Summary
Built for teaching math concepts through Claude, this exposes 17 tools split across basic calculations, matrix operations, and matplotlib visualizations. You get persistent workspace storage so students can save and reload their work between sessions, plus structured tutoring prompts and formula explainers. The eval safety model whitelists math module functions only. Includes statistical analysis (mean, median, variance), unit conversions, compound interest calculators, and full matrix ops (multiply, transpose, determinant, eigenvalues). Ships with cloud hosting at math-mcp.fastmcp.app or runs locally via uvx. Designed for educational workflows where you want Claude to walk through problem solving with actual computation and visual output, not just explanation.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Tools
Public tool metadata for what this MCP can expose to an agent.
17 tools
calculateSafely evaluate mathematical expressions with support for basic operations and math functions. Supported operations: +, -, *, /, **, () Supported functions: sin, cos, tan, log, sqrt, abs, pow Note: Use this tool to evaluate a single mathematical expression. To compute descript...1 params
Safely evaluate mathematical expressions with support for basic operations and math functions. Supported operations: +, -, *, /, **, () Supported functions: sin, cos, tan, log, sqrt, abs, pow Note: Use this tool to evaluate a single mathematical expression. To compute descript...
Parameters* required
expressionstringMathematical expression to evaluate. Supports +, -, *, /, **, and math functions (sin, cos, sqrt, log, etc.). Example: '2 * sin(pi/4) + sqrt(16)'
statisticsPerform statistical calculations on a list of numbers. Available operations: mean, median, mode, std_dev, variance Note: Use this tool to compute descriptive statistics over a list of numbers. To evaluate a single mathematical expression, use the calculate tool instead. Exampl...2 params
Perform statistical calculations on a list of numbers. Available operations: mean, median, mode, std_dev, variance Note: Use this tool to compute descriptive statistics over a list of numbers. To evaluate a single mathematical expression, use the calculate tool instead. Exampl...
Parameters* required
numbersarrayList of numbers to compute descriptive statistics on. Example: [1.0, 2.5, 3.0, 4.5, 5.0]
operationstringStatistical operation to perform. Allowed values: mean, median, mode, std_dev, variance
compound_interestCalculate compound interest for investments. Formula: A = P(1 + r/n)^(nt) Where: - P = principal amount - r = annual interest rate (as decimal) - n = number of times interest compounds per year - t = time in years Examples: compound_interest(10000, 0.05, 5) # $10,000 at 5% for...4 params
Calculate compound interest for investments. Formula: A = P(1 + r/n)^(nt) Where: - P = principal amount - r = annual interest rate (as decimal) - n = number of times interest compounds per year - t = time in years Examples: compound_interest(10000, 0.05, 5) # $10,000 at 5% for...
Parameters* required
ratenumberAnnual interest rate as decimal between 0.0 and 1.0. Example: 0.05 for 5%
timenumberTime period in years, must be greater than 0. Example: 10
principalnumberInitial investment amount, must be greater than 0. Example: 1000.0
compounds_per_yearintegerCompounding frequency per year, must be >= 1. Example: 12 for monthlydefault: 1
convert_unitsConvert between different units of measurement. Supported unit types: - length: mm, cm, m, km, in, ft, yd, mi - weight: g, kg, oz, lb - temperature: c, f, k (Celsius, Fahrenheit, Kelvin) Examples: convert_units(5, "km", "mi", "length") # 5 kilometers → 3.11 miles convert_units...4 params
Convert between different units of measurement. Supported unit types: - length: mm, cm, m, km, in, ft, yd, mi - weight: g, kg, oz, lb - temperature: c, f, k (Celsius, Fahrenheit, Kelvin) Examples: convert_units(5, "km", "mi", "length") # 5 kilometers → 3.11 miles convert_units...
Parameters* required
valuenumberNumeric value to convert, e.g., 100.0
to_unitstringTarget unit abbreviation. Valid units depend on unit_type: length (mm, cm, m, km, in, ft, yd, mi), weight (g, kg, oz, lb), temperature (c, f, k)
from_unitstringSource unit abbreviation. Valid units depend on unit_type: length (mm, cm, m, km, in, ft, yd, mi), weight (g, kg, oz, lb), temperature (c, f, k)
unit_typestringUnit category: length, weight, or temperature
matrix_multiplyMultiply two matrices (A × B). Args: matrix_a: First matrix (m x n) matrix_b: Second matrix (n x p) Note: Requires NumPy. Raises ValueError if NumPy is unavailable. Examples: matrix_multiply([[1, 2], [3, 4]], [[5, 6], [7, 8]]) matrix_multiply([[1, 2, 3]], [[1], [2], [3]])2 params
Multiply two matrices (A × B). Args: matrix_a: First matrix (m x n) matrix_b: Second matrix (n x p) Note: Requires NumPy. Raises ValueError if NumPy is unavailable. Examples: matrix_multiply([[1, 2], [3, 4]], [[5, 6], [7, 8]]) matrix_multiply([[1, 2, 3]], [[1], [2], [3]])
Parameters* required
matrix_aarray2D list of numbers representing the first matrix. Each inner list is a row. Example: [[1, 2], [3, 4]]
matrix_barray2D list of numbers representing the second matrix. Each inner list is a row. Example: [[5, 6], [7, 8]]
