FreeToolHub
44 calculators for AI agents: US tax, finance, business + an MCP engineering & security suite.
我该使用它吗
质量与安全性
发现(6)
- LOW在 calculate_roi 中
- LOW在 calculate_rental_affordability 中
- LOW在 calculate_freelancer_pricing 中
- LOW在 score_mcp_server_trust 中
- LOW在 plan_mcp_token_budget 中
- LOW在 compare_automation_platform_costs 中
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高,可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中:
{
"mcpServers": {
"freetoolhub": {
"url": "https://freetoolhub.org/api/mcp"
}
}
}远程端点
https://freetoolhub.org/api/mcpstreamable-http它能做什么
工具清单
工具(50)
🟢calculate_se_tax(netEarnings, filingStatus, state)
Calculate US self-employment tax (15.3%), QBI deduction, quarterly payments. Uses latest IRS brackets from CDN data.
输入模式
{
"type": "object",
"properties": {
"netEarnings": {
"type": "number",
"description": "Net SE income"
},
"filingStatus": {
"type": "string",
"description": "Tax filing status",
"enum": [
"single",
"married",
"head"
],
"default": "single"
},
"state": {
"type": "string",
"description": "US state abbreviation (e.g. CA, NY, TX)",
"default": ""
}
},
"required": [
"netEarnings"
]
}🟢calculate_freelancer_tax(grossIncome, businessExpenses, filingStatus, state)
Complete freelancer tax: SE tax, QBI deduction, federal + state income tax. Returns quarterly payment. Uses latest CDN data.
输入模式
{
"type": "object",
"properties": {
"grossIncome": {
"type": "number",
"description": "Gross freelance income"
},
"businessExpenses": {
"type": "number",
"description": "Deductible expenses"
},
"filingStatus": {
"type": "string",
"description": "Tax filing status",
"enum": [
"single",
"married",
"head"
],
"default": "single"
},
"state": {
"type": "string",
"description": "US state abbreviation (e.g. CA, NY, TX)",
"default": ""
}
},
"required": [
"grossIncome"
]
}🟢calculate_1099k_tax(grossReceipts, costOfGoodsSold, otherExpenses, filingStatus, state)
Estimate tax on 1099-K income (reselling, gig work). SE tax, QBI, quarterly 1040-ES. Uses latest CDN data.
输入模式
{
"type": "object",
"properties": {
"grossReceipts": {
"type": "number",
"description": "Total 1099-K receipts"
},
"costOfGoodsSold": {
"type": "number",
"description": "COGS"
},
"otherExpenses": {
"type": "number",
"description": "Other expenses"
},
"filingStatus": {
"type": "string",
"description": "Tax filing status",
"enum": [
"single",
"married",
"head"
],
"default": "single"
},
"state": {
"type": "string",
"description": "US state abbreviation (e.g. CA, NY, TX)",
"default": ""
}
},
"required": [
"grossReceipts"
]
}🟢calculate_capital_gains_tax(purchasePrice, salePrice, holdingPeriodDays, filingStatus, ordinaryIncome, ...)
US capital gains tax on stock/crypto. Short vs long-term, NIIT 3.8%, state tax. Uses latest CDN LTCG brackets.
输入模式
{
"type": "object",
"properties": {
"purchasePrice": {
"type": "number",
"description": "Cost basis"
},
"salePrice": {
"type": "number",
"description": "Sale price"
},
"holdingPeriodDays": {
"type": "number",
"description": "Days held (>365=long-term)"
},
"filingStatus": {
"type": "string",
"description": "Tax filing status",
"enum": [
"single",
"married",
"head"
],
"default": "single"
},
"ordinaryIncome": {
"type": "number",
"description": "Annual ordinary income"
},
"state": {
"type": "string",
"description": "US state abbreviation (e.g. CA, NY, TX)",
"default": ""
}
},
"required": [
"purchasePrice",
"salePrice",
"holdingPeriodDays"
]
}⚪compare_w2_vs_1099(w2Salary, contractorRate, filingStatus, state)
Compare take-home pay: W-2 salary vs 1099 contractor rate. SE tax, FICA, standard deduction, state tax. Latest CDN data.
输入模式
{
"type": "object",
"properties": {
"w2Salary": {
"type": "number",
"description": "W-2 annual salary"
},
"contractorRate": {
"type": "number",
"description": "1099 annual income"
},
"filingStatus": {
"type": "string",
"description": "Tax filing status",
"enum": [
"single",
"married",
"head"
],
"default": "single"
},
"state": {
"type": "string",
"description": "US state abbreviation (e.g. CA, NY, TX)",
"default": ""
}
},
"required": [
"w2Salary",
"contractorRate"
]
}🟢get_sales_tax_rate(state, amount)
Get state sales tax rate for any US state. Returns base state rate + estimated local rate. Latest CDN data.
