How do I use Math-MCP?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Math-MCP what is the average of 10,20,30?" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

Math-MCP

by PolarisHub

Overview Schema Source Related Servers Discussions Admin

TypeScript

Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Math-MCP what is the average of 10,20,30?"

That's it! The server will respond to your query, and you can continue using it as needed.

Here is a step-by-step guide with screenshots.

Math-MCP

A Model Context Protocol (MCP) server that provides basic mathematical, statistical and trigonometric functions to Large Language Models (LLMs). This server enables LLMs to perform accurate numerical calculations through a simple API.

Features

Basic arithmetic operations (addition, subtraction, multiplication, division, sum, modulo)
Statistical functions (mean, median, mode, min, max)
Advanced statistics (variance, standard deviation, percentile, correlation, linear regression)
Rounding functions (floor, ceiling, round)
Trigonometric functions (sin, cos, tan, and their inverses; degrees/radians conversions)
Exact number theory and combinatorics (GCD, LCM, primes, factors, factorials, combinations, permutations)
Exact fraction simplification and arithmetic using arbitrary-size integers
Percentages, compound interest, and fixed-rate loan payments
Quadratic equations and 2x2 linear systems, including complex or non-unique solutions
3D graphics transforms, bone hierarchies, camera matrices, and world-to-screen projection
Bayes' theorem and normalized multi-hypothesis Bayesian updates

Related MCP server: Calculator MCP

Installation

Note: Ensure you have Node.js installed on your computer.

Just clone this repository and save it locally somewhere on your computer.

Then add this server to your MCP configuration file:

"math": {
  "command": "node",
  "args": ["PATH\\TO\\PROJECT\\math-mcp\\build\\index.js"]
}

Here is an example for OpenCode

{
  "mcp": {
    "math-mcp": {
      "type": "local",
      "command": [
        "node",
        "PATH\\TO\\PROJECT\\math-mcp\\build\\index.js"
      ]
    }
  }
}

Replace PATH\\TO\\PROJECT with the actual path to where you cloned the repository.

Note: This project comes prebuilt, so installation is easy but if you change anything in the code, rebuild the project with npm run build.

Available Functions

The Math-MCP server provides the following mathematical operations:

Arithmetic Operations

Function	Description	Parameters
`add`	Adds two numbers together	`firstNumber`: The first addend`secondNumber`: The second addend
`subtract`	Subtracts the second number from the first number	`minuend`: The number to subtract from (minuend)`subtrahend`: The number being subtracted (subtrahend)
`multiply`	Multiplies two numbers together	`firstNumber`: The first number`secondNumber`: The second number
`division`	Divides the first number by the second number	`numerator`: The number being divided (numerator)`denominator`: The number to divide by (denominator)
`sum`	Adds any number of numbers together	`numbers`: Array of numbers to sum
`modulo`	Divides two numbers and returns the remainder	`numerator`: The number being divided (numerator)`denominator`: The number to divide by (denominator)
`floor`	Rounds a number down to the nearest integer	`number`: The number to round down
`ceiling`	Rounds a number up to the nearest integer	`number`: The number to round up
`round`	Rounds a number to the nearest integer	`number`: The number to round

Statistical Operations

Function	Description	Parameters
`mean`	Calculates the arithmetic mean of a list of numbers	`numbers`: Array of numbers to find the mean of
`median`	Calculates the median of a list of numbers	`numbers`: Array of numbers to find the median of
`mode`	Finds the most common number in a list of numbers	`numbers`: Array of numbers to find the mode of
`min`	Finds the minimum value from a list of numbers	`numbers`: Array of numbers to find the minimum of
`max`	Finds the maximum value from a list of numbers	`numbers`: Array of numbers to find the maximum of
`variance`	Calculates population or sample variance	`numbers`: Values`sample`: Optional; use `true` for n-1
`standard_deviation`	Calculates population or sample standard deviation	`numbers`: Values`sample`: Optional; use `true` for n-1
`percentile`	Calculates an inclusive R-7/Excel-style percentile	`numbers`: Values`percentile`: 0 through 100
`correlation`	Calculates Pearson correlation for paired observations	`firstValues`: First series`secondValues`: Second series
`linear_regression`	Fits `y = slope*x + intercept` and returns R-squared	`xValues`: X series`yValues`: Y series

