get_invoiceread invoice history.kimai_list_expensesandkimai_get_expenseread expenses when that endpoint is available.kimai_list_tasksandkimai_get_taskread tasks when that endpoint is available.
Setup
Configure an MCP client to run the server with npx:
{
"mcpServers": {
"kimai": {
"command": "npx",
"args": ["-y", "@nightsquawktech/kimai-mcp-server"],
"env": {
"KIMAI_BASE_URL": "https://your-instance.example.com",
"KIMAI_API_TOKEN": "your-api-token"
}
}
}
}
For Codex global TOML config:
[mcp_servers.kimai]
command = "npx"
args = ["-y", "@nightsquawktech/kimai-mcp-server"]
[mcp_servers.kimai.env]
KIMAI_BASE_URL = "https://your-instance.example.com"
KIMAI_API_TOKEN = "your-api-token"
Environment variables
| Variable | Required | Description |
|---|---|---|
KIMAI_BASE_URL |
Yes | Base URL of your Kimai instance without a trailing slash, e.g. https://your-instance.example.com |
KIMAI_API_TOKEN |
Yes | Kimai API token (bearer token) |
KIMAI_TIMEOUT_MS |
No | HTTP request timeout in milliseconds, default 30000 |
Development
npm install
npm run dev
npm run build
Create .env for local development:
KIMAI_BASE_URL=https://your-instance.example.com
KIMAI_API_TOKEN=your-api-token
KIMAI_TIMEOUT_MS=30000
The server uses stdio for local MCP clients. Use stderr for logs so stdout remains reserved for MCP protocol messages.
License
Licensed under the GNU AGPL v3.0. Free for personal and open-source use.
Organizations that cannot comply with the AGPL can purchase a commercial license. See COMMERCIAL.md or contact hello@nightsquawk.tech.
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。