输入模式
{
"type": "object",
"properties": {
"state": {
"type": "string",
"description": "US state abbreviation (e.g. CA, NY, TX)"
},
"amount": {
"type": "number",
"description": "Purchase amount (optional)"
}
},
"required": [
"state"
]
}🟢calculate_payroll_tax(grossSalary, filingStatus, state, retirementContribution)
Calculate paycheck deductions: federal tax, Social Security, Medicare, state tax. All 50 states. Latest CDN data.
输入模式
{
"type": "object",
"properties": {
"grossSalary": {
"type": "number",
"description": "Annual gross salary"
},
"filingStatus": {
"type": "string",
"description": "Tax filing status",
"enum": [
"single",
"married",
"head"
],
"default": "single"
},
"state": {
"type": "string",
"description": "US state abbreviation (e.g. CA, NY, TX)",
"default": ""
},
"retirementContribution": {
"type": "number",
"description": "401(k) contribution"
}
},
"required": [
"grossSalary"
]
}🟢calculate_estate_tax(estateValue, spousalInheritance)
Calculate federal estate tax. 2026 exemption $13.61M, 40% rate. Includes marital deduction.
输入模式
{
"type": "object",
"properties": {
"estateValue": {
"type": "number",
"description": "Total estate value"
},
"spousalInheritance": {
"type": "number",
"description": "Amount left to spouse (marital deduction)"
}
},
"required": [
"estateValue"
]
}🟢calculate_hsa_fsa_savings(hsaContribution, fsaContribution, filingStatus, state, marginalRate)
Calculate tax savings from HSA and FSA contributions. Federal + FICA + state tax savings. Latest CDN limits.
输入模式
{
"type": "object",
"properties": {
"hsaContribution": {
"type": "number",
"description": "HSA annual contribution"
},
"fsaContribution": {
"type": "number",
"description": "FSA annual contribution"
},
"filingStatus": {
"type": "string",
"description": "Tax filing status",
"enum": [
"single",
"married",
"head"
],
"default": "single"
},
"state": {
"type": "string",
"description": "US state abbreviation (e.g. CA, NY, TX)",
"default": ""
},
"marginalRate": {
"type": "number",
"description": "Your marginal tax rate % (e.g. 24)"
}
},
"required": []
}🟢calculate_quarterly_tax(annualIncome, businessExpenses, filingStatus, state)
Calculate quarterly estimated tax payments (Form 1040-ES). SE tax + income tax divided by 4. Latest CDN data.
输入模式
{
"type": "object",
"properties": {
"annualIncome": {
"type": "number",
"description": "Estimated annual net income"
},
"businessExpenses": {
"type": "number",
"description": "Estimated expenses"
},
"filingStatus": {
"type": "string",
"description": "Tax filing status",
"enum": [
"single",
"married",
"head"
],
"default": "single"
},
"state": {
"type": "string",
"description": "US state abbreviation (e.g. CA, NY, TX)",
"default": ""
}
},
"required": [
"annualIncome"
]
}🟢check_economic_nexus(totalSales, statesWithSales)
Check which US states you have economic nexus in for sales tax collection. Based on Wayfair ruling. Latest CDN thresholds.
输入模式
{
"type": "object",
"properties": {
"totalSales": {
"type": "number",
"description": "Total annual US sales"
},
"statesWithSales": {
"type": "number",
"description": "Number of states you sell to"
}
},
"required": [
"totalSales"
]
}🟢calculate_tariff(productValue, freight, tariffRate, category)
Estimate import duties and landed cost by HS code category. Covers US MFN + Section 301 tariffs.
输入模式
{
"type": "object",
"properties": {
"productValue": {
"type": "number",
"description": "Product value (FOB)"
},
"freight": {
"type": "number",
"description": "Freight cost"
},
"tariffRate": {
"type": "number",
"description": "Tariff rate % (e.g. 7.5 for 7.5%)"
},
"category": {
"type": "string",
"description": "Product category"
}
},
"required": [
"productValue"
]
}🟢calculate_compound_interest(principal, monthlyContribution, annualRate, years, inflationRate)
Compound interest with monthly contributions. Returns final balance, total interest, inflation-adjusted value. Uses latest CDN inflation rate.
输入模式
{
"type": "object",
"properties": {
"principal": {
"type": "number",
"description": "Initial investment"
},
"monthlyContribution": {
"type": "number",
"description": "Monthly contribution"
},
"annualRate": {
"type": "number",
"description": "Annual rate % (e.g. 7)"
},
"years": {
"type": "number",
"description": "Years"
},
"inflationRate": {
"type": "number",
"description": "Inflation rate % (default: from CDN)"
}
},
"required": [
"principal",
"annualRate",
"years"
]
}🟢calculate_mortgage(homePrice, downPayment, interestRate, loanTermYears, propertyTaxRate, ...)
Monthly mortgage payment (P&I) + property tax, insurance, PMI. Full PITI breakdown. Uses latest CDN mortgage rates for defaults.
