ai.cleartape/clear-tape

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

None of its 11 tools are described as changing anything.

• calculate_position_sizeon 3 other serverscalculates or converts

  “Position size from the stop: how many shares to buy (or short) so that a stop-out loses a set percentage of the account.”

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

  5 inputs, 4 required

  • accountnumberrequired“Account size in USD.”
  • riskPctnumberrequired“Risk per trade, percent of the account (1 = 1%).”
  • entrynumberrequired“Entry price per share in USD.”
  • stopnumberrequired“Stop price per share in USD.”
  • langstring“Language of the returned text: "en" (default) or "zh" (Simplified Chinese).”
• calculate_risk_rewardcalculates or converts

  “Risk/reward ratio of a planned trade, the win rate it needs to break even, and (optionally) an exit expressed as an R multiple.”

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

  5 inputs, 3 required

  • entrynumberrequired“Entry price per share in USD.”
  • stopnumberrequired“Stop price per share in USD; not equal to the entry.”
  • targetnumberrequired“Target price per share in USD, on the other side of the entry from the stop.”
  • exitnumber“Optional: an actual or planned exit price in USD, returned as an R multiple.”
  • langstring“Language of the returned text: "en" (default) or "zh" (Simplified Chinese).”
• calculate_expectancycalculates or converts

  “Expectancy per trade, per 100 trades, payoff ratio, break-even win rate and profit factor from a win rate and average win and loss.”

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

  4 inputs, 3 required

  • winRatenumberrequired“Win rate in percent (40 = 40%).”
  • avgWinnumberrequired“Average winning trade as a positive amount, in USD or in R.”
  • avgLossnumberrequired“Average losing trade as a positive amount, in the same unit as avgWin.”
  • langstring“Language of the returned text: "en" (default) or "zh" (Simplified Chinese).”
• calculate_atr_stopcalculates or converts

  “A volatility (ATR) stop: entry minus (long) or plus (short) a multiple of the average true range.”

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

  6 inputs, 2 required

  • entrynumberrequired“Entry price per share in USD.”
  • atrnumber“Average true range in USD (e.g.”
  • rangesarray“Alternative to atr: 5 to 500 recent daily ranges (high minus low) in USD; their average stands in for the ATR.”
  • multiplenumberrequired“ATR multiple for the stop distance, commonly 1.5 to 3.”
  • sidestring“Trade direction: "long" (default) or "short".”
  • langstring“Language of the returned text: "en" (default) or "zh" (Simplified Chinese).”
• calculate_drawdown_recoverycalculates or converts

  “The gain needed to recover from a drawdown and, optionally, how many losing trades in a row at a fixed risk per trade cause it.”

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

  3 inputs, 1 required

  • lossnumberrequired“Drawdown in percent of the account (20 = 20%).”
  • riskPctnumber“Optional: risk per trade in percent of the account.”
  • langstring“Language of the returned text: "en" (default) or "zh" (Simplified Chinese).”
• calculate_kelly_criterioncalculates or converts

  “Full and fractional Kelly risk per trade from a win rate and payoff ratio, with the edge per 1R and the break-even win rate.”

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

  4 inputs, 3 required

  • winRatenumberrequired“Win rate in percent.”
  • payoffnumberrequired“Payoff ratio: average win divided by average loss (2 = winners twice the size of losers).”
  • fractionnumberrequired“Share of full Kelly to use, in percent: 25 = quarter Kelly, 50 = half, 100 = full.”
  • langstring“Language of the returned text: "en" (default) or "zh" (Simplified Chinese).”
• calculate_trading_coston 1 other servercalculates or converts

  “The cost of one round trip (commissions, bid-ask spread, slippage) in USD, in R, as a share of the target move and of the position, and over a year of trades.”

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

  9 inputs, 6 required

  • entrynumberrequired“Entry price per share in USD.”
  • stopnumberrequired“Stop price per share in USD; not equal to the entry.”
  • targetnumber“Optional: target price per share in USD, on the other side of the entry from the stop.”
  • sharesnumberrequired“Number of shares.”
  • commissionnumberrequired“Commission per order (each side) in USD; 0 if none.”
  • spreadnumberrequired“Bid-ask spread per share in USD (paid once per round trip, half on each side).”
  • slippagenumberrequired“Slippage per share per side in USD.”
  • tradesnumber“Optional: round trips per year, for the annual cost.”
  • langstring“Language of the returned text: "en" (default) or "zh" (Simplified Chinese).”
• calculate_losing_streakcalculates or converts

  “The exact probability of at least one losing streak of a given length over a number of independent trades, the expected longest streak and the streak 95% of sequences stay within.”

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

  4 inputs, 3 required

  • winRatenumberrequired“Win rate in percent.”
  • tradesintegerrequired“Number of trades, a whole number from 1 to 2000.”
  • streakintegerrequired“Losing streak length to test, a whole number no larger than trades.”
  • langstring“Language of the returned text: "en" (default) or "zh" (Simplified Chinese).”
• get_trading_system_rulesreads or searches

  “Without id: lists Clear Tape's eleven preset trading systems (trend, breakout, momentum and volume) with their style, holding period and one-line entry, stop and exit.”

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

  2 inputs

  • idstring“The system to describe; leave out to list them all.”
  • langstring“Language of the returned text: "en" (default) or "zh" (Simplified Chinese).”
• lookup_glossary_termreads or searches

  “Looks up a trading term in Clear Tape's bilingual (English and Simplified Chinese) glossary of about 70 terms, such as "R multiple", "ATR", "drawdown" or "止损".”

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

  2 inputs, 1 required

  • termstringrequired“The term to look up, in English or Chinese.”
  • langstring“Language of the returned text: "en" (default) or "zh" (Simplified Chinese).”
• search_learningreads or searches

  “Searches Clear Tape's free trading education by keyword: the Learn articles, the Academy lessons, the trading-strategy pages and the calculators, in English or Chinese.”

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

  3 inputs, 1 required

  • querystringrequired“Keywords, e.g.”
  • limitinteger“Most results to return (1 to 20, default 8).”
  • langstring“Language of the returned text: "en" (default) or "zh" (Simplified Chinese).”

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.