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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.