business_days

Works with business (working) days. mode "add": returns the date N business days after start_date (start_date itself is not counted; negative N goes backward; 0 returns start_date, or the next business day if start_date is not one). mode "count": counts business days from start_date to end_date, including both ends. Weekends default to Saturday and Sunday. Public holidays are NOT built in — pass them in "holidays".

read-only

Argument	Type	Description
days	integer	Business days to add (mode "add")
mode*	string	"add" or "count"
weekend	array	Weekend days as ISO weekday numbers (1=Monday ... 7=Sunday). Default [6, 7]. Example for Friday-Saturday weekends: [5, 6]
end_date	string	YYYY-MM-DD (mode "count")
holidays	array	Dates (YYYY-MM-DD) to treat as non-working days
start_date*	string	YYYY-MM-DD

Input schema (JSON)

{
  "type": "object",
  "required": [
    "mode",
    "start_date"
  ],
  "properties": {
    "days": {
      "type": "integer",
      "maximum": 10000,
      "minimum": -10000,
      "description": "Business days to add (mode \"add\")"
    },
    "mode": {
      "enum": [
        "add",
        "count"
      ],
      "type": "string",
      "description": "\"add\" or \"count\""
    },
    "weekend": {
      "type": "array",
      "items": {
        "type": "integer",
        "maximum": 7,
        "minimum": 1
      },
      "maxItems": 6,
      "description": "Weekend days as ISO weekday numbers (1=Monday ... 7=Sunday). Default [6, 7]. Example for Friday-Saturday weekends: [5, 6]"
    },
    "end_date": {
      "type": "string",
      "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
      "description": "YYYY-MM-DD (mode \"count\")"
    },
    "holidays": {
      "type": "array",
      "items": {
        "type": "string",
        "pattern": "^\\d{4}-\\d{2}-\\d{2}$"
      },
      "maxItems": 1000,
      "description": "Dates (YYYY-MM-DD) to treat as non-working days"
    },
    "start_date": {
      "type": "string",
      "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
      "description": "YYYY-MM-DD"
    }
  },
  "additionalProperties": false
}

calculate

Evaluates an arithmetic expression exactly, so you don't have to do mental math. Supports + - * / % ^ (or **), parentheses, constants pi/e/tau and functions: sqrt, cbrt, abs, round(x, digits), floor, ceil, trunc, sign, ln, log(x[, base]), log10, log2, exp, pow, sin, cos, tan, asin, acos, atan, atan2, min, max, hypot, factorial. Trig uses radians. Example: "(1250 * 1.08^5) - 1250".

read-only

Argument	Type	Description
decimals	integer	Optional: round the result to this many decimal places
expression*	string	The expression to evaluate

Input schema (JSON)

{
  "type": "object",
  "required": [
    "expression"
  ],
  "properties": {
    "decimals": {
      "type": "integer",
      "maximum": 15,
      "minimum": 0,
      "description": "Optional: round the result to this many decimal places"
    },
    "expression": {
      "type": "string",
      "maxLength": 2000,
      "minLength": 1,
      "description": "The expression to evaluate"
    }
  },
  "additionalProperties": false
}

convert_timezone

Converts a date/time from one time zone to another, correctly handling daylight saving time. If the input already includes an offset or 'Z', from_timezone is ignored.

read-only

Argument	Type	Description
datetime*	string	Date/time in ISO 8601 (e.g. "2026-03-08T14:30", "2026-03-08T14:30:00Z", "2026-03-08"), "YYYY-MM-DD HH:mm", a Unix timestamp in seconds or milliseconds, or "now".
to_timezone*	string	IANA time zone name, e.g. "America/New_York", "Europe/London", "Asia/Tokyo", or "UTC". Fixed offsets like "UTC+5:30" also work.
from_timezone	string	IANA time zone name, e.g. "America/New_York", "Europe/London", "Asia/Tokyo", or "UTC". Fixed offsets like "UTC+5:30" also work. Defaults to UTC.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "datetime",
    "to_timezone"
  ],
  "properties": {
    "datetime": {
      "type": "string",
      "maxLength": 64,
      "description": "Date/time in ISO 8601 (e.g. \"2026-03-08T14:30\", \"2026-03-08T14:30:00Z\", \"2026-03-08\"), \"YYYY-MM-DD HH:mm\", a Unix timestamp in seconds or milliseconds, or \"now\"."
    },
    "to_timezone": {
      "type": "string",
      "maxLength": 64,
      "description": "IANA time zone name, e.g. \"America/New_York\", \"Europe/London\", \"Asia/Tokyo\", or \"UTC\". Fixed offsets like \"UTC+5:30\" also work."
    },
    "from_timezone": {
      "type": "string",
      "maxLength": 64,
      "description": "IANA time zone name, e.g. \"America/New_York\", \"Europe/London\", \"Asia/Tokyo\", or \"UTC\". Fixed offsets like \"UTC+5:30\" also work. Defaults to UTC."
    }
  },
  "additionalProperties": false
}

