absolute
Absolute value.
LABSCO SUMMARY
Sample versus population variance being a flag rather than an assumption is the detail that says this was written by someone who cares about being right.
Most calculator tools pick one variance formula and never mention it, which produces answers that are wrong by a factor nobody notices. Defaulting to the sample form and exposing the population form as a parameter is the correct handling of a real ambiguity. The same care shows in errors: dividing by zero raises rather than returning infinity or a plausible number, which matters more here than in a library because the caller is a model that will happily narrate whatever comes back. Percentage operations in three directions is a small thing that reflects how the question is actually asked.
What it is
A deterministic calculator exposed as tools: arithmetic and powers, trigonometry with degrees or radians, logarithms, descriptive statistics, percentage operations and a constants lookup.
What you get
- Arithmetic and algebra including power, square root, modulo, absolute value and factorial — the last one stating its own overflow point.
- Full trigonometry with inverses, defaulting to degrees and taking radians on request, which removes the single most common unit mistake.
- Descriptive statistics done correctly: variance and standard deviation default to the sample form with a flag for the population form, rather than silently picking one.
- Percentages in all three directions people actually ask them — X percent of Y, the change from A to B, and X is Y percent of what.
- Error cases named rather than returned as a value: divide and modulo error on a zero divisor, square root errors on negative input, and the logarithms error on non-positive input.
- get_constant returns mathematical, physical and chemical constants from a defined set.
Requirements
Nothing to supply.
Setup effort
One command — npx @slbdn/cruncher-mcp
USE CASES
01
Getting arithmetic that is actually computed
Run the calculation as a tool call rather than letting the model produce a number that looks right, with zero divisors and negative roots raising instead of returning something.
02
Summarising a set of numbers
Get the mean, median, range and spread — choosing sample or population variance deliberately rather than inheriting whichever the tool assumed.
03
Working with angles without a unit mistake
Use degrees by default or ask for radians explicitly, in both directions of the trig functions.
04
Answering a percentage question whichever way it was asked
Compute what X percent of Y is, the change between two figures, or the base a figure is a percentage of.
05
Getting a constant right
Look it up from the defined set rather than recalling a value to the wrong number of digits.
34 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
acos
Arccosine. Result in degrees by default, or radians with unit param.
add
Adds two numbers.
asin
Arcsine. Result in degrees by default, or radians with unit param.
atan
Arctangent. Result in degrees by default, or radians with unit param.
avg
Average (mean) of numbers.
convert_unit
Convert between common units. Categories: length, weight, temperature, area, volume, time, speed, digital_storage.
cosine
Cosine. Angle in degrees by default, or radians with unit: "radians".
count
Count elements.
divide
Divides two numbers. Errors on zero divisor.
evaluate_expression
Evaluate a mathematical expression. PRIMARY tool for ALL math: +, -, *, /, %, ^. Functions: sqrt, sin, cos, tan, asin, acos, atan, log10, ln, log(x,base), abs, round, floor, ceil, min, max. Constants: pi, e, tau, phi, sqrt2, euler_mascheroni, c, g, G, h, k, R, NA, e_charge, m_e, m_p. Parentheses and scientific notation (1e6) supported. Use explicit operators: 2 * pi, not 2pi.
factorial
Factorial of non-negative integer (n!). n > 170 overflows.
get_angle_mode
Get current trig angle mode.
get_constant
Returns a mathematical, physical, or chemical constant. See enum values.
logarithm
Base-10 logarithm. Errors on non-positive input.
max
Maximum of numbers.
median
Median of numbers.
min
Minimum of numbers.
modulo
Remainder of a / b. Errors on zero divisor.
multiply
Multiplies two numbers.
natural_log
Natural logarithm (ln). Errors on non-positive input.
percentage_change
Percentage change from A to B. e.g., 50→80 = +60%
percentage_of
What is X% of Y? e.g., 15% of 200 = 30
percentage_reverse
X is Y% of what? e.g., 30 is 15% of 200
power
Raises a to the power of b.
range
Range (max - min) of numbers.
set_angle_mode
Set global trig angle mode. Individual calls with unit param override this.
sine
Sine. Angle in degrees by default, or radians with unit: "radians".
sqrt
Square root. Errors on negative input.
std_dev
Sample standard deviation (n-1). Set population: true for population (n).
subtract
Subtracts two numbers.
sum
Sum of numbers.
tangent
Tangent. Angle in degrees by default, or radians with unit: "radians".
variance
Sample variance (n-1). Set population: true for population variance (n).
BEFORE YOU INSTALL
What to know first
Tools you get
34 tools when we connected.
Requires
- npx on PATH
- Node.js 18.0.0 or newer
INSTALLATION
Connect your client
Server setup
TERMINAL
npx @slbdn/cruncher-mcpMCP Clients
Claude Desktop, Cline
JSON
{
"mcpServers": {
"cruncher": {
"command": "npx",
"args": [
"-y",
"@slbdn/cruncher-mcp"
]
}
}
}Cursor
Open Cursor Settings (gear icon) > Features > MCP Servers.
Click + Add New MCP Server.
Set Type to command, Name to cruncher, and Command to npx @slbdn/cruncher-mcp.
