How do I use Mathematical Calculator MCP Server?

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., "@Mathematical Calculator MCP Server Can you calculate 3.5^2 * sin(pi/4)?" 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.

Mathematical Calculator MCP Server

by Chetto983

Overview Schema Source Related Servers Discussions Admin

Python

Remote

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., "@Mathematical Calculator MCP Server Can you calculate 3.5^2 * sin(pi/4)?"

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.

Mathematical Calculator MCP Server

This is a Model Context Protocol (MCP) server that provides advanced mathematical calculation capabilities, including symbolic math, statistical analysis, matrix operations, vector operations, and headless function plotting.

Features

The Mathematical Calculator MCP Server provides the following tools:

Basic Calculations: Evaluate mathematical expressions safely
Symbolic Mathematics:
- Solve equations (linear, quadratic, polynomial, etc.)
- Calculate derivatives of expressions
- Compute integrals of expressions
Statistical Analysis:
- Mean, median, mode
- Variance, standard deviation
- Correlation coefficient
- Linear regression
- Confidence intervals
Matrix Operations:
- Matrix addition
- Matrix multiplication
- Matrix transposition
- Matrix determinant
Vector Operations:
- Dot product
- Cross product
- Magnitude
Plotting:
- Headless function plot generation with a PNG render check

Related MCP server: Math MCP Server

Installation

Prerequisites

Python 3.11+
uv (recommended) or pip
Any MCP host that supports stdio servers

Installation Steps

Clone the repository:

git clone https://github.com/chetto1983/calculator-mcp-server.git
cd calculator-mcp-server

(Option 1) Setup with the provided script:

chmod +x setup_venv.sh
./setup_venv.sh

(Option 2) Or manually set up the virtual environment:

python3 -m venv venv
source venv/bin/activate
pip install -e ".[dev]"

Run doc-tests to verify everything works:
```
bash run_doctests.sh
```

Integration with Claude Desktop

Method 1: Configure in Claude Desktop

Add the server to your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

Add the following to the mcpServers section:

{
  "mcpServers": {
    "calculator": {
      "command": "uvx",
      "args": [
        "--from",
        "calculator-mcp-server@git+https://github.com/chetto1983/calculator-mcp-server.git",
        "--",
        "calculator-mcp-server",
        "--stdio"
      ]
    }
  }
}

Note: The server defaults to stdio. The --stdio flag is accepted for explicit host configuration, and --sse is available for local SSE experiments. The -- separates uvx arguments from the calculator server arguments.

Method 2: Install with the MCP CLI

Make sure you have uv installed (Installation Guide)

Install the MCP server in Claude Desktop:

mcp install calculator_server.py

Or with a custom name:

mcp install calculator_server.py --name "Math Calculator"

Once installed, Claude will automatically have access to all the mathematical tools and functions.

Usage Examples

After integrating with Claude Desktop, you can ask Claude to perform various mathematical operations. Here are some examples:

Basic Calculations

Can you calculate 3.5^2 * sin(pi/4)?

Solving Equations

Solve the following equation: x^2 - 5x + 6 = 0

Calculating Derivatives

What's the derivative of sin(x^2) with respect to x?

Computing Integrals

Calculate the integral of x^2 * e^x

Statistical Analysis

Find the mean, median, mode, and standard deviation of this dataset: [23, 45, 12, 67, 34, 23, 18, 95, 41, 23]

Linear Regression

Perform a linear regression on these points: (1,2), (2,3.5), (3,5.1), (4,6.5), (5,8.2)

Matrix Operations

Multiply these two matrices:
[1, 2, 3]
[4, 5, 6]

and

[7, 8]
[9, 10]
[11, 12]

Vector Operations

Compute the dot product of [1, 2, 3] and [4, 5, 6].

Function Plotting

Plot y = x^2 from -2 to 2.

Development

Testing

Run the comprehensive doctest suite:

bash run_doctests.sh

Run the pytest suite:

python -m pytest

Run linting:

ruff check .

Interactive Development Mode

For development and debugging, you can use the MCP development mode:

mcp dev calculator_server.py

This will start a local web interface where you can test all tools interactively.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgements

MCP Python SDK for the FastMCP server framework
SymPy for symbolic mathematics
NumPy and SciPy for numerical and statistical computations

Available Tools

23 tools

calculateA

Evaluates a mathematical expression and returns the result.

Supports basic operators (+, -, *, /, **, %, ^), mathematical functions (sin, cos, tan, exp, log, log10, sqrt), and constants (pi, e). Uses an AST whitelist for safe execution.