Exact and Number-Theory Operations

Function	Description	Parameters
`greatest_common_divisor`	Finds the GCD of two safe integers	`first`, `second`: Integers
`least_common_multiple`	Finds the exact LCM as a decimal string	`first`, `second`: Integers
`is_prime`	Tests a safe integer for primality	`value`: Non-negative integer
`prime_factors`	Finds prime factors up to 1,000,000,000,000	`value`: Integer
`factorial`	Calculates n! exactly through 1000!	`value`: Integer
`combinations`	Calculates n choose r exactly	`total`: n`selected`: r
`permutations`	Calculates nPr exactly	`total`: n`selected`: r
`simplify_fraction`	Reduces an arbitrary-size integer fraction exactly	`numerator`, `denominator`: Decimal integer strings
`fraction_arithmetic`	Adds, subtracts, multiplies, or divides fractions exactly	`operation`; two numerator/denominator pairs as strings

Applied Operations

Function	Description	Parameters
`percentage_of`	Calculates a percentage of a value	`valuepercentage`: Use 15 for 15%
`percentage_change`	Calculates percent increase or decrease	`originalValuenewValue`
`round_to`	Rounds to a requested number of decimal places	`valuedecimalPlaces`: 0 through 15
`compound_interest`	Calculates compound growth and optional end-of-period contributions	`principal`, `annualRatePercent`, `years`, `compoundsPerYear`, optional `contributionPerPeriod`
`loan_payment`	Calculates fixed-rate payment, total paid, and total interest	`principal`, `annualRatePercent`, `years`, `paymentsPerYear`

Algebra Operations

Function	Description	Parameters
`solve_quadratic`	Solves `ax^2 + bx + c = 0`, including complex roots	`a`, `b`, `c`
`solve_linear_system_2x2`	Solves or classifies two linear equations	Coefficients `a1`, `b1`, `c1`, `a2`, `b2`, `c2`

3D Graphics and Bone Projection

All matrices are flat, row-major 4x4 arrays used with column vectors. Transform composition is projection * view * world * point. Quaternions use {x, y, z, w}; Euler inputs are radians. Defaults are right-handed coordinates, OpenGL-style NDC depth -1..1, and a top-left screen origin where Y points down.

Function	Description
`quaternion_from_euler`	Converts Euler radians and an explicit rotation order to a quaternion
`compose_transform_4x4`	Builds a `translation * rotation * scale` matrix
`multiply_matrices_4x4`	Multiplies two matrices as `first * second`
`transform_point_3d`	Applies a matrix to a 3D point with homogeneous `w=1`
`bone_local_to_world`	Combines one bone's local transform with its parent world matrix
`bone_hierarchy_to_world`	Resolves named parent/child local transforms into world-space bones
`look_at_view_matrix`	Creates a right- or left-handed world-to-view camera matrix
`perspective_projection_matrix`	Creates a projection matrix with selectable handedness and clip-depth range
`world_to_view`	Applies the view matrix to a world-space point
`view_to_clip`	Applies the projection matrix to produce a 4D clip-space point
`clip_to_ndc`	Performs perspective division: `(x/w, y/w, z/w)`
`ndc_to_screen`	Scales NDC to a requested pixel width and height
`world_to_screen`	Runs projection with a combined `projection * view` matrix and reports visibility
`project_bone_points`	Batch-projects named world-space bone positions to 2D screen coordinates

The explicit projection pipeline is:

world point -> view matrix -> view point
view point  -> projection matrix -> clip point (x, y, z, w)
clip point  -> divide by w -> NDC
NDC         -> resolution scaling -> screen pixels

Probability Operations

Function	Description	Parameters
`bayes_theorem`	Calculates `P(H	E) = P(E
`bayes_update_hypotheses`	Normalizes likelihood-weighted priors across hypotheses	Array of hypothesis labels, priors, and likelihoods