convert_units

Converts a value between units of length, mass, volume (US and imperial), area, speed, time, digital data (KB vs KiB, bits vs bytes), energy, pressure and temperature. Accepts common abbreviations (km, lb, fl oz, mph, °F, GiB). US customary units are used for cup/pint/quart/gallon unless you say imperial.

read-only

Argument	Type	Description
to*	string	Unit to convert to, e.g. "km", "kg", "celsius", "GiB"
from*	string	Unit to convert from, e.g. "mi", "pound", "°F", "GB"
value*	number	The number to convert

Input schema (JSON)

{
  "type": "object",
  "required": [
    "value",
    "from",
    "to"
  ],
  "properties": {
    "to": {
      "type": "string",
      "maxLength": 40,
      "description": "Unit to convert to, e.g. \"km\", \"kg\", \"celsius\", \"GiB\""
    },
    "from": {
      "type": "string",
      "maxLength": 40,
      "description": "Unit to convert from, e.g. \"mi\", \"pound\", \"°F\", \"GB\""
    },
    "value": {
      "type": "number",
      "description": "The number to convert"
    }
  },
  "additionalProperties": false
}

current_time

Returns the exact current date, time, weekday and UTC offset in any time zone. Use this whenever you need to know today's date or the current time instead of guessing — your training data does not know what day it is.

read-only

Argument	Type	Description
timezone	string	IANA time zone name, e.g. "America/New_York", "Europe/London", "Asia/Tokyo", or "UTC". Fixed offsets like "UTC+5:30" also work.

Input schema (JSON)

{
  "type": "object",
  "properties": {
    "timezone": {
      "type": "string",
      "default": "UTC",
      "maxLength": 64,
      "description": "IANA time zone name, e.g. \"America/New_York\", \"Europe/London\", \"Asia/Tokyo\", or \"UTC\". Fixed offsets like \"UTC+5:30\" also work."
    }
  },
  "additionalProperties": false
}

date_add

Adds or subtracts a duration (years, months, weeks, days, hours, minutes, seconds) to a date/time. Use negative numbers to subtract. Calendar-aware: adding 1 month to Jan 31 gives Feb 28/29, and adding days keeps the same local clock time across daylight-saving changes.

read-only

Argument	Type	Description
days	number	days to add (negative to subtract)
hours	number	hours to add (negative to subtract)
weeks	number	weeks to add (negative to subtract)
years	number	years to add (negative to subtract)
months	number	months to add (negative to subtract)
minutes	number	minutes to add (negative to subtract)
seconds	number	seconds to add (negative to subtract)
datetime*	string	Date/time in ISO 8601 (e.g. "2026-03-08T14:30", "2026-03-08T14:30:00Z", "2026-03-08"), "YYYY-MM-DD HH:mm", a Unix timestamp in seconds or milliseconds, or "now".

date_diff

Calculates the exact time between two dates/times: a calendar breakdown (years, months, days, hours, minutes, seconds) plus totals in days, hours, minutes and seconds, and the number of calendar days. Negative if end is before start.

