Run a regular expression against text. Returns up to 100 matches with index and capture groups. Pattern ≤ 200 chars, text ≤ 10KB.

Flesch Reading Ease score and Flesch–Kincaid grade level for English text, plus word/sentence/syllable counts.

Caesar-cipher a string. Default shift 13 (ROT13, self-inverse). Set shift for any rotation 1-25.

Compute Flesch-Kincaid Grade Level, Flesch Reading Ease, Gunning Fog Index, and Automated Readability Index from text. Returns all 4 scores plus word, sentence, and syllable counts.

Search operations in an OpenAPI 3.x or Swagger 2.x spec against a free-text query. Tokenizes the query (lowercase, alphanumeric runs), scores each operation by which fields the tokens match - operationId +3, path +3, tags +2, summary +2, description +1 per matched token - and returns ranked results with a `matches` array naming the contributing fields. Sort: score descending, then path ascending for stability. Limit defaults to 10 (max 100).

Fetch a site's robots.txt and answer: may this user-agent crawl this path? Returns the matched rule and all declared sitemaps.

Open interest for one perpetual in coins and USD notional with its share of the venue total, or the top N contracts ranked by open interest plus the venue total. Use it when an agent needs positioning size for a market or a leaderboard of where leverage is concentrated right now.

Descriptive statistics for an array of numbers: count, sum, mean, median, mode, min, max, range, variance, stddev, and percentiles.

Sort the lines of a text. order: asc (default) | desc | numeric. unique:true removes duplicates; ci:true is case-insensitive.

Compute the full descriptive-stats panel for an array of numbers in one call: count, sum, mean, median, mode, stddev (sample), variance, min, max, range, q1, q3, IQR. Beats calling 12 separate tools when you already have the array in front of you.

Split text into overlapping chunks for RAG ingestion - by characters (default) or by exact LLM tokens. Returns the chunks plus offsets. Deterministic, no model needed.

Compute the relative strength index (Wilder's smoothing, default period 14) over a price series you supply, such as daily closes. Returns one value per input position (null until the first full period), the latest value, and a reading: overbought at 70 or above, oversold at 30 or below, else neutral. No market data is fetched: pass your own closes.

Verify an Ed25519 execution certificate against the exact SQL statement you are about to run - the gate your database layer calls before it obeys an agent. Checks the signature, the certificate version, the expiry, and that the statement's SHA-256 matches the one certified, so a certificate for a different (or edited) statement is rejected. Returns { valid, reason, payload } and never throws on a malformed token, so the executor always gets one uniform answer.

Parse a semantic version, or compare two (a vs b → -1/0/1, with greater/lesser flags).

Risk-adjusted return: (mean return - risk-free rate) / sample standard deviation of returns (n-1). Pass periodsPerYear to also get the annualized ratio (× sqrt(periodsPerYear)).

Counts for any text in one call: characters (Unicode code points), words, sentences, paragraphs, avgWordLength, readingTimeMinutes (200 words a minute) and estimatedTokens, a rough LLM token estimate (about 4 characters a token, one per Chinese or Japanese character). Chinese and Japanese text, which has no spaces, is counted a character per word, and 。！？ end sentences.

Resolve an ERC-20 contract address to its on-chain metadata: symbol, decimals, name, and logo URL where available. Use this to humanize a raw contract address before showing it to a user or before computing fiat values.

Return the current USD spot price for an ERC-20 token, identified by its contract address and network. Sourced from an aggregated market price feed. Use this for portfolio-value calculations or to denominate a balance in fiat without depending on a separate market-data API.

Current time: UTC ISO, epoch seconds/ms, day of week/year, ISO week - optionally rendered in any IANA timezone.

Verify a webhook's HMAC signature against the correct per-provider scheme: GitHub (X-Hub-Signature-256, sha256=hex), Stripe (Stripe-Signature t/v1 over "<t>.<body>" with replay tolerance), Shopify (X-Shopify-Hmac-Sha256, base64), Slack (X-Slack-Signature, v0:<ts>:<body> with replay tolerance). Constant-time comparison; the secret is never echoed. Pass the RAW request body string - signatures are over the raw bytes. Deterministic.