Trigonometric Operations

Function	Description	Parameters
`sin`	Calculates the sine of a number in radians	`number`: The number in radians to find the sine of
`arcsin`	Calculates the arcsine (in radians) of a number	`number`: The number to find the arcsine of
`cos`	Calculates the cosine of a number in radians	`number`: The number in radians to find the cosine of
`arccos`	Calculates the arccosine (in radians) of a number	`number`: The number to find the arccosine of
`tan`	Calculates the tangent of a number in radians	`number`: The number in radians to find the tangent of
`arctan`	Calculates the arctangent (in radians) of a number	`number`: The number to find the arctangent of
`radiansToDegrees`	Converts a radian value to its equivalent in degrees	`number`: The number in radians to convert to degrees
`degreesToRadians`	Converts a degree value to its equivalent in radians	`number`: The number in degrees to convert to radians

Available Tools

59 tools

addB

Adds two numbers together

Inputs: firstNumber (required), secondNumber (required).

arccosB

Calculates the arccosine (in radians) of a number

Inputs: number (required).

arcsinA

Calculates the arcsine (in radians) of a number

Inputs: number (required).

arctanA

Calculates the arctangent (in radians) of a number

Inputs: number (required).

bayes_theoremA

Calculates P(hypothesis|evidence) = P(evidence|hypothesis) * P(hypothesis) / P(evidence)

Inputs: prior (required), evidence (required), likelihood (required).

bayes_update_hypothesesB

Normalizes priors and evidence likelihoods into posterior probabilities for mutually exclusive, exhaustive hypotheses

Inputs: hypotheses (required).

bone_hierarchy_to_worldA

Resolves a complete bone hierarchy from local transforms to world matrices and world positions; detects missing parents and cycles

Inputs: bones (required).

bone_local_to_worldA

Combines a parent bone world matrix with a child local position, quaternion rotation, and scale

Inputs: localPosition (required), parentWorldMatrix (required), localScale, localRotation.

ceilingA

Rounds a number up to the nearest integer

Inputs: number (required).

clip_to_ndcB

Performs the 4D clip-space perspective divide x/w, y/w, z/w to normalized device coordinates

Inputs: clipPoint (required).

combinationsA

Calculates n choose r exactly when order does not matter; returns a decimal string

Inputs: total (required), selected (required).

compose_transform_4x4A

Builds a row-major 4x4 TRS transform from position, quaternion rotation, and scale for column vectors

Inputs: position (required), scale, rotation.

compound_interestA

Calculates compound growth with optional equal contributions made at the end of every compounding period

Inputs: years (required), principal (required), compoundsPerYear (required), annualRatePercent (required), +1 more.

correlationB

Calculates the Pearson correlation coefficient for paired numeric observations

Inputs: firstValues (required), secondValues (required).

cosA

Calculates the cosine of a number in radians

Inputs: number (required).

degreesToRadiansA

Converts a degree value to its equivalent in radians

Inputs: number (required).

divisionB

Divides the first number by the second number

Inputs: numerator (required), denominator (required).

factorialA

Calculates n! exactly for an integer from 0 through 1000; returns a decimal string

Inputs: value (required).

floorA

Rounds a number down to the nearest integer

Inputs: number (required).

fraction_arithmeticA

Adds, subtracts, multiplies, or divides two fractions exactly and returns the reduced result

Inputs: operation (required), firstNumerator (required), secondNumerator (required), firstDenominator (required), +1 more.

greatest_common_divisorA

Finds the greatest common divisor (GCD) of two safe integers

Inputs: first (required), second (required).

is_primeA

Determines whether a non-negative safe integer is prime

Inputs: value (required).

least_common_multipleA

Finds the exact least common multiple (LCM) of two safe integers; returns a decimal string

Inputs: first (required), second (required).

linear_regressionA

Fits the least-squares line y = slope*x + intercept and returns slope, intercept, and R-squared

Inputs: xValues (required), yValues (required).

loan_paymentA

Calculates the payment and total interest for a standard fixed-rate amortizing loan

Inputs: years (required), principal (required), paymentsPerYear (required), annualRatePercent (required).

look_at_view_matrixA

Creates a row-major look-at world-to-view matrix for a right- or left-handed coordinate system