read-only

Argument	Type	Description
end*	string	Date/time in ISO 8601 (e.g. "2026-03-08T14:30", "2026-03-08T14:30:00Z", "2026-03-08"), "YYYY-MM-DD HH:mm", a Unix timestamp in seconds or milliseconds, or "now".
start*	string	Date/time in ISO 8601 (e.g. "2026-03-08T14:30", "2026-03-08T14:30:00Z", "2026-03-08"), "YYYY-MM-DD HH:mm", a Unix timestamp in seconds or milliseconds, or "now".
timezone	string	Time zone for inputs without an offset. IANA time zone name, e.g. "America/New_York", "Europe/London", "Asia/Tokyo", or "UTC". Fixed offsets like "UTC+5:30" also work. Defaults to UTC.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "start",
    "end"
  ],
  "properties": {
    "end": {
      "type": "string",
      "maxLength": 64,
      "description": "Date/time in ISO 8601 (e.g. \"2026-03-08T14:30\", \"2026-03-08T14:30:00Z\", \"2026-03-08\"), \"YYYY-MM-DD HH:mm\", a Unix timestamp in seconds or milliseconds, or \"now\"."
    },
    "start": {
      "type": "string",
      "maxLength": 64,
      "description": "Date/time in ISO 8601 (e.g. \"2026-03-08T14:30\", \"2026-03-08T14:30:00Z\", \"2026-03-08\"), \"YYYY-MM-DD HH:mm\", a Unix timestamp in seconds or milliseconds, or \"now\"."
    },
    "timezone": {
      "type": "string",
      "maxLength": 64,
      "description": "Time zone for inputs without an offset. IANA time zone name, e.g. \"America/New_York\", \"Europe/London\", \"Asia/Tokyo\", or \"UTC\". Fixed offsets like \"UTC+5:30\" also work. Defaults to UTC."
    }
  },
  "additionalProperties": false
}

hash_text

Computes a cryptographic hash (SHA-1, SHA-256, SHA-384, SHA-512) of text, or encodes/decodes it as Base64, Base64URL, hex or URL-encoding. Text is treated as UTF-8.

read-only

Argument	Type	Description
text*	string
operation*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "text",
    "operation"
  ],
  "properties": {
    "text": {
      "type": "string",
      "maxLength": 200000
    },
    "operation": {
      "enum": [
        "sha1",
        "sha256",
        "sha384",
        "sha512",
        "base64_encode",
        "base64_decode",
        "base64url_encode",
        "base64url_decode",
        "hex_encode",
        "hex_decode",
        "url_encode",
        "url_decode"
      ],
      "type": "string"
    }
  },
  "additionalProperties": false
}

json_repair

Turns almost-JSON into valid JSON: removes markdown code fences, comments and trailing commas, adds missing quotes, commas and closing brackets, converts single quotes, Python True/False/None and truncated output. Returns the repaired JSON string and whether the input was already valid.

read-only

Argument	Type	Description
text*	string	The broken JSON text
pretty	boolean	Indent the output. Default false.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "text"
  ],
  "properties": {
    "text": {
      "type": "string",
      "maxLength": 500000,
      "minLength": 1,
      "description": "The broken JSON text"
    },
    "pretty": {
      "type": "boolean",
      "description": "Indent the output. Default false."
    }
  },
  "additionalProperties": false
}

json_schema_validate

Checks a JSON value against a JSON Schema (drafts 4, 7, 2019-09 and 2020-12) and lists every violation with its location. Use it to confirm structured output or an API payload is correct before sending it. `data` and `schema` may be JSON values or JSON strings.

read-only

Argument	Type	Description
data*	any	The JSON value to check (any type), or a JSON string of it
draft	string	Default 2020-12
schema*	any	The JSON Schema (object), or a JSON string of it

Input schema (JSON)

{
  "type": "object",
  "required": [
    "data",
    "schema"
  ],
  "properties": {
    "data": {
      "description": "The JSON value to check (any type), or a JSON string of it"
    },
    "draft": {
      "enum": [
        "4",
        "7",
        "2019-09",
        "2020-12"
      ],
      "type": "string",
      "description": "Default 2020-12"
    },
    "schema": {
      "description": "The JSON Schema (object), or a JSON string of it"
    }
  },
  "additionalProperties": false
}

regex_test

Runs a JavaScript regular expression against text and returns every match with its position and capture groups, or the text after replacement. Use it to verify a regex actually works before relying on it.

