com.pnltoolkit/calculators

What it mainly works on, as our AI model read its tool descriptions: nothing outside itself: it only answers questions.

None of its 8 tools are described as changing anything.

• historical_returnreads or searches

  “Historical investment return using installed monthly closes, not live quotes.”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

  9 inputs

  • assetstring“Asset ticker.”
  • startstring“Start month, YYYY-MM.”
  • endstring“End month, YYYY-MM.”
  • amountnumber“Dollar budget including fees, or coin/share quantity when unit is coins.”
  • unitstring“cash for a dollar budget; coins for a coin or share quantity.”
  • returnBasisstring“total reinvests distributions; price excludes distributions.”
  • buyFeenumber“Buying fee as a percentage, e.g.”
  • benchmarkstring“Optional benchmark asset.”
  • include_imageboolean“Also inline a PNG no wider than 1000 pixels.”
• dca_backtestreads or searches

  “Dollar-cost-averaging backtest using installed monthly closes, not live quotes.”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

  10 inputs

  • assetstring“Asset ticker.”
  • startstring“Start month, YYYY-MM.”
  • endstring“End month, YYYY-MM.”
  • monthlynumber“Contribution in dollars per chosen frequency (DCA), or per month (compound interest).”
  • initialnumber“Initial deposit in dollars.”
  • frequencynumber“Contribution interval in months: 1, 3 or 12.”
  • buyFeenumber“Buying fee as a percentage, e.g.”
  • returnBasisstring“total reinvests distributions; price excludes distributions.”
  • benchmarkstring“Optional benchmark asset.”
  • include_imageboolean“Also inline a PNG no wider than 1000 pixels.”
• compound_intereston 10 other serversreads or searches

  “Compound interest in USD: initial dollars, monthly dollars, annual return/fees/inflation in percent, and whole years.”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

  9 inputs

  • principalnumber“Initial investment, or peak account balance for recovery, in dollars.”
  • monthlynumber“Contribution in dollars per chosen frequency (DCA), or per month (compound interest).”
  • ratenumber“Assumed gross annual percentage return.”
  • yearsinteger“Number of years, 1 to 40.”
  • timingstring“Deposit at the beginning or end of each month.”
  • annualFeenumber“Annual asset fee in percent.”
  • inflationnumber“Assumed annual inflation in percent.”
  • contributionGrowthnumber“Annual increase in contributions, in percent.”
  • include_imageboolean“Also inline a PNG no wider than 1000 pixels.”
• position_sizeon 6 other serversreads or searches

  “Position sizing for linear USD shares/coins: prices in USD, account risk in percent, fees/slippage in basis points, quantity increment in units.”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

  11 inputs

  • balancenumber“Account balance in dollars.”
  • risknumber“Loss budget as a percentage of the account.”
  • entrynumber“Trade entry price.”
  • stopnumber“Stop price.”
  • targetnumber“Trade target price, or target inventory percentage for inventory quotes.”
  • directionstring“long or short.”
  • feenumber“Fee per fill in basis points; negative maker fees are rebates in the spread model.”
  • slippagenumber“Slippage per side in basis points.”
  • unitStepnumber“Quantity increment; 0 disables rounding.”
  • maxLeveragenumber“Maximum notional exposure divided by equity.”
  • include_imageboolean“Also inline a PNG no wider than 1000 pixels.”
• trade_expectancyreads or searches

  “Trade expectancy and fractional Kelly: balance in USD, win rate/buffer/cap in percent, wins/losses/cost in R, fraction 0–1.”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

  9 inputs

  • balancenumber“Account balance in dollars.”
  • winRatenumber“Estimated win rate in percent.”
  • avgWinnumber“Average winning trade in R units.”
  • avgLossnumber“Average losing trade in R units.”
  • costnumber“Cost per trade in R units.”
  • fractionnumber“Kelly multiplier, e.g.”
  • winBuffernumber“Conservative reduction in win rate, in percentage points.”
  • riskCapnumber“Maximum account risk in percent.”
  • include_imageboolean“Also inline a PNG no wider than 1000 pixels.”
• drawdown_recoveryreads or searches

  “Drawdown recovery: balances/deposits in USD, drawdown and monthly return in percent, target horizon in whole months.”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

  10 inputs

  • principalnumber“Initial investment, or peak account balance for recovery, in dollars.”
  • scenariostring“drawdown, balance or streak.”
  • lossnumber“Drawdown in percent, from 0 to 100.”
  • currentnumber“Current base inventory percentage, or current balance in dollars in recovery.”
  • riskPerTradenumber“Loss per trade as a percentage of remaining equity.”
  • lossesinteger“Number of consecutive losing trades.”
  • monthlyReturnnumber“Assumed net monthly return in percent; not a forecast.”
  • monthlyDepositnumber“New monthly deposit in dollars.”
  • targetMonthsinteger“Recovery target horizon in months.”
  • include_imageboolean“Also inline a PNG no wider than 1000 pixels.”
• spread_and_feesreads or searches

  “Round-trip spread economics: one-side notional in USD; full spread, fee per fill and adverse cost in basis points (1 bp = 0.01%).”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

  5 inputs

  • notionalnumber“One-side trade notional in dollars.”
  • spreadnumber“Full quoted spread in basis points.”
  • feenumber“Fee per fill in basis points; negative maker fees are rebates in the spread model.”
  • adversenumber“Adverse-selection cost in basis points.”
  • include_imageboolean“Also inline a PNG no wider than 1000 pixels.”
• inventory_quotesreads or searches

  “Inventory quotes: mid and tick in USD, inventory weights in percent, spread/skew/cap in basis points.”

  Publisher declares: read-only yes · destructive no · idempotent yes · open-world no

  8 inputs

  • midnumber“Market mid price.”
  • currentnumber“Current base inventory percentage, or current balance in dollars in recovery.”
  • targetnumber“Trade target price, or target inventory percentage for inventory quotes.”
  • spreadnumber“Full quoted spread in basis points.”
  • skewnumber“Quote shift in basis points per 10 percentage points of inventory deviation.”
  • tickSizenumber“Price tick size; 0 disables rounding.”
  • skewCapnumber“Maximum quote-center shift in basis points.”
  • include_imageboolean“Also inline a PNG no wider than 1000 pixels.”

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-23.

The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.