Inputs: up (required), eye (required), target (required), handedness.

maxB

Finds the maximum value from a list of numbers

Inputs: numbers (required).

meanA

Calculates the arithmetic mean of a list of numbers

Inputs: numbers (required).

medianB

Calculates the median of a list of numbers

Inputs: numbers (required).

minA

Finds the minimum value from a list of numbers

Inputs: numbers (required).

modeA

Finds the most common number in a list of numbers

Inputs: numbers (required).

moduloA

Divides two numbers and returns the remainder

Inputs: numerator (required), denominator (required).

multiplyA

Multiplies two numbers together

Inputs: firstNumber (required), secondNumber (required).

multiply_matrices_4x4A

Multiplies two row-major 4x4 matrices and returns first * second, for column-vector transforms

Inputs: first (required), second (required).

ndc_to_screenB

Scales normalized device coordinates to a 2D screen resolution

Inputs: width (required), height (required), ndcPoint (required), yDirection.

percentage_changeA

Calculates the percentage increase or decrease from an original value to a new value

Inputs: newValue (required), originalValue (required).

percentage_ofA

Calculates a percentage of a value, such as 15% of 240

Inputs: value (required), percentage (required).

percentileA

Calculates a percentile using sorted linear interpolation (R-7 / Excel PERCENTILE.INC method)

Inputs: numbers (required), percentile (required).

permutationsA

Calculates ordered selections nPr exactly; returns a decimal string

Inputs: total (required), selected (required).

perspective_projection_matrixB

Creates a perspective view-to-clip matrix with explicit handedness and NDC depth range

Inputs: farPlane (required), nearPlane (required), aspectRatio (required), verticalFieldOfViewDegrees (required), +2 more.

prime_factorsB

Returns the prime factorization of an integer from 2 through 1,000,000,000,000

Inputs: value (required).

project_bone_pointsB

Batch-projects named bone or joint world positions to 2D pixels using a combined projection*view matrix

Inputs: width (required), height (required), points (required), viewProjectionMatrix (required), +2 more.

quaternion_from_eulerA

Converts Euler rotations in radians to a normalized quaternion; order states the rotations applied first-to-last

Inputs: eulerRadians (required), order.

radiansToDegreesA

Converts a radian value to its equivalent in degrees

Inputs: number (required).

roundB

Rounds a number to the nearest integer

Inputs: number (required).

round_toA

Rounds a number to a specified count of decimal places

Inputs: value (required), decimalPlaces (required).

simplify_fractionA

Reduces a fraction exactly using integer strings, preserving values larger than JSON's safe integer range

Inputs: numerator (required), denominator (required).

sinA

Calculates the sine of a number in radians

Inputs: number (required).

solve_linear_system_2x2A

Solves a1x + b1y = c1 and a2x + b2y = c2, including no-solution and infinite-solution cases

Inputs: a1 (required), a2 (required), b1 (required), b2 (required), +2 more.

solve_quadraticC

Solves ax^2 + bx + c = 0 and returns real or complex roots

Inputs: a (required), b (required), c (required).

standard_deviationA

Calculates population or sample standard deviation with a numerically stable algorithm

Inputs: numbers (required), sample.

subtractA

Subtracts the second number from the first number

Inputs: minuend (required), subtrahend (required).

sumB

Adds any number of numbers together

Inputs: numbers (required).

tanB

Calculates the tangent of a number in radians

Inputs: number (required).

transform_point_3dA

Transforms a 3D position by a row-major 4x4 matrix using homogeneous w=1 and returns x,y,z,w

Inputs: point (required), matrix (required).

varianceC

Calculates population or sample variance with a numerically stable algorithm

Inputs: numbers (required), sample.

view_to_clipA

Transforms one homogeneous view-space position into 4D clip space with a supplied projection matrix

Inputs: viewPoint (required), projectionMatrix (required).

world_to_screenA

Projects one world-space 3D point through a combined projection*view matrix to 2D pixels with visibility and behind-camera flags

Inputs: width (required), height (required), worldPoint (required), viewProjectionMatrix (required), +2 more.

world_to_viewA

Transforms one world-space 3D position into view space with a supplied row-major view matrix

Inputs: viewMatrix (required), worldPoint (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.3/5.0

Scored 2026-07-28 11:45 across 59 tools

Disambiguation5/5

Each tool has a distinct mathematical operation with clear descriptions. Overlaps are minimal (e.g., add vs. sum, round vs. round_to) but descriptions differentiate them. No two tools perform the same function.