输入模式
{
"type": "object",
"properties": {
"homePrice": {
"type": "number",
"description": "Home price"
},
"downPayment": {
"type": "number",
"description": "Down payment"
},
"interestRate": {
"type": "number",
"description": "Interest rate % (default: from CDN)"
},
"loanTermYears": {
"type": "number",
"description": "Loan term years"
},
"propertyTaxRate": {
"type": "number",
"description": "Property tax % (default 1.1)"
},
"insuranceRate": {
"type": "number",
"description": "Insurance % (default 0.35)"
}
},
"required": [
"homePrice",
"downPayment"
]
}🟡compare_401k_vs_roth(annualContribution, currentTaxRate, retirementTaxRate, annualReturn, years, ...)
Compare 401(k) pre-tax vs Roth IRA post-tax. 30-year growth, tax drag, recommendation. Uses latest CDN contribution limits.
输入模式
{
"type": "object",
"properties": {
"annualContribution": {
"type": "number",
"description": "Annual contribution"
},
"currentTaxRate": {
"type": "number",
"description": "Current tax rate %"
},
"retirementTaxRate": {
"type": "number",
"description": "Expected retirement tax rate %"
},
"annualReturn": {
"type": "number",
"description": "Annual return % (default 7)"
},
"years": {
"type": "number",
"description": "Years to retirement (default 30)"
},
"employerMatch": {
"type": "number",
"description": "Employer match $/yr"
}
},
"required": [
"annualContribution",
"currentTaxRate",
"retirementTaxRate"
]
}🟢calculate_car_loan(price, downPayment, tradeIn, interestRate, loanTermMonths, ...)
Monthly car payment, total interest, amortization. Includes sales tax, trade-in, down payment. Uses latest CDN sales tax rates.
输入模式
{
"type": "object",
"properties": {
"price": {
"type": "number",
"description": "Car price"
},
"downPayment": {
"type": "number",
"description": "Down payment"
},
"tradeIn": {
"type": "number",
"description": "Trade-in value"
},
"interestRate": {
"type": "number",
"description": "Interest rate %"
},
"loanTermMonths": {
"type": "number",
"description": "Loan term months (default 60)"
},
"salesTaxRate": {
"type": "number",
"description": "Sales tax % (default: from CDN by state)"
},
"state": {
"type": "string",
"description": "US state for sales tax lookup"
}
},
"required": [
"price",
"interestRate"
]
}🟢calculate_rental_roi(propertyValue, monthlyRent, downPayment, interestRate, vacancyRate, ...)
Rental property ROI: cap rate, cash-on-cash return, NOI, annual cash flow. Includes vacancy and management.
输入模式
{
"type": "object",
"properties": {
"propertyValue": {
"type": "number",
"description": "Property value"
},
"monthlyRent": {
"type": "number",
"description": "Monthly rent"
},
"downPayment": {
"type": "number",
"description": "Down payment"
},
"interestRate": {
"type": "number",
"description": "Mortgage rate %"
},
"vacancyRate": {
"type": "number",
"description": "Vacancy rate % (default 5)"
},
"managementRate": {
"type": "number",
"description": "Property management % (default 8)"
}
},
"required": [
"propertyValue",
"monthlyRent",
"downPayment"
]
}🟢calculate_student_loan(loanAmount, interestRate, loanTermYears, extraPayment)
Student loan payoff: monthly payment, total interest, months saved with extra payments.
输入模式
{
"type": "object",
"properties": {
"loanAmount": {
"type": "number",
"description": "Loan amount"
},
"interestRate": {
"type": "number",
"description": "Interest rate %"
},
"loanTermYears": {
"type": "number",
"description": "Loan term years (default 10)"
},
"extraPayment": {
"type": "number",
"description": "Extra monthly payment"
}
},
"required": [
"loanAmount",
"interestRate"
]
}🟢calculate_roi(revenue, cost, adSpend, clicks, conversions)
ROI, ROAS, net profit, CPA, CPC for marketing campaigns. Facebook, Google, TikTok ad analysis.
输入模式
{
"type": "object",
"properties": {
"revenue": {
"type": "number",
"description": "Total revenue"
},
"cost": {
"type": "number",
"description": "Total cost"
},
"adSpend": {
"type": "number",
"description": "Ad spend (for ROAS)"
},
"clicks": {
"type": "number",
"description": "Ad clicks (for CPC)"
},
"conversions": {
"type": "number",
"description": "Conversions (for CPA)"
}
},
"required": [
"revenue",
"cost"
]
}🟢calculate_life_insurance(annualIncome, yearsToReplace, debt, mortgage, collegeFund, ...)
Calculate life insurance needs using DIME method: Debt, Income, Mortgage, Education.
