Skip the install. Get this working in under 2 minutes.
Start a free trial on cloud.anythingmcp.com, add the Kimai in one click, then point your AI client (Claude, ChatGPT, Copilot or Cursor) at the generated MCP endpoint. No Docker, no git clone, zero engineering experience required.
Summary
Kimai — the self-hosted open-source time tracker. Read and create timesheets, browse customers, projects, activities and users, and check the running clock. REST API v1 on your own Kimai instance, bearer API token.
Try asking
Example prompts for Kimai
Click any prompt to copy it. Paste into Claude, ChatGPT, Cursor, Gemini, Copilot or OpenClaw to run it against this connector.
Claude is AI and can make mistakes. Please double-check responses.
💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Kimai, paste your credentials, mint an MCP API key — done. No Docker, no
git clone, no local server.
Kimai + Claude
Kimai — the self-hosted open-source time tracker. Read and create timesheets, browse customers, projects, activities and users, and check the running clock. REST API v1 on your own Kimai instance, bearer API token.
Prerequisites
See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:
KIMAI_URL, KIMAI_API_TOKEN
Step 1 — Get credentials
Getting a token (Kimai 2.x)
- Sign in to your Kimai instance, open your user profile and go to the API tab.
- Create an API token and copy it into
KIMAI_API_TOKEN. Kimai 2.x uses a bearer token here; the olderX-AUTH-USER/X-AUTH-TOKENheader pair from Kimai 1.x is deprecated and is not what this adapter sends. - Set
KIMAI_URLto the base URL of your instance without a trailing slash and without/api, e.g.https://time.example.com. The adapter appends/api.
…(continued in the in-app connector instructions)
Step 2 — Install the adapter
curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d
Step 3 — Add the connector in Claude
Recommended path — works on claude.ai web without editing any config file.
- Open claude.ai/customize/connectors.
- Click "Add custom connector".
- Fill in:
- Name:
Kimai - URL:
https://cloud.anythingmcp.com/mcp - Authentication: Bearer token → paste your MCP API key (from AnythingMCP → Profile → MCP API Keys → New Key)
- Name:
- Click Connect to authorize.
All tools below appear in your chat — start typing prompts.
Available tools
| Tool | What it does |
|---|---|
kimai_get_version | Read the Kimai version and copyright of the connected instance |
kimai_list_timesheets | Read timesheet entries in a date range with their project, activity, duration, rate and billable flag |
kimai_get_active_timesheets | Read the entries that are running right now for the authenticated user — Kimai's live clock, answering 'am I still tracking something' |
kimai_list_customers | List customers with their number, country, currency and visible flag |
kimai_list_projects | List projects, optionally for one customer, with their budget, time budget and start and end dates |
kimai_list_activities | List activities — the task types time is booked against — either global or attached to one project |
kimai_list_users | List Kimai users with their username, alias, e-mail and roles |
kimai_create_timesheet | Book a timesheet entry against a project and activity |
kimai_stop_timesheet | Stop a running timesheet entry, setting its end to now |
FAQ
Does it work with Claude Code as well as Claude Desktop? Yes — point both at https://cloud.anythingmcp.com/mcp.
Next steps
Was this guide helpful?
