Taiwan Payroll

9 tools. 0 can modify or destroy data without limits.

Read-only server. Low risk, but rate limits prevent runaway API costs.

Last updated:

0 can modify or destroy data
9 read-only
9 tools total

Verified server · catalogue entry verified 02/07/2026 · full schemas captured for 8 of 9 tools

How to control Taiwan Payroll ↓

What Taiwan Payroll exposes to your agents

Read (9) Write / Execute (0) Destructive / Financial (0)

What Taiwan Payroll costs in tokens

3,938 tokens of tool definitions, loaded on every request
2.0% of a 200k context window
748 heaviest tool: calculate_prorated

What can go wrong

Even read-only tools carry cost. An agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up bills.

How to control Taiwan Payroll

PolicyLayer is an MCP gateway — it sits between your AI agents and Taiwan Payroll, and nothing reaches the server without passing your rules. These are the rules we recommend:

Cap read operations
{
  "calculate_employer_supplementary_premium": {
    "limits": [
      {
        "counter": "calculate_employer_supplementary_premium_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register Taiwan Payroll — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON TAIWAN PAYROLL →

Instant setup, no code required.

All 9 Taiwan Payroll tools

READ 9 tools
Read calculate_employer_supplementary_premium 計算雇主端二代健保補充保費(費率 2.11%):(每月支付薪資總額 − 受僱者當月健保投保金額總額) × 費率,無上限。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。 Read calculate_income_tax_withholding 計算薪資所得扣繳稅額:居住者固定月薪(公式法)、非每月給付獎金(5%,未達起扣標準免扣)、非居住者(18%;月薪≤1.5倍基本工資為6%)。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。 Read calculate_old_age_lump_sum 依勞保老年一次金法定公式(平均月投保薪資 × 給付月數;年資每滿 1 年給 1 個月、逾 60 歲後之年資最多計入 5 年)試算給付金額。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。 Read calculate_old_age_pension 依勞保老年年金法定公式(擇優兩式、提前/延後增減給每年 ±4%,上限 ±5 年(±20%))試算月領金額;年資未滿 15 年不符年金請領資格。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。 Read calculate_old_age_single_payment 依勞保一次請領老年給付法定公式(基數制:前 15 年每年 1 個基數、第 16 年起每年 2 個基數、60 歲前最高 45 個基數、逾 60 歲後年資每年 2 個基數最多計 5 年、合併最高 50 個基數)試算給付金額。 Read 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。 Read calculate_prorated 計算月中到職或離職當月的破月保費。勞保/職保/勞退按日(30 日基準);健保採官方「月底歸屬」——到職當月計整月、離職當月不計。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。 Read calculate_supplementary_premium 計算二代健保補充保費(費率 2.11%)。bonus 課徵年度累計超過當月投保額 4 倍部分;其餘五類單次達門檻全額課(單次上限 1,000 萬)。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。 Read list_years 列出目前支援的年度、資料版本與基本工資(月薪/時薪)。計算前可先用本工具確認有效的 year 值。

Questions about Taiwan Payroll

Is the Taiwan Payroll MCP server safe to use without restrictions? +

The Taiwan Payroll server is primarily read-only with 9 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the Taiwan Payroll MCP server expose? +

9 tools across 1 categories: Read. 9 are read-only. 0 can modify, create, or delete data.

How do I enforce a policy on Taiwan Payroll? +

Register the Taiwan Payroll MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Taiwan Payroll tool call.

Deterministic rules across all 9 Taiwan Payroll tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

9 Taiwan Payroll tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.