输入模式
{
"type": "object",
"properties": {
"annualIncome": {
"type": "number",
"description": "Annual income (for income replacement)"
},
"yearsToReplace": {
"type": "number",
"description": "Years to replace income (default 10)"
},
"debt": {
"type": "number",
"description": "Outstanding debt (excluding mortgage)"
},
"mortgage": {
"type": "number",
"description": "Mortgage balance"
},
"collegeFund": {
"type": "number",
"description": "College fund per child"
},
"children": {
"type": "number",
"description": "Number of children"
},
"savings": {
"type": "number",
"description": "Existing savings/insurance"
}
},
"required": [
"annualIncome"
]
}🟢calculate_rental_affordability(monthlyIncome, monthlyDebts)
How much rent can you afford? 30% rule, DTI ratio, comfortable rent range.
输入模式
{
"type": "object",
"properties": {
"monthlyIncome": {
"type": "number",
"description": "Monthly income"
},
"monthlyDebts": {
"type": "number",
"description": "Monthly debt payments"
}
},
"required": [
"monthlyIncome"
]
}🟢calculate_home_equity(homeValue, mortgageBalance, interestRate, loanTermYears)
Calculate home equity, max borrowable amount (HELOC), and monthly payments. LTV limits included.
输入模式
{
"type": "object",
"properties": {
"homeValue": {
"type": "number",
"description": "Current home value"
},
"mortgageBalance": {
"type": "number",
"description": "Remaining mortgage balance"
},
"interestRate": {
"type": "number",
"description": "HELOC rate %"
},
"loanTermYears": {
"type": "number",
"description": "Loan term years (default 15)"
}
},
"required": [
"homeValue",
"mortgageBalance"
]
}🟢calculate_break_even(fixedCosts, pricePerUnit, variableCostPerUnit, targetProfit)
Break-even point: units to sell to cover fixed costs. Contribution margin, target profit analysis.
输入模式
{
"type": "object",
"properties": {
"fixedCosts": {
"type": "number",
"description": "Fixed costs"
},
"pricePerUnit": {
"type": "number",
"description": "Price per unit"
},
"variableCostPerUnit": {
"type": "number",
"description": "Variable cost per unit"
},
"targetProfit": {
"type": "number",
"description": "Target profit"
}
},
"required": [
"fixedCosts",
"pricePerUnit",
"variableCostPerUnit"
]
}⚪compare_llc_cost(state, years)
Compare LLC formation and maintenance costs across US states. 5-year total cost. Uses latest CDN LLC state fees data.
输入模式
{
"type": "object",
"properties": {
"state": {
"type": "string",
"description": "State abbreviation (optional, omit for comparison)"
},
"years": {
"type": "number",
"description": "Years to calculate (default 5)"
}
},
"required": []
}🟢calculate_dropship_profit(salePrice, productCost, adSpendPerOrder, shippingCost, platform, ...)
True dropshipping profit after product cost, platform fees, payment processing, ad spend. Uses latest CDN payment processor fees.
输入模式
{
"type": "object",
"properties": {
"salePrice": {
"type": "number",
"description": "Selling price"
},
"productCost": {
"type": "number",
"description": "Product cost"
},
"adSpendPerOrder": {
"type": "number",
"description": "Ad spend per order"
},
"shippingCost": {
"type": "number",
"description": "Shipping cost"
},
"platform": {
"type": "string",
"description": "Platform (shopify/etsy/woocommerce)"
},
"paymentProcessor": {
"type": "string",
"description": "Payment processor ID"
}
},
"required": [
"salePrice",
"productCost",
"adSpendPerOrder"
]
}🟢calculate_reseller_profit(purchasePrice, salePrice, shippingCost, state)
Compare real profit across reselling platforms (eBay, Poshmark, Mercari, etc.) after fees. Uses latest CDN platform fee data.
输入模式
{
"type": "object",
"properties": {
"purchasePrice": {
"type": "number",
"description": "Purchase price"
},
"salePrice": {
"type": "number",
"description": "Sale price"
},
"shippingCost": {
"type": "number",
"description": "Shipping cost"
},
"state": {
"type": "string",
"description": "US state for tax estimate"
}
},
"required": [
"purchasePrice",
"salePrice"
]
}🟢calculate_freelancer_pricing(hourlyRate, projectHours, overheadPct, profitMarginPct)
Turn hourly rate into project quote with overhead, profit margin, milestone splits.
输入模式
{
"type": "object",
"properties": {
"hourlyRate": {
"type": "number",
"description": "Desired hourly rate"
},
"projectHours": {
"type": "number",
"description": "Estimated project hours"
},
"overheadPct": {
"type": "number",
"description": "Overhead % (default 20)"
},
"profitMarginPct": {
"type": "number",
"description": "Profit margin % (default 15)"
}
},
"required": [
"hourlyRate",
"projectHours"
]
}🟢calculate_income_tax(grossIncome, filingStatus, state, preTaxDeductions, itemizedDeductions)
US income tax for 2026: federal tax bracket by bracket, state tax, marginal vs effective rate. Uses latest IRS brackets from CDN data.
