Crucher MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CRUNCHER_TIMEOUT | No | Worker thread execution timeout (ms). Range 100-60000 | 3000 |
| CRUNCHER_TOOL_SET | No | Controls tool exposure: minimal (5), standard (34 default), full (43) | standard |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| addB | Adds two numbers. |
| subtractC | Subtracts two numbers. |
| multiplyA | Multiplies two numbers. |
| divideA | Divides two numbers. Errors on zero divisor. |
| powerB | Raises a to the power of b. |
| sqrtA | Square root. Errors on negative input. |
| sineA | Sine. Angle in degrees by default, or radians with unit: "radians". |
| cosineA | Cosine. Angle in degrees by default, or radians with unit: "radians". |
| tangentB | Tangent. Angle in degrees by default, or radians with unit: "radians". |
| asinA | Arcsine. Result in degrees by default, or radians with unit param. |
| acosA | Arccosine. Result in degrees by default, or radians with unit param. |
| atanA | Arctangent. Result in degrees by default, or radians with unit param. |
| logarithmA | Base-10 logarithm. Errors on non-positive input. |
| natural_logA | Natural logarithm (ln). Errors on non-positive input. |
| absoluteB | Absolute value. |
| get_constantA | Returns a mathematical, physical, or chemical constant. See enum values. |
| sumB | Sum of numbers. |
| avgA | Average (mean) of numbers. |
| medianC | Median of numbers. |
| minB | Minimum of numbers. |
| maxA | Maximum of numbers. |
| countB | Count elements. |
| rangeB | Range (max - min) of numbers. |
| varianceA | Sample variance (n-1). Set population: true for population variance (n). |
| std_devA | Sample standard deviation (n-1). Set population: true for population (n). |
| percentage_ofA | What is X% of Y? e.g., 15% of 200 = 30 |
| percentage_changeA | Percentage change from A to B. e.g., 50→80 = +60% |
| percentage_reverseA | X is Y% of what? e.g., 30 is 15% of 200 |
| moduloA | Remainder of a / b. Errors on zero divisor. |
| factorialA | Factorial of non-negative integer (n!). n > 170 overflows. |
| evaluate_expressionA | 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. |
| convert_unitA | Convert between common units. Categories: length, weight, temperature, area, volume, time, speed, digital_storage. |
| set_angle_modeA | Set global trig angle mode. Individual calls with unit param override this. |
| get_angle_modeA | Get current trig angle mode. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 34 tools
Many tools heavily overlap: add, subtract, multiply, divide, sum, evaluate_expression, and others all handle basic arithmetic, and evaluate_expression claims to be the PRIMARY tool for ALL math, making the individual operations redundant. The three percentage tools and multiple aggregation tools (avg, median, min, max, range) are similar enough to cause misselection without careful reading.
Most names are lowercase snake_case, but there's no consistent verb_noun pattern: simple verbs (add, divide, power, sqrt) mix with noun-style names (absolute, range, count) and multiword snake_case (evaluate_expression, convert_unit, set_angle_mode). The truncation styles also vary (sqrt vs natural_log vs modulo), though still readable.
34 tools is excessive for a math utility server, especially because evaluate_expression alone can handle most arithmetic, power, trig, log, absolute, and function needs. The individual arithmetic and function tools become redundant, making the set feel bloated.
Domain coverage is strong: arithmetic, trigonometry, logarithms, statistics, percentages, constants, and unit conversion are all present. Minor gaps like standalone rounding/floor/ceil functions exist, but evaluate_expression covers them, so no significant dead ends.