Naming Consistency2/5

The naming convention is inconsistent: single-word names (min, add), snake_case (percentage_of, compose_transform_4x4), and camelCase (radiansToDegrees) are mixed. Verbs like 'division' instead of 'divide' break patterns. While many tools follow verb_noun or noun_verb, the overall pattern is chaotic.

Tool Count2/5

With 59 tools, the server is extremely heavy for an MCP server. While each tool is well-defined, the sheer number can overwhelm an agent's tool selection. A more focused scope (e.g., separating linear algebra from basic arithmetic) would improve usability.

Completeness4/5

The tool set covers a vast range of mathematical domains: arithmetic, trigonometry, statistics, number theory, finance, linear algebra, 3D graphics, and probability. Minor gaps exist (e.g., no general linear system solver beyond 2x2, no calculus operations), but overall it is very comprehensive for a general math server.

Maintenance

ActivityInactive

ResponsivenessOutdated data

Resources

Related MCP Connectors

Aman-Amith-Shastry-scientific_computation_mcpA
ai.smithery
This MCP server enables users to perform scientific computations regarding linear algebra and vect…
Research & Data
2623
https://server.smithery.ai/@Aman-Amith-Shastry/scientific_computation_mcp/mcp
Math MCP LearningA
io.github.clouatre-labs
Educational MCP server with 17 math/stats tools, visualizations, and persistent workspace
Education & Learning Tools Research & Data Developer Tools
1727
https://math-mcp.fastmcp.app/mcp
mcpA
io.scorecard
MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.
RAG Systems Monitoring Testing & QA Tools
3
https://mcp.scorecard.io/mcp
hithereiamaliff-mcp-nextcloud
ai.smithery
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Cloud Storage File Systems Workplace & Productivity
239
https://server.smithery.ai/@hithereiamaliff/mcp-nextcloud/mcp

Related MCP Servers

Math-MCP
Code Execution Developer Tools
EthanHenrickson
A
license
A
quality
C
maintenance
A Model Context Protocol server that provides basic mathematical and statistical functions to LLMs, enabling them to perform accurate numerical calculations through a simple API.
Updated 6 months ago (2026-05-30 16:32 UTC)
13
33 npm
191
MIT
Calculator MCP
Developer Tools Code Execution
wrtnlabs
A
license
B
quality
C
maintenance
A Model Context Protocol server that provides basic calculator functionality for LLMs, enabling them to perform mathematical operations like addition, subtraction, multiplication, division, modulo, and square root.
Updated 2 years ago (2025-05-13 04:49 UTC)
6
235 npm
15
MIT
MCP Calculator Server
RMahshie
-
license
Not graded
quality
Not graded
maintenance
A calculator server that exposes mathematical functions as tools (add, subtract, multiply, divide, square, power, square root), enabling language models to perform calculations through Model Context Protocol (MCP).
Updated a year ago (2025-06-01 02:51 UTC)
-
Math MCP Server
Research & Data Developer Tools
YasogaN
A
license
A
quality
D
maintenance
A Model Context Protocol server that exposes 8 mathematical tools (arithmetic, algebra, calculus, matrix operations, statistics, probability, unit conversions) to any MCP-compatible AI agent, enabling mathematical computations without code.
Updated 3 months ago (2026-08-01 02:45 UTC)
8
11 npm
1
MIT

Appeared in Searches

A server for improving AI math capability without using an API

Math-MCP

Features

Installation

Available Functions

Arithmetic Operations

Statistical Operations

Exact and Number-Theory Operations

Applied Operations

Algebra Operations

3D Graphics and Bone Projection

Probability Operations

Trigonometric Operations

Available Tools

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

Math-MCP

Calculator MCP

MCP Calculator Server

Math MCP Server

Appeared in Searches