输入模式
{
"type": "object",
"properties": {
"grossIncome": {
"type": "number",
"description": "Gross annual income"
},
"filingStatus": {
"type": "string",
"description": "Tax filing status",
"enum": [
"single",
"married",
"head"
],
"default": "single"
},
"state": {
"type": "string",
"description": "US state abbreviation (e.g. CA, NY, TX)",
"default": ""
},
"preTaxDeductions": {
"type": "number",
"description": "Pre-tax deductions (401k, HSA)"
},
"itemizedDeductions": {
"type": "number",
"description": "Itemized deductions (used only if above standard)"
}
},
"required": [
"grossIncome"
]
}🟢calculate_tax_refund(grossIncome, federalWithheld, filingStatus, state, stateWithheld, ...)
Estimate US tax refund or balance due before filing: tax owed minus withholding minus credits, federal and state. NOT the IRS refund tracker.
输入模式
{
"type": "object",
"properties": {
"grossIncome": {
"type": "number",
"description": "Gross annual income"
},
"federalWithheld": {
"type": "number",
"description": "Federal tax already withheld"
},
"filingStatus": {
"type": "string",
"description": "Tax filing status",
"enum": [
"single",
"married",
"head"
],
"default": "single"
},
"state": {
"type": "string",
"description": "US state abbreviation (e.g. CA, NY, TX)",
"default": ""
},
"stateWithheld": {
"type": "number",
"description": "State tax withheld"
},
"credits": {
"type": "number",
"description": "Tax credits (e.g. Child Tax Credit)"
},
"preTaxDeductions": {
"type": "number",
"description": "Pre-tax deductions (401k, HSA)"
},
"itemizedDeductions": {
"type": "number",
"description": "Itemized deductions"
}
},
"required": [
"grossIncome",
"federalWithheld"
]
}🟢calculate_loan(principal, interestRate, termYears, extraMonthlyPayment)
Any fixed-rate loan: monthly payment, total interest, payoff time, and interest saved by extra monthly payments.
输入模式
{
"type": "object",
"properties": {
"principal": {
"type": "number",
"description": "Loan amount"
},
"interestRate": {
"type": "number",
"description": "Annual interest rate %"
},
"termYears": {
"type": "number",
"description": "Loan term in years"
},
"extraMonthlyPayment": {
"type": "number",
"description": "Extra monthly payment"
}
},
"required": [
"principal",
"interestRate",
"termYears"
]
}🟢calculate_retirement(currentAge, retirementAge, currentSavings, monthlyContribution, annualReturnPct, ...)
Retirement projection in today's dollars: projected nest egg, sustainable income at your withdrawal rate, gap, and the monthly contribution that closes it.
输入模式
{
"type": "object",
"properties": {
"currentAge": {
"type": "number",
"description": "Current age"
},
"retirementAge": {
"type": "number",
"description": "Planned retirement age"
},
"currentSavings": {
"type": "number",
"description": "Current retirement savings"
},
"monthlyContribution": {
"type": "number",
"description": "Monthly contribution"
},
"annualReturnPct": {
"type": "number",
"description": "Expected annual return %"
},
"inflationPct": {
"type": "number",
"description": "Expected inflation %"
},
"desiredAnnualIncome": {
"type": "number",
"description": "Desired annual income in retirement (today's dollars)"
},
"otherRetirementIncome": {
"type": "number",
"description": "Other retirement income, e.g. Social Security (today's dollars)"
},
"withdrawalRatePct": {
"type": "number",
"description": "Withdrawal rate % (default 4)"
}
},
"required": [
"currentAge",
"retirementAge",
"currentSavings",
"monthlyContribution",
"annualReturnPct",
"inflationPct",
"desiredAnnualIncome"
]
}🟢calculate_margin(cost, price, marginPct, markupPct, discountPct)
Gross margin AND markup for the same deal, plus reverse pricing from a target margin or markup and the real margin cost of a discount.
输入模式
{
"type": "object",
"properties": {
"cost": {
"type": "number",
"description": "Unit cost (what you paid)"
},
"price": {
"type": "number",
"description": "Selling price — omit if you are solving from a target"
},
"marginPct": {
"type": "number",
"description": "Target gross margin % — solve for price"
},
"markupPct": {
"type": "number",
"description": "Target markup % — solve for price"
},
"discountPct": {
"type": "number",
"description": "Discount to test against the resulting price"
}
},
"required": [
"cost"
]
}🟢calculate_pay_raise(currentSalary, filingStatus, state, raisePct, raiseAmount, ...)
What a raise is actually worth after tax. Runs the real brackets before and after, so bracket crossings are handled — not a flat marginal rate applied to the raise.
