salaxy-mcp
Exposes Finnish payroll (palkanlaskenta) API as MCP tools for calculating salaries, retrieving income types, and fetching mock employee data.
README
Salaxy MCP
A Model Context Protocol server that exposes a Finnish payroll (palkanlaskenta) API as MCP tools. Built with the official TypeScript MCP SDK.
Tools
get_income_types
Returns all Finnish payroll income types (tulolajit) supported by the server.
Parameters: none
Returns: JSON array of income types, each with:
| Field | Description |
|---|---|
code |
Incomes Register (tulorekisteri) code, e.g. "101" |
name_fi |
Finnish name, e.g. "Aikapalkka" |
name_en |
English translation, e.g. "Time-based wage" |
indicative_tax_rate_pct |
Flat withholding rate used in demo calculations |
description |
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_salary
Calculates 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 |
|---|---|---|
base_salary |
number |
Hourly rate (€) when hours_worked > 0; monthly salary (€) when hours_worked = 0 |
income_type_code |
string |
Income type code from get_income_types, e.g. "101" |
hours_worked |
number |
Hours in the pay period; pass 0 for a fixed monthly salary |
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_employee
Returns mock employee master data by ID.
Parameters:
| Parameter | Type | Description |
|---|---|---|
employee_id |
string |
Employee identifier (case-insensitive). Available: EMP001, EMP002, EMP003, EMP004 |
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"
}
}
Getting started
npm install
npm run build
npm start
The 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"]
}
}
}
Project structure
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.md
Notes
- Tax 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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.