matrix_transposeTranspose a matrix (swap rows and columns). Args: matrix: Input matrix (m x n) Note: Requires NumPy. Raises ValueError if NumPy is unavailable. Examples: matrix_transpose([[1, 2, 3], [4, 5, 6]]) matrix_transpose([[1], [2], [3]])1 params
Transpose a matrix (swap rows and columns). Args: matrix: Input matrix (m x n) Note: Requires NumPy. Raises ValueError if NumPy is unavailable. Examples: matrix_transpose([[1, 2, 3], [4, 5, 6]]) matrix_transpose([[1], [2], [3]])
Parameters* required
matrixarray2D list of numbers representing the matrix. Each inner list is a row. Example: [[1, 2, 3], [4, 5, 6]]
matrix_determinantCalculate the determinant of a square matrix. Args: matrix: Square matrix (n x n) Note: Requires NumPy. Raises ValueError if NumPy is unavailable. Examples: matrix_determinant([[1, 2], [3, 4]]) matrix_determinant([[1, 0, 0], [0, 1, 0], [0, 0, 1]]) # Identity matrix1 params
Calculate the determinant of a square matrix. Args: matrix: Square matrix (n x n) Note: Requires NumPy. Raises ValueError if NumPy is unavailable. Examples: matrix_determinant([[1, 2], [3, 4]]) matrix_determinant([[1, 0, 0], [0, 1, 0], [0, 0, 1]]) # Identity matrix
Parameters* required
matrixarray2D list of numbers representing a square matrix. Each inner list is a row. Example: [[1, 2], [3, 4]]
matrix_inverseCalculate the inverse of a square matrix. Args: matrix: Square matrix (n x n) Note: Requires NumPy. Raises ValueError if NumPy is unavailable. Examples: matrix_inverse([[1, 2], [3, 4]]) matrix_inverse([[2, 0], [0, 2]]) # Diagonal matrix1 params
Calculate the inverse of a square matrix. Args: matrix: Square matrix (n x n) Note: Requires NumPy. Raises ValueError if NumPy is unavailable. Examples: matrix_inverse([[1, 2], [3, 4]]) matrix_inverse([[2, 0], [0, 2]]) # Diagonal matrix
Parameters* required
matrixarray2D list of numbers representing a square matrix. Each inner list is a row. Example: [[1, 2], [3, 4]]
matrix_eigenvaluesCalculate the eigenvalues of a square matrix. Args: matrix: Square matrix (n x n) Note: Requires NumPy. Raises ValueError if NumPy is unavailable. Examples: matrix_eigenvalues([[4, 2], [1, 3]]) matrix_eigenvalues([[3, 0, 0], [0, 5, 0], [0, 0, 7]]) # Diagonal matrix1 params
Calculate the eigenvalues of a square matrix. Args: matrix: Square matrix (n x n) Note: Requires NumPy. Raises ValueError if NumPy is unavailable. Examples: matrix_eigenvalues([[4, 2], [1, 3]]) matrix_eigenvalues([[3, 0, 0], [0, 5, 0], [0, 0, 7]]) # Diagonal matrix
Parameters* required
matrixarray2D list of numbers representing a square matrix. Each inner list is a row. Example: [[4, 2], [1, 3]]
save_calculationSave calculation to persistent workspace (survives restarts). Examples: save_calculation("portfolio_return", "10000 * 1.07^5", 14025.52) save_calculation("circle_area", "pi * 5^2", 78.54)3 params
Save calculation to persistent workspace (survives restarts). Examples: save_calculation("portfolio_return", "10000 * 1.07^5", 14025.52) save_calculation("circle_area", "pi * 5^2", 78.54)
Parameters* required
namestringVariable name for the saved calculation. Used to retrieve it later. Example: 'circle_area'
resultnumberNumeric result of evaluating the expression, e.g., 78.54
expressionstringThe mathematical expression that was evaluated. Example: 'pi * r**2'
load_variableLoad previously saved calculation result from workspace. Examples: load_variable("portfolio_return") # Returns saved calculation load_variable("circle_area") # Access across sessions1 params
Load previously saved calculation result from workspace. Examples: load_variable("portfolio_return") # Returns saved calculation load_variable("circle_area") # Access across sessions
Parameters* required
namestringName of the variable to load from workspace, e.g., 'circle_area'
plot_functionGenerate mathematical function plots (requires matplotlib). Args: expression: Mathematical expression to plot (e.g., "x**2", "sin(x)") x_range: Tuple of (min, max) for x-axis range num_points: Number of points to plot (default: 100) ctx: FastMCP context for logging Examples: p...3 params
Generate mathematical function plots (requires matplotlib). Args: expression: Mathematical expression to plot (e.g., "x**2", "sin(x)") x_range: Tuple of (min, max) for x-axis range num_points: Number of points to plot (default: 100) ctx: FastMCP context for logging Examples: p...
Parameters* required
x_rangearrayX-axis range as (min, max), e.g., (-5.0, 5.0)
expressionstringMathematical expression to plot, e.g., "x**2" or "sin(x)". Must be <= MAX_EXPRESSION_LENGTH characters. Example: "x**2"
num_pointsintegerNumber of sample points to plot along x_range, e.g., 100default: 100
create_histogramCreate statistical histograms (requires matplotlib). Args: data: List of numerical values bins: Number of histogram bins (default: 20) title: Chart title ctx: FastMCP context for logging Examples: create_histogram([1.0, 2.0, 2.5, 3.0, 3.5, 4.0, 5.0]) create_histogram([10, 20,...3 params
Create statistical histograms (requires matplotlib). Args: data: List of numerical values bins: Number of histogram bins (default: 20) title: Chart title ctx: FastMCP context for logging Examples: create_histogram([