输入模式
{
"type": "object",
"properties": {
"currentSalary": {
"type": "number",
"description": "Current annual salary"
},
"filingStatus": {
"type": "string",
"description": "Tax filing status",
"enum": [
"single",
"married",
"head"
],
"default": "single"
},
"state": {
"type": "string",
"description": "US state abbreviation (e.g. CA, NY, TX)",
"default": ""
},
"raisePct": {
"type": "number",
"description": "Raise as a percentage, e.g. 5 (negative for a cut)"
},
"raiseAmount": {
"type": "number",
"description": "Raise as a dollar amount — takes priority over raisePct"
},
"preTaxDeductions": {
"type": "number",
"description": "Pre-tax deductions (401k, HSA), held constant"
}
},
"required": [
"currentSalary"
]
}⚪estimate_mcp_context_budget(config, contextWindow, reservedForConversation)
Estimate how much of an LLM context window your MCP servers consume, and which tool definitions to cut first. Paste your MCP config. Returns per-server token cost, remaining budget, and ranked reduction advice.
输入模式
{
"type": "object",
"properties": {
"config": {
"type": [
"string",
"array",
"object"
],
"description": "Your MCP config as JSON. Either {\"mcpServers\":{...}} or a raw {name:{...}} map. Each server may declare \"tools\":[{name,description,inputSchema}]. Accepts a JSON object, or a JSON string containing one."
},
"contextWindow": {
"type": "number",
"description": "Model context window in tokens (default 200000)"
},
"reservedForConversation": {
"type": "number",
"description": "Tokens you want to keep for the actual conversation (default 40000)"
}
},
"required": [
"config"
]
}⚪compress_tool_definitions(definitions)
Shrink MCP tool descriptions and JSON schemas to cut context cost without changing how agents call them. Returns the compressed definitions plus exact token savings.
输入模式
{
"type": "object",
"properties": {
"definitions": {
"type": [
"string",
"array",
"object"
],
"description": "JSON array of tool definitions to compress. Each item: {name, description, inputSchema}. Accepts a JSON array, or a JSON string containing one."
}
},
"required": [
"definitions"
]
}⚪score_mcp_server_trust(serverName, stars, daysSinceLastCommit, repoExists, npmDeprecated, ...)
Score an MCP server A–F on trustworthiness and maintenance health, so you can choose between four servers that all claim to do the same thing. Supply what you know about the server.
输入模式
{
"type": "object",
"properties": {
"serverName": {
"type": "string",
"description": "Server name (for the report)"
},
"stars": {
"type": "number",
"description": "GitHub stars"
},
"daysSinceLastCommit": {
"type": "number",
"description": "Days since the last commit"
},
"repoExists": {
"type": "boolean",
"description": "Is the declared GitHub repo still reachable?"
},
"npmDeprecated": {
"type": "boolean",
"description": "Is the npm/PyPI package marked deprecated?"
},
"hasInstallConfig": {
"type": "boolean",
"description": "Does it ship a working install config for Claude Desktop / Cursor / VS Code?"
},
"hasToolDocs": {
"type": "boolean",
"description": "Does the README document the exposed tools and required credentials?"
},
"inOfficialRegistry": {
"type": "boolean",
"description": "Is it listed in the official MCP registry?"
}
},
"required": []
}⚪audit_mcp_server_security(serverName, hasAuthentication, usesStdioTransport, performsFileOperations, executesCommands, ...)
Audit an MCP server against the OWASP MCP Top 10. Reports authentication, path traversal, command injection, secret exposure and supply-chain risk with a concrete remediation list.
输入模式
{
"type": "object",
"properties": {
"serverName": {
"type": "string",
"description": "Server name (for the report)"
},
"hasAuthentication": {
"type": "boolean",
"description": "Does the server enforce authentication on every request?"
},
"usesStdioTransport": {
"type": "boolean",
"description": "Does it run over local STDIO transport?"
},
"performsFileOperations": {
"type": "boolean",
"description": "Does it read/write files based on model-supplied paths?"
},
"executesCommands": {
"type": "boolean",
"description": "Does it execute shell commands or spawn processes?"
},
"hasHardcodedSecrets": {
"type": "boolean",
"description": "Are credentials hardcoded in the source or config?"
},
"acceptsUserInputInCommands": {
"type": "boolean",
"description": "Is untrusted input interpolated into commands or queries?"
},
"hasProvenanceAttestation": {
"type": "boolean",
"description": "Is the package published with build provenance / trusted publishing?"
},
"restrictsNetworkEgress": {
"type": "boolean",
"description": "Are outbound network destinations restricted?"
}
},
"required": []
}⚪generate_mcp_server_card(name, description, version, endpointUrl, transport, ...)
Generate a SEP-1649 MCP Server Card (/.well-known/mcp/server-card.json) so crawlers and registries can discover your server without connecting to it.
输入模式
{
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "Server name"
},
"description": {
"type": "string",
"description": "What the server does"
},
"version": {
"type": "string",
"description": "Server version (semver)"
},
"endpointUrl": {
"type": "string",
"description": "Public Streamable HTTP endpoint URL"
},
"transport": {
"type": "string",
"description": "Transport: streamable-http or sse (default streamable-http)"
},
"tools": {
"type": [
"string",
"array",
"object"
],
"description": "Optional JSON array of {name, description} for the capability summary. Accepts a JSON array, or a JSON string containing one."
