clockify-mcp-server
Allows logging and managing Clockify time entries in bulk, including listing projects, creating entries by project name with local date and start/end times, listing entries between dates, and deleting entries.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
clockify-mcp-server
Log time to your Clockify projects by asking your agent, instead of clicking through the UI.
"add 4h on ACME every morning this week and 4h on Evil Corp every afternoon"
β one
log_timecall, 10 entries created, 40h total.
A local stdio MCP server. Run it with your own API key, nothing is shared or hosted. It
ships as a single file with no dependencies: a 140 kB download, so npx starts it in a
moment.
Tool | What it does |
| Active projects you can log time to |
| Create entries in bulk, project by name (and client if names repeat), |
| Your time entries between two dates |
| Delete entries |
Times are in your Clockify profile time zone. You say 09:00, the server reads
settings.timeZone from your Clockify profile and converts to UTC.
Approval prompts come from your agent, not from this server. Whether you are asked
before each call is up to your harness and its permission settings. The server marks the
list_* tools read-only and delete_time_entries destructive, but these are
treated as hints: the server enforces no authorization of its own. Anything your API key
can do, the tools can too.
Use it π
Everything you need if you just want to log time. Takes about two minutes.
1. Have Node 20 or later. Check with node --version.
2. Get your Clockify API key:
Clockify β your avatar β Preferences β ADVANCED tab β Manage API keys β GENERATE NEW
3. Register the server with your agent:
claude mcp add clockify -s user -e CLOCKIFY_API_KEY=<key> -- npx -y @condensetech/clockify-mcp-server@1-s user writes it to your personal config so it loads in every project (the default
scope, local, would bind it to the current directory).
Add this to its MCP config:
{
"mcpServers": {
"clockify": {
"command": "npx",
"args": ["-y", "@condensetech/clockify-mcp-server@1"],
"env": { "CLOCKIFY_API_KEY": "<key>" }
}
}
}Updates are automatic: each time your harness starts the server, npx fetches the
latest 1.x release. @1 also means a breaking 2.0 never reaches you unannounced.
4. Check it in a fresh session:
list my clockify projects
log 2 hours on <project> today from 09:00 to 11:00, description test
show my clockify entries for this week
delete that entryOpen the Clockify UI after the second prompt and confirm the entry reads 09:00β11:00. If it shows a different time, your Clockify profile time zone is not what you think it is, fix it in Clockify preferences.
Environment
Variable | Required | Notes |
| yes | Preferences β Advanced β Manage API keys |
| no | Regional hosts: |
Time is logged to your active workspace: the one selected in Clockify. To use another, switch to it in Clockify.
If something goes wrong
CLOCKIFY_API_KEY is not setβ the key did not reach the server process. Put it in the harness config'senv, not in your shell.Ambiguous project "x". Candidates: β¦β deliberate. The server refuses to guess; use one of the listed names. Projects with the same name under different clients are listed asName (Client): name the client too, or pass the project id fromlist_projects.404s on every call β your workspace is on a regional host. Set
CLOCKIFY_API_BASE.Entries land at the wrong hour β check your Clockify profile time zone (see step 4 of "Use it").
Related MCP server: Clockify Time Tracking
Contribute
Setup, checks and pull request rules are in CONTRIBUTING.md.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
This server cannot be deployed
Maintenance
Related MCP Connectors
Track time in Clockify: time entries, projects, clients, tags and reports; start, stop and log time.
timesheet.io MCP server - manage timers, projects, tasks and reports
Read your tracked time and projects, pause tracking or add a note, from Claude or ChatGPT.
Nifty's MCP server β exposes tasks, projects, messages, and files as tools for AI agents.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceIntegrates with Clockify to manage time entries through natural language prompts, allowing users to register and track their work time directly via LLM conversations.27MIT
- AlicenseCqualityCmaintenanceEnables interacting with Clockify time-tracking data through natural language, providing tools to manage workspaces, projects, time entries, reports, and more via the MCP protocol.4842 PyPI1MIT
- AlicenseBqualityDmaintenanceMCP server that enables AI agents to interact with Clockify time tracking via curated workflows and a generic API tool for managing workspaces, projects, tasks, and time entries.912 npmMIT
- AlicenseAqualityCmaintenanceA standalone MCP server that exposes the ATimeLogger REST API to Claude Desktop/Code over stdio, enabling activity tracking (start/stop/pause/log), reports/history, and activity type management.864 npm1MIT