ClockifySAFE
A MCP Server to manage your time entries in Clockify
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://smithery.ai/server/@https-eduardo/clockify-mcp-server)
This MCP Server integrates with AI Tools to manage your time entries in Clockify, so you can register your time entries just sending an prompt to LLM.
Using in Claude Desktop
Installing via Smithery
To install clockify-mcp-server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @https-eduardo/clockify-mcp-server --client claude
Installing Manually
First, install tsx globally
npm i -g tsx
Then insert the MCP server in claude_desktop_config
{
"mcpServers": {
"clockify-time-entries": {
"command": "tsx",
"args": ["ABSOLUTE_PATH/src/index.ts", "--local"],
"env": {
"CLOCKIFY_API_URL": "https://api.clockify.me/api/v1",
"CLOCKIFY_API_TOKEN": "YOUR_CLOCKIFY_API_TOKEN_HERE"
}
}
}
}cc277521bd55OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add clockify-mcp-server --env CLOCKIFY_API_TOKEN=${CLOCKIFY_API_TOKEN} -- npx -y [email protected]{
"mcpServers": {
"clockify-mcp-server": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"CLOCKIFY_API_TOKEN": "${CLOCKIFY_API_TOKEN}"
}
}
}
}Exposed tools (14)
7 read · 5 write · 2 destructive. Blast radius: 2 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
create-tag | write | Create a new tag in a workspace |
create-task | write | Create a new task (activity) within a project. The created task can be associated with time entries. |
create-time-entry | write | Register a new time entry of a task or break in a workspace |
delete-task | destructive | Permanently delete a task (activity) from a project. Requires an admin API token — Clockify returns 403 for non-admins regardless of the task |
delete-time-entry | destructive | Delete a specific time entry from a workspace |
edit-time-entry | write | Edit an existing time entry in a workspace |
get-current-user | read | Get the current user id and name, to search for entries is required to have the user id |
get-hours-by-client | read | Get total hours worked per client for a date range in a workspace, aggregated on the server. Returns a compact summary (hours per client + total) instead of raw time entries. Note: projects are grouped by their Clockify client name. |
get-projects | read | Get workspace projects id and name, the projects can be associated with time entries |
get-tags | read | Get all tags in a workspace |
get-workspaces | read | Get user available workspaces id and name, a workspace is required to manage time entries |
list-tasks | read | List tasks (activities) within a project. Tasks can be associated with time entries. |
list-time-entries | read | Get registered time entries from a workspace |
update-task | write | Update a task (activity) in a project: rename it, change its status (ACTIVE/DONE), and/or reassign it. Clockify |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (3)
delete-task, delete-time-entry
@modelcontextprotocol/sdk, axios, dotenv, zod, @smithery/cli, @types/node, ts-node-dev, tsx
Gates applied: no_behavioural_pass, no_license.
cc277521bd55full audit observations/trust-audit/mcp-server/https-eduardo__clockify.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | cc277521bd55 | SAFE | B | 89 | first audit |
Questions
What is the Clockify MCP server?
A MCP Server to manage your time entries in Clockify
What tools does Clockify expose?
14 in total: 7 read-only, 5 that write, and 2 that can delete or overwrite (delete-task, delete-time-entry). Every one is listed on this page with its risk.
Is Clockify safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 2 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Clockify need?
It reads CLOCKIFY_API_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Clockify run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as clockify-mcp-server at 1.1.1.
How current is this page?
The grade is for one exact copy of the source (cc277521bd55), read on 2026-10-08. The repository is watched and re-audited when it changes.