Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@salaxy-mcp Calculate salary for 80 hours at hourly rate 38.5 with income type 101"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol server that exposes a Finnish payroll (palkanlaskenta) API as MCP tools. Built with the official TypeScript MCP SDK.
get_income_typesReturns all Finnish payroll income types (tulolajit) supported by the server.
Parameters: none
Returns: JSON array of income types, each with:
Field | Description |
| Incomes Register (tulorekisteri) code, e.g. |
| Finnish name, e.g. |
| English translation, e.g. |
| Flat withholding rate used in demo calculations |
| Plain-language description of the income type |
Supported codes include time-based wages (101), piece-rate wages (102), overtime (201), shift supplements (210), holiday compensation (301), holiday bonus (302), sick pay (401), fringe benefits (501, 502), and commission pay (601).
calculate_salaryCalculates gross and net salary by applying Finnish statutory deductions:
Income tax — based on the income type's indicative withholding rate
TyEL pension — 7.45 % employee contribution (2024 rate)
Unemployment insurance — 0.79 % employee share (2024 rate)
Parameters:
Parameter | Type | Description |
|
| Hourly rate (€) when |
|
| Income type code from |
|
| Hours in the pay period; pass |
Returns:
{
"income_type": { "code": "101", "name_fi": "Aikapalkka", "name_en": "Time-based wage" },
"currency": "EUR",
"deduction_rates": {
"income_tax_pct": 25,
"pension_pct": 7.45,
"unemployment_pct": 0.79
},
"gross_salary": 3080.00,
"income_tax": 750.03,
"pension_deduction": 229.46,
"unemployment_deduction": 24.33,
"net_salary": 2076.18,
"hours_worked": 80,
"effective_hourly_rate": 38.50
}get_employeeReturns mock employee master data by ID.
Parameters:
Parameter | Type | Description |
|
| Employee identifier (case-insensitive). Available: |
Returns:
{
"employee": {
"id": "EMP001",
"first_name": "Mikael",
"last_name": "Virtanen",
"ssn_masked": "150385-****",
"employment_type": "Toistaiseksi voimassa oleva / Permanent",
"department": "Ohjelmistokehitys / Software Development",
"hourly_rate": 38.5,
"monthly_salary": 6160,
"tax_card_rate": 28,
"municipality": "Helsinki",
"iban": "FI21 1234 5600 0007 85"
}
}Related MCP server: openproject-mcp
npm install
npm run build
npm startThe server communicates over stdio (standard MCP transport). To integrate with Claude Desktop, add this to claude_desktop_config.json:
{
"mcpServers": {
"salaxy": {
"command": "node",
"args": ["/absolute/path/to/salaxy-mcp/dist/index.js"]
}
}
}salaxy-mcp/
├── src/
│ ├── index.ts # MCP server, tool definitions, salary calculation logic
│ └── data.ts # Income types and mock employee data
├── package.json
├── tsconfig.json
└── README.mdTax rates and statutory deduction percentages are illustrative 2024 values for demonstration purposes and should not be used for real payroll.
SSNs in mock data are masked; IBANs are synthetic.
This server cannot be deployed
Hosted MCP endpoint with realistic fake data for prototyping agents. 12 tools, no setup.
MCP server exposing klokin time-tracking operations (employees, time entries, stores) to AI clients.