},
"requiresAuth": {
"type": "boolean",
"description": "Does the server require authentication?"
}
},
"required": [
"name",
"description"
]
}🟡validate_mcp_server_card(card)
Validate an MCP Server Card against SEP-1649 and report every missing or malformed field before you publish it. Checks structure (serverInfo, transport, capabilities, authentication) and format (semver version, http(s) transport URL, capabilities.tools entries), returning a full error and warning list.
输入模式
{
"type": "object",
"properties": {
"card": {
"type": [
"string",
"array",
"object"
],
"description": "The server-card.json content to validate. Accepts a JSON object, or a JSON string containing one."
}
},
"required": [
"card"
]
}🔴advise_tool_portfolio(tools, targetToolCount)
Too many MCP tools makes agents pick the wrong one. Given your tool list and usage, get keep / merge / remove recommendations to get under the 10–15 tool guideline.
输入模式
{
"type": "object",
"properties": {
"tools": {
"type": [
"string",
"array",
"object"
],
"description": "JSON array of {name, category?, callsPerDay?, description?}. Accepts a JSON array, or a JSON string containing one."
},
"targetToolCount": {
"type": "number",
"description": "Target number of tools to keep (default 12)"
}
},
"required": [
"tools"
]
}⚪plan_mcp_token_budget(workloads, inputPricePerMillion, outputPricePerMillion, monthlyBudget)
Plan and attribute MCP token spend across agents, servers and workflows — something the protocol provides no native support for. Outputs per-dimension cost split and a quota plan.
输入模式
{
"type": "object",
"properties": {
"workloads": {
"type": [
"string",
"array",
"object"
],
"description": "JSON array of {name, callsPerDay, inputTokensPerCall, outputTokensPerCall, owner?}. Accepts a JSON array, or a JSON string containing one."
},
"inputPricePerMillion": {
"type": "number",
"description": "Input price per 1M tokens in USD (default 3)"
},
"outputPricePerMillion": {
"type": "number",
"description": "Output price per 1M tokens in USD (default 15)"
},
"monthlyBudget": {
"type": "number",
"description": "Optional monthly budget cap in USD for over/under comparison"
}
},
"required": [
"workloads"
]
}⚪generate_mcp_client_config(serverName, command, args, url, env)
Generate ready-to-paste MCP server config for Claude Desktop, Cursor, VS Code and Windsurf from one input. Config completeness decides whether developers can install your server at all.
输入模式
{
"type": "object",
"properties": {
"serverName": {
"type": "string",
"description": "Server name used as the config key"
},
"command": {
"type": "string",
"description": "Launch command for stdio servers (e.g. npx)"
},
"args": {
"type": [
"string",
"array",
"object"
],
"description": "JSON array of command arguments. Accepts a JSON array, or a JSON string containing one."
},
"url": {
"type": "string",
"description": "Endpoint URL for remote/streamable-http servers"
},
"env": {
"type": [
"string",
"array",
"object"
],
"description": "JSON object of environment variables. Accepts a JSON object, or a JSON string containing one."
}
},
"required": [
"serverName"
]
}🟢find_tool(query, limit)
Semantic tool router. Given a natural-language intent, return only the most relevant tools from this server so the client can inject 3 schemas instead of 27. This is the "find_tool" meta-tool the MCP optimisation literature calls for.
输入模式
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Natural-language description of what you want to accomplish"
},
"limit": {
"type": "number",
"description": "Maximum number of tools to return (default 3)"
}
},
"required": [
"query"
]
}🟢calculate_github_actions_cost(linuxMinutes, windowsMinutes, macosMinutes, plan, publicRepo)
Estimate a GitHub Actions monthly bill using the January 2026 runner rates (Linux $0.006/min, Windows $0.010, macOS $0.062), accounting for plan allowances. Also reports what the same workload cost before the price cut.
输入模式
{
"type": "object",
"properties": {
"linuxMinutes": {
"type": "number",
"description": "Linux runner minutes per month"
},
"windowsMinutes": {
"type": "number",
"description": "Windows runner minutes per month"
},
"macosMinutes": {
"type": "number",
"description": "macOS runner minutes per month"
},
"plan": {
"type": "string",
"description": "GitHub plan: free, pro, team or enterprise (default free)"
},
"publicRepo": {
"type": "boolean",
"description": "Are these workflows in public repositories? (unlimited free)"
}
},
"required": [],
"anyOf": [
{
"required": [
"linuxMinutes"
]
},
{
"required": [
"windowsMinutes"
]
},
{
"required": [
"macosMinutes"
]
}
]
}⚪compare_automation_platform_costs(runsPerMonth, stepsPerRun, workflowCount)
Compare real monthly cost on Zapier (per task) versus Make (per operation) for the same workflow volume, including the counting-model difference that makes the two quotes non-obvious.