Args: expression: The mathematical expression to evaluate as a string. Examples: "2 + 2", "sin(pi/4)", "sqrt(16) * 2", "log(100, 10)"

Returns: On success: {"result": } On error: {"error": }

Examples: >>> calculate("2 * 3 + 4") {'result': 10} >>> calculate("sin(pi/2)") {'result': 1.0} >>> calculate("sqrt(16)") {'result': 4.0} >>> calculate("(2 + 3)^2") {'result': 25}

Notes: - Use 'x' as the variable (e.g., x2, not x^2) - Multiplication must be explicitly indicated with * (e.g., 2*x, not 2x) - Powers can be represented with ** or ^ (e.g., x2 or x^2)

Inputs: expression (required).

confidence_intervalB

Computes the confidence interval for the mean of a dataset.

Args: data: A list of numerical values. confidence: The confidence level (default is 0.95).

Returns: On success: {"confidence_interval": <(lower_bound, upper_bound)>} On error: {"error": }

Examples: >>> import numpy as np >>> np.random.seed(42) # For reproducible results >>> confidence_interval([1, 2, 3, 4]) # doctest: +ELLIPSIS {'confidence_interval': (0.445739743239..., 4.554260256760...)}

Inputs: data (required), confidence.

correlation_coefficientB

Computes the Pearson correlation coefficient between two lists of numbers.

Args: data_x: The first list of numerical values. data_y: The second list of numerical values.

Returns: On success: {"result": } On error: {"error": }

Examples: >>> correlation_coefficient([1, 2, 3], [4, 5, 6]) {'result': 1.0}

Inputs: data_x (required), data_y (required).

differentiateA

Computes the derivative of a mathematical expression with respect to a variable.

Supports polynomials, trigonometric functions, exponential functions, logarithms, and other functions supported by SymPy.

Args: expression: The mathematical expression to differentiate as a string. Examples: "x**2", "sin(x)", "exp(x)", "log(x)" variable: The variable with respect to which to differentiate. Default is "x". Optionally, other variables can be specified.

Returns: On success: {"result": } On error: {"error": }

Examples: >>> differentiate("x**2") {'result': '2x'} >>> differentiate("sin(x)") {'result': 'cos(x)'} >>> differentiate("xy", "y") {'result': 'x'} >>> differentiate("exp(x)") {'result': 'exp(x)'}

Notes: - Use mathematical notation with explicit operators (* for multiplication) - Powers can be represented with ** or ^ (e.g., x**2 or x^2) - For trigonometric functions, use sin(x), cos(x), etc. - Only support for one variable at a time (implicit differentiation not supported)

Inputs: expression (required), variable.

expandB

Expands an expression.

Args: expression: The expression to expand as a string.

Returns: On success: {"result": } On error: {"error": }

Examples: >>> expand("(x + 1)2") {'result': 'x2 + 2*x + 1'}

Inputs: expression (required).

factorizeA

Factorizes an expression.

Args: expression: The expression to factorize as a string.

Returns: On success: {"result": } On error: {"error": }

Examples: >>> factorize("x**2 + 2*x + 1") {'result': '(x + 1)**2'}

Inputs: expression (required).

integrateA

Computes the indefinite integral of a mathematical expression with respect to a variable.

Supports polynomials, trigonometric functions, exponential functions, logarithms, and other functions supported by SymPy.

Args: expression: The mathematical expression to integrate as a string. Examples: "x**2", "sin(x)", "exp(x)", "1/x" variable: The variable with respect to which to integrate. Default is "x". Optionally, other variables can be specified.

Returns: On success: {"result": } On error: {"error": }

Examples: >>> integrate("x2") {'result': 'x3/3'} >>> integrate("sin(x)") {'result': '-cos(x)'} >>> integrate("exp(x)") {'result': 'exp(x)'} >>> integrate("1/x") {'result': 'log(x)'} >>> integrate("xy", "y") {'result': 'xy**2/2'}

Notes: - The result is the indefinite integral without the constant of integration - Complex expressions may be returned in simplified form

Inputs: expression (required), variable.

linear_regressionA

Performs linear regression on a set of points and returns the slope and intercept.

Args: data: A list of tuples, where each tuple contains (x, y) coordinates.

Returns: On success: {"slope": , "intercept": } On error: {"error": }

Examples: >>> linear_regression([(1, 2), (2, 3), (3, 5)]) {'slope': 1.5, 'intercept': 0.3333333333333335}

Inputs: data (required).

matrix_additionA

Adds two matrices.

Args: matrix_a: The first matrix as a list of lists. matrix_b: The second matrix as a list of lists.

Returns: On success: {"result": } On error: {"error": }

Examples: >>> matrix_addition([[1, 2], [3, 4]], [[5, 6], [7, 8]]) {'result': [[6, 8], [10, 12]]}

Inputs: matrix_a (required), matrix_b (required).

matrix_determinantA

Computes the determinant of a square matrix.

