mcpField
L
leave-pto-requests-approvals

leave-pto-requests-approvals

Local
mcp.zovo.oneBusiness & Marketing2Updated 1d ago
RepositoryVisit website

About leave-pto-requests-approvals

leave-pto-requests-approvals is an employee leave-management MCP server for solopreneurs and small studios. It handles requests, approvals, balances, and absence calendars, while rejecting overlapping requests for the same person.

Key features

  1. 01Manage annual allowances and carryover
  2. 02Record full- or half-day leave requests
  3. 03Approve, reject, or cancel requests
  4. 04View balances and leave calendars
  5. 05Pro CSV import and ICS export

Use cases

  1. 01Track team members’ remaining leave
  2. 02Review vacation, sick, or personal leave requests
  3. 03Check absences across a date range

MCP support

It provides MCP clients with tools for employees, leave requests, decisions, balances, and calendars; Pro adds bulk CSV import and ICS calendar export.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository
Packages
mcpbleave.mcpb0.22.5

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

mcp-leave

theluckystrike/mcp-leave MCP server

In the official MCP Registry (io.github.theluckystrike/leave). Employee leave/PTO tracking for solopreneurs and small studios: who is off, when, and how many days each person has left. Add employees with an annual allowance and any carried-over days, log vacation/sick/personal requests (including half-days), approve or reject them, and read balances, conflicts and who-is-out calendars directly from your MCP client - Claude Desktop, Cursor, or any MCP host.

Tools

  • "leave_employee_add" - add an employee with annualAllowance (and optional carriedOver).
  • "leave_request" - log a leave request (employee, type, start, end, optional halfDay, reason).
  • "leave_approve" / "leave_reject" - decide a request; decisions are recorded with dates.
  • "leave_cancel" - cancel a pending or approved request (keeps the audit trail).
  • "leave_balance" - allowance, carried, approved, pending, committed and remaining days per employee.
  • "leave_out_range" - who is out in a date range: day-by-day calendar rows plus person-days.
  • "leave_list" - all employees and requests, filterable by employee and status.
  • "leave_import" (Pro) - bulk-create requests from CSV; conflicting rows are rejected one by one, valid rows still apply.
  • "leave_export_ics" (Pro) - export approved leave as an RFC5545 .ics calendar.

The one rule that decides everything else

A day is committed when the request that spends it is approved or pending. Balance is allowance + carried − approved − pending. Cancelling returns the days immediately; rejecting never charged them.

Overlapping requests for the same person are refused at creation time - both pending and approved count - so the calendar never contains two requests claiming the same day.

Free vs Pro

The free tier is the full CRUD surface: employees, requests, approvals, balances, calendars - watermark-free, no request limits. Pro (an MCP_LICENSE_KEY, activate with "license_activate") adds bulk CSV import and ICS calendar export. Run "license_status" to see the current tier.

Quick start

{
  "mcpServers": {
    "leave": { "command": "npx", "args": ["-y", "@theluckystrike/mcp-leave"] }
  }
}

Data lives in a single JSON store (~/.mcp-leave/store.json, or $XDG_DATA_HOME/mcp-servers/leave/store.json when set), written atomically under a file lock, so two clients on one machine never interleave writes.

Use these docs as an MCP server

Any MCP client (Claude, Cursor, Windsurf, VS Code) can read this repository's documentation directly via GitMCP - no install:

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.