How do I enable write operations?
Set the environment variable `CLOCKIFY_ACCESS_MODE` to `time-tracking` (only time‑entry writes) or `full` (all 64 write tools). The legacy `CLOCKIFY_ENABLE_WRITES=true` also works and maps to `full`.

@tracegazer
Basic information
Full-coverage Clockify MCP — 112 tools across 18 domains (incl. invoices, scheduling, time-off & approvals), native OpenTelemetry observability, and a 3-tier read/time-tracking/full access model.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"clockify": {
"command": "uvx",
"args": [
"clockify-mcp"
],
"env": {
"CLOCKIFY_API_KEY": "your-clockify-api-key"
}
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
Clockify Time Tracking is a Model Context Protocol (MCP) server that gives AI assistants access to the Clockify time-tracking API. It provides 112 tools across 18 domains for querying workspaces, projects, time entries, generating reports, logging hours, and managing clients, invoices, and more — all through natural language. The server is read‑only by default, with optional write operations behind an explicit opt‑in.
Install via pip install clockify-mcp, run with uvx clockify-mcp, or use the Docker image. The easiest way with Claude Desktop is to download the prebuilt .mcpb bundle and double‑click it. Configure by setting CLOCKIFY_API_KEY in environment variables, a TOML config file at ~/.config/clockify-mcp/config.toml, or adding it to claude_desktop_config.json. Optionally set CLOCKIFY_ACCESS_MODE to time-tracking (log hours) or full (all writes).
.mcpb installer for Claude Desktopread, time-tracking, fullSet the environment variable `CLOCKIFY_ACCESS_MODE` to `time-tracking` (only time‑entry writes) or `full` (all 64 write tools). The legacy `CLOCKIFY_ENABLE_WRITES=true` also works and maps to `full`.
Tools for time off, holidays, expenses, approvals, custom fields, scheduling, invoices, and webhooks error with HTTP 402/403/404 on plans that don’t include those features.
Most operations require a workspace ID. Tools accept an optional `workspace_id` parameter; if omitted they fall back to `CLOCKIFY_DEFAULT_WORKSPACE_ID`. If neither is set, the assistant will ask you to resolve one via `list_workspaces`.
List tools accept optional `page` and `page_size` parameters and return one page. High‑volume lists (`list_time_entries`, `list_projects`, etc.) also accept `fetch_all=true` to retrieve all pages concatenated.
The server runs on STDIO by default. Use `--transport sse` for SSE/HTTP. The `streamable-http` transport is also available. Note that SSE and HTTP have no built‑in authentication—only use them bound to loopback or behind an authenticated reverse proxy.

Official 42min MCP server: let Claude, ChatGPT, Cursor or any MCP client manage your meeting scheduling. Check availability, find free slots, book, cancel and reschedule meetings, manage recurring series, secret booking

Index your docs, help center, support tickets, wikis and code into one fast knowledge base. Connect Zendesk, Confluence, Notion, GitHub, Slack, Google Drive, Jira, Salesforce, websites, PDFs and 15+ more sources. Kapa sy

Built for companies. Ready for AI agents. PaperOffice is the headless DMS your agent can actually operate: one MCP endpoint to search, read, upload, extract and sign business documents — no UI, no glue code. AI-OCR, invo
WhatsMCP — WhatsApp for AI agents. Put an AI agent on a real WhatsApp number. Expose regular WhatsApp accounts to your LLM agents over JSON-RPC. A complete Model Context Protocol server that turns phone numbers into addr

Connect AI assistants to Mailercloud, the email marketing platform — manage campaigns, contacts, lists, templates, and sending, plus AI-powered campaign analysis and deliverability audits. Endpoint: https://mcp.mailerclo
Comments