calculate_payroll

計算台灣某月薪資的勞保(含就保)、健保、勞退、職災各方(員工/雇主/政府)負擔。支援不同身份別、眷屬、自提、部分工時。結果僅供參考,以勞保局、健保署核發之繳款單為準,不構成法律或會計建議。

Server Taiwan Payroll taiwan-payroll-mcp
Category Read
Risk class Low
Parameters 91 required

What calculate_payroll does on Taiwan Payroll

AI agents call calculate_payroll to retrieve information from Taiwan Payroll without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

ParameterTypeRequiredDescription
year integer 年度(西元,如 2026)。省略則使用最新可用年度;可先用 list_years 查可用年度。
identity string 身份別(預設 category1):category1=本國勞工或外籍配偶;migrantGeneral=一般移工(勞保僅普通事故 11.5%、無就保/勞退);migrantDomestic=家事移工(僅健保+職災,職災費率請以 occupationalRate 傳 0.0018)。不適用的險種回傳 0。
partTime boolean 是否為部分工時:true 時未達基本工資者勞保/健保對到官方低級距(職保仍歸第 1 級)。預設 false。
rounding string 進位策略:round=四捨五入(預設)、ceil=無條件進位、aggregate-then-round=合計後分配(政府方吸收進位差)。
dependents integer 健保眷屬人數(計費上限 3 口),預設 0。
monthlySalary number Yes 月薪資總額(經常性薪資),新臺幣元/月。
occupationalRate number 職災行業別費率,小數比例(如 0.0021 表 0.21%;家事移工 0.0018),範圍 [0, 0.02)。省略則用該年度平均費率。
employmentInsurance boolean 是否參加就業保險(勞保費率 12.5% 或 11.5%),預設 true。一般移工/家事移工一律視為不參加。
pensionSelfContribution number 勞工自願提繳率,小數(0~0.06,如 0.06 表 6%),預設 0。

Parameters from the server's own tool schema.

Why calculate_payroll needs a policy

This tool performs read-like calculations of statutory payroll amounts based on input data (employee salary, status, dependents, etc.). It is purely computational and informational—it calculates what amounts should be deducted or contributed according to Taiwan law, but does not execute payments, modify payroll systems, delete records, or run arbitrary code. The disclaimer reinforces that outputs are advisory only.

From the tool's definition calculate_payroll - computes payroll deductions (labor insurance, health insurance, pension, occupational injury insurance) for informational purposes.

Questions about calculate_payroll

What does the calculate_payroll tool do? +

計算台灣某月薪資的勞保(含就保)、健保、勞退、職災各方(員工/雇主/政府)負擔。支援不同身份別、眷屬、自提、部分工時。結果僅供參考,以勞保局、健保署核發之繳款單為準,不構成法律或會計建議。. It is categorised as a Read tool in the Taiwan Payroll MCP Server, which means it retrieves data without modifying state.

What parameters does calculate_payroll accept? +

calculate_payroll accepts 9 parameters: year, identity, partTime, rounding, dependents, monthlySalary, occupationalRate, employmentInsurance, pensionSelfContribution. Required: monthlySalary. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on calculate_payroll? +

Register the Taiwan Payroll MCP server in PolicyLayer and add a rule for calculate_payroll: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Taiwan Payroll. Nothing to install.

What risk level is calculate_payroll? +

calculate_payroll is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit calculate_payroll? +

Yes. Add a rate_limit block to the calculate_payroll rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block calculate_payroll completely? +

Set action: deny in the PolicyLayer policy for calculate_payroll. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides calculate_payroll? +

calculate_payroll is provided by the Taiwan Payroll MCP server (taiwan-payroll-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER SERVER

Every MCP server has a record like this.

Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.