Args: matrix: A square matrix as a list of rows.

Returns: On success: {"result": } On error: {"error": }

Examples: >>> matrix_determinant([[1, 2], [3, 4]]) {'result': -2.0}

Inputs: matrix (required).

matrix_multiplicationA

Multiplies two matrices.

Args: matrix_a: The first matrix as a list of lists. matrix_b: The second matrix as a list of lists.

Returns: On success: {"result": } On error: {"error": }

Examples: >>> matrix_multiplication([[1, 2], [3, 4]], [[5, 6], [7, 8]]) {'result': [[19, 22], [43, 50]]}

Inputs: matrix_a (required), matrix_b (required).

matrix_transposeA

Transposes a matrix.

Args: matrix: The matrix to transpose as a list of lists.

Returns: On success: {"result": } On error: {"error": }

Examples: >>> matrix_transpose([[1, 2], [3, 4]]) {'result': [[1, 3], [2, 4]]}

Inputs: matrix (required).

meanB

Computes the mean of a list of numbers.

Args: data: A list of numerical values.

Returns: On success: {"result": } On error: {"error": }

Examples: >>> mean([1, 2, 3, 4]) {'result': 2.5} >>> mean([10, 20, 30]) {'result': 20.0}

Inputs: data (required).

medianB

Computes the median of a list of numbers.

Args: data: A list of numerical values.

Returns: On success: {"result": } On error: {"error": }

Examples: >>> median([1, 2, 3, 4]) {'result': 2.5}

Inputs: data (required).

modeA

Computes the mode of a list of numbers.

Args: data: A list of numerical values.

Returns: On success: {"result": } On error: {"error": }

Examples: >>> mode([1, 2, 2, 3]) {'result': 2.0} >>> mode([1, 1, 2, 2]) {'result': 1.0} >>> mode([]) {'error': 'Cannot compute mode of empty array'}

Inputs: data (required).

plot_functionA

Plots a graph of y = f(x).

Args: expression: The function expression as a string. start: The first x value to plot. end: The final x value to plot. step: The number of x samples to render.

Returns: On success: {"result": "Plot generated successfully.", "format": "png", ...} On error: {"error": }

Notes: - Use 'x' as the variable (e.g., x2, not x^2) - Multiplication must be explicitly indicated with * (e.g., 2*x, not 2x) - Powers can be represented with ** or ^ (e.g., x2 or x^2)

Inputs: expression (required), end, step, start.

solve_equationA

Solves an algebraic equation for x and returns all solutions.

The equation must contain exactly one equality sign (=) and use a variable x. Can solve polynomial, trigonometric, and other equations supported by SymPy.

Args: equation: The equation to solve as a string. Format: ' = ' Examples: "x**2 - 5x + 6 = 0", "sin(x) = 0.5", "2x + 3 = 7"

Returns: On success: {"solutions": } On error: {"error": }

Examples: >>> solve_equation("x**2 - 5x + 6 = 0") {'solutions': '[2, 3]'} >>> solve_equation("2x + 3 = 7") {'solutions': '[2]'} >>> solve_equation("x = 0") {'solutions': '[0]'}

Notes: - Use 'x' as the variable (e.g., x2, not x^2) - Multiplication must be explicitly indicated with * (e.g., 2*x, not 2x) - Powers can be represented with ** or ^ (e.g., x2 or x^2)

Inputs: equation (required).

standard_deviationA

Computes the standard deviation of a list of numbers.

Args: data: A list of numerical values.

Returns: On success: {"result": } On error: {"error": }

Examples: >>> standard_deviation([1, 2, 3, 4]) {'result': 1.118033988749895}

Inputs: data (required).

summationA

Calculates the summation of a function from start to end.

Args: expression: The expression of function x as a string. start: The starting value of the summation. end: The ending value of the summation.

Returns: On success: {"result": } On error: {"error": }

Examples: >>> summation("x**2", 0, 10) {'result': 385}

Inputs: expression (required), end, start.

varianceB

Computes the variance of a list of numbers.

Args: data: A list of numerical values.

Returns: On success: {"result": } On error: {"error": }

Examples: >>> variance([1, 2, 3, 4]) {'result': 1.25}

Inputs: data (required).

vector_cross_productB

Computes the cross product of two 2D or 3D vectors.

Args: vector_a: The first vector as a list of numbers. vector_b: The second vector as a list of numbers.

Returns: On success: {"result": } On error: {"error": }

Examples: >>> vector_cross_product([1, 2, 3], [4, 5, 6]) {'result': [-3, 6, -3]}

Inputs: vector_a (required), vector_b (required).

vector_dot_productA

Computes the dot product of two equal-length vectors.