read-only

Argument	Type	Description
text*	string
flags	string	Optional flags: i (ignore case), m (multiline), s (dotall), u (unicode), y (sticky). Global matching is always on.
pattern*	string	Regex pattern without slashes, e.g. "(\\d{3})-(\\d{4})"
max_matches	integer	Default 100
replace_with	string	Optional replacement string ($1, $<name> supported). If set, returns the replaced text too.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "pattern",
    "text"
  ],
  "properties": {
    "text": {
      "type": "string",
      "maxLength": 50000
    },
    "flags": {
      "type": "string",
      "pattern": "^[imsuy]*$",
      "maxLength": 6,
      "description": "Optional flags: i (ignore case), m (multiline), s (dotall), u (unicode), y (sticky). Global matching is always on."
    },
    "pattern": {
      "type": "string",
      "maxLength": 1000,
      "minLength": 1,
      "description": "Regex pattern without slashes, e.g. \"(\\\\d{3})-(\\\\d{4})\""
    },
    "max_matches": {
      "type": "integer",
      "maximum": 1000,
      "minimum": 1,
      "description": "Default 100"
    },
    "replace_with": {
      "type": "string",
      "maxLength": 1000,
      "description": "Optional replacement string ($1, $<name> supported). If set, returns the replaced text too."
    }
  },
  "additionalProperties": false
}

text_stats

Counts exactly what language models are bad at counting: characters (as humans see them), words, lines, sentences, paragraphs, UTF-8 bytes, and occurrences of a letter or substring (e.g. how many "r" in "strawberry"). Use it to check length limits (tweets, SMS, meta descriptions, form fields) before submitting text.

read-only

Argument	Type	Description
text*	string	The text to analyze
count	string	Optional letter, word or substring to count occurrences of
overlapping	boolean	For `count`: count overlapping matches ("aa" in "aaa" = 2). Default false.
case_sensitive	boolean	For `count`. Default false.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "text"
  ],
  "properties": {
    "text": {
      "type": "string",
      "maxLength": 200000,
      "description": "The text to analyze"
    },
    "count": {
      "type": "string",
      "maxLength": 1000,
      "description": "Optional letter, word or substring to count occurrences of"
    },
    "overlapping": {
      "type": "boolean",
      "description": "For `count`: count overlapping matches (\"aa\" in \"aaa\" = 2). Default false."
    },
    "case_sensitive": {
      "type": "boolean",
      "description": "For `count`. Default false."
    }
  },
  "additionalProperties": false
}

validate_email

Checks whether an email address is correctly formatted and returns a normalized version. Set check_dns=true to also confirm the domain exists and can receive mail (MX records). Does not send email and cannot confirm that a specific mailbox exists.

read-only

Argument	Type	Description
email*	string
check_dns	boolean	Also look up the domain's mail servers. Default false.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "email"
  ],
  "properties": {
    "email": {
      "type": "string",
      "maxLength": 512
    },
    "check_dns": {
      "type": "boolean",
      "description": "Also look up the domain's mail servers. Default false."
    }
  },
  "additionalProperties": false
}

validate_iban

Validates an International Bank Account Number: country, length for that country, and the mod-97 check digits. Returns electronic and printed formats. A valid IBAN is correctly formed; this does not confirm the account exists.

read-only

Argument	Type	Description
iban*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "iban"
  ],
  "properties": {
    "iban": {
      "type": "string",
      "maxLength": 64
    }
  },
  "additionalProperties": false
}

validate_phone

Validates a phone number using Google's libphonenumber rules and returns it in E.164 (+14155552671), international and national formats, plus the country and line type (mobile, fixed line, toll free...). For numbers without a +country code, pass default_country.

read-only

Argument	Type	Description
phone*	string
default_country	string	Two-letter country code used when the number has no "+" prefix, e.g. "US", "GB", "DE"

Input schema (JSON)

{
  "type": "object",
  "required": [
    "phone"
  ],
  "properties": {
    "phone": {
      "type": "string",
      "maxLength": 64
    },
    "default_country": {
      "type": "string",
      "pattern": "^[A-Za-z]{2}$",
      "description": "Two-letter country code used when the number has no \"+\" prefix, e.g. \"US\", \"GB\", \"DE\""
    }
  },
  "additionalProperties": false
}

validate_url

Checks that a URL is well-formed, normalizes it (lowercase host, punycode, default ports removed, spaces encoded) and splits it into parts including each query parameter. Flags common problems such as missing scheme, private/localhost addresses and credentials embedded in the URL. Does not fetch the URL.

read-only

Argument	Type	Description
url*	string
require_https	boolean	Treat http:// as invalid. Default false.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 8192
    },
    "require_https": {
      "type": "boolean",
      "description": "Treat http:// as invalid. Default false."
    }
  },
  "additionalProperties": false
}

Plumbkit

Try it

business_days Read-only

Plumbkit

Try it

business_days Read-only

Tools (16)