输入模式
{
"type": "object",
"properties": {
"runsPerMonth": {
"type": "number",
"description": "Workflow executions per month"
},
"stepsPerRun": {
"type": "number",
"description": "Total steps (trigger + actions) per run"
},
"workflowCount": {
"type": "number",
"description": "Number of distinct workflows (default 1)"
}
},
"required": [
"runsPerMonth",
"stepsPerRun"
]
}🟢detect_polling_cost_traps(workflows, platform)
Find the most common hidden cost in no-code automation: using polling where a webhook would do. Quantifies the wasted task/operation quota and the monthly dollars.
输入模式
{
"type": "object",
"properties": {
"workflows": {
"type": [
"string",
"array",
"object"
],
"description": "JSON array of {name, triggerType: \"polling\"|\"webhook\", intervalMinutes, runsPerMonth, stepsPerRun, hasBranching?}. Accepts a JSON array, or a JSON string containing one."
},
"platform": {
"type": "string",
"description": "zapier or make (default zapier)"
}
},
"required": [
"workflows"
]
}⚪estimate_selfhosted_tco(monthlyMinutes, runnerType, maintenanceHoursPerMonth, engineerHourlyCost, runnerHostingCostPerMonth)
Compare paying hosted CI overage against running self-hosted runners, including the maintenance hours people forget to cost. Reports the true break-even volume.
输入模式
{
"type": "object",
"properties": {
"monthlyMinutes": {
"type": "number",
"description": "Current hosted runner minutes per month"
},
"runnerType": {
"type": "string",
"description": "linux, windows or macos (default linux)"
},
"maintenanceHoursPerMonth": {
"type": "number",
"description": "Hours per month spent maintaining self-hosted runners (default 4)"
},
"engineerHourlyCost": {
"type": "number",
"description": "Fully-loaded engineer cost per hour in USD (default 75)"
},
"runnerHostingCostPerMonth": {
"type": "number",
"description": "Monthly infra cost for the self-hosted runner(s) in USD (default 20)"
}
},
"required": [
"monthlyMinutes"
]
}⚪compare_ai_coding_tool_costs(seats, usageLevel, includeApiBaseline, apiModel)
Compare monthly and annual cost of AI coding subscriptions (GitHub Copilot, Cursor, Claude Code/Pro/Max, OpenAI Codex) for a given team size and usage intensity, then compare the winner against pay-as-you-go API pricing for the same workload. Prices verified 2026-09.
输入模式
{
"type": "object",
"properties": {
"seats": {
"type": "number",
"description": "Number of developer seats (default 1)"
},
"usageLevel": {
"type": "string",
"description": "Usage intensity: light, standard, heavy or extreme (default standard)"
},
"includeApiBaseline": {
"type": "boolean",
"description": "Also compute the pay-as-you-go API cost for the same workload (default true)"
},
"apiModel": {
"type": "string",
"description": "Model id for the API baseline (default claude-4-sonnet)"
}
},
"required": []
}⚪compare_llm_api_costs(inputTokensPerCall, outputTokensPerCall, callsPerMonth, topN, provider, ...)
Rank 18 LLM models by the real monthly cost of a given workload (input/output tokens per call × calls per month). Reports the cheapest and most expensive option, the cost spread, and which models can actually hold your prompt in their context window.
输入模式
{
"type": "object",
"properties": {
"inputTokensPerCall": {
"type": "number",
"description": "Average input (prompt) tokens per call"
},
"outputTokensPerCall": {
"type": "number",
"description": "Average output (completion) tokens per call"
},
"callsPerMonth": {
"type": "number",
"description": "Number of API calls per month"
},
"topN": {
"type": "number",
"description": "How many models to return, cheapest first (default 8)"
},
"provider": {
"type": "string",
"description": "Filter to one provider: openai, anthropic, google, deepseek or meta"
},
"minContextWindow": {
"type": "number",
"description": "Only include models whose context window is at least this many tokens"
}
},
"required": [
"callsPerMonth"
]
}🟡plan_context_window_budget(servers, avgTokensPerTool, reserveForOutput, conversationShare)
Given a set of MCP servers and their tool counts, show for every model context window (128K, 200K, 1M, 10M) how much of the window the tool definitions consume, how much is left for conversation, and whether the server set fits at all. Answers "how many servers can I attach on model X?".
输入模式
{
"type": "object",
"properties": {
"servers": {
"type": [
"string",
"array",
"object"
],
"description": "JSON array of {name, toolCount, avgTokensPerTool?} — e.g. [{\"name\":\"github\",\"toolCount\":35}]. Accepts a JSON array, or a JSON string containing one."
},
"avgTokensPerTool": {
"type": "number",
"description": "Default tokens per tool definition when a server omits it (default 550)"
},
"reserveForOutput": {
"type": "number",
"description": "Tokens to reserve for the model response (default 8000)"
},
"conversationShare": {
"type": "number",
"description": "Fraction of the window you want left for human/agent conversation, 0-1 (default 0.25)"
}
},
"required": [
"servers"
]
}社区
证据