Args: vector_a: The first vector as a list of numbers. vector_b: The second vector as a list of numbers.

Returns: On success: {"result": } On error: {"error": }

Examples: >>> vector_dot_product([1, 2], [7, 8]) {'result': 23}

Inputs: vector_a (required), vector_b (required).

vector_magnitudeA

Computes the magnitude of a vector.

Args: vector: A vector as a list of numbers.

Returns: On success: {"result": } On error: {"error": }

Examples: >>> vector_magnitude([1, 2, 3]) {'result': 3.7416573867739413}

Inputs: vector (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

A3.5/5.0

Scored 2026-10-20 13:05 across 23 tools

Disambiguation4/5

Each tool targets a distinct mathematical operation (e.g., mean/median/mode, differentiate/integrate, matrix vs vector ops) and names make the difference clear. A few tools all consume symbolic expressions (calculate, expand, factorize, summation, plot_function), which could occasionally cause hesitation, but their outputs and semantics are still distinguishable.

Naming Consistency4/5

All names use lowercase snake_case consistently, which is good. However the convention is not uniformly verb_noun: some are bare operation names (mode, median, calculate, expand) while others are category_operation (matrix_addition, vector_dot_product, correlation_coefficient), so the pattern varies although it stays readable.

Tool Count3/5

23 tools is on the heavy side for a calculator. Each tool covers a genuinely distinct operation and earns its place, but the surface is large enough that some grouping (e.g., a generic matrix tool) or sub-domain organization would improve usability.

Completeness4/5

Coverage is broad across statistics, calculus, symbolic algebra, matrices, vectors, and plotting, with no obvious dead ends for common workflows. Minor gaps exist such as matrix inverse/scalar ops, definite integrals, limits, and systems of equations, but these are workaround-able.

Maintenance

ActivityInactive

ResponsivenessNo recent community issues

Resources

Related MCP Connectors

MathjsA
io.github.pipeworx-io
Math.js MCP — wraps the mathjs.org API (free, no auth)
Developer Tools
462
https://gateway.pipeworx.io/mathjs/mcp
MCPCalcB
com.mcpcalc
MCPCalc gives agents access to a comprehensive library of calculators spanning finance, math, health, construction, engineering, food, automotive, and more. It includes a full Computer Algebra System (CAS) and a grid-based Spreadsheet calculator.
Finance Developer Tools
102
https://mcpcalc.com/api/v1/mcp
Scientific Math Calculator MCP
net.nexlab
Safe scientific calculator MCP for numeric expressions
Developer Tools
1
https://mcp.nexlab.net/mcp/scientific-math-calculator
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
1725
https://math-mcp.fastmcp.app/mcp

Related MCP Servers

Math Calculation MCP Server
Research & Data
K-Summer
A
license
Not graded
quality
D
maintenance
Provides comprehensive mathematical capabilities including basic arithmetic, advanced functions, statistical tools, and access to mathematical constants. It allows users to perform computations and generate math-related prompts through a standardized MCP interface.
Updated 9 months ago (2026-02-18 15:50 UTC)
MIT
Math MCP Server
Data Visualization
amichae2
F
license
C
quality
D
maintenance
Exposes a broad mathematics toolkit including symbolic algebra, calculus, numerical methods, linear algebra, statistics, discrete math, graph theory, rendering, and optional GPU acceleration via MCP tools for use with Claude Desktop and other MCP hosts.
Updated 6 months ago (2026-05-20 02:04 UTC)
51
3
-
calculator-mcp-server
Developer Tools
mvavassori
A
license
Not graded
quality
D
maintenance
Provides a comprehensive set of mathematical functions as MCP tools, enabling language models to perform calculations including arithmetic, trigonometry, logarithms, and more.
Updated a year ago (2025-05-12 14:08 UTC)
10 npm
1
MIT
advanced-math-mcp
PsyWhat
A
license
A
quality
C
maintenance
Enables advanced mathematics operations including linear algebra, vector math, symbolic computation, and calculus through MCP tools. Designed for use with Claude and other MCP-compatible LLMs.
Updated 4 months ago (2026-07-18 02:11 UTC)
19
2
MIT

Mathematical Calculator MCP Server

Features

Installation

Prerequisites

Installation Steps

Integration with Claude Desktop

Method 1: Configure in Claude Desktop

Method 2: Install with the MCP CLI

Usage Examples

Basic Calculations

Solving Equations

Calculating Derivatives

Computing Integrals

Statistical Analysis

Linear Regression

Matrix Operations

Vector Operations

Function Plotting

Development

Testing

Interactive Development Mode

License

Acknowledgements

Available Tools

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

Math Calculation MCP Server

Math MCP Server

calculator-mcp-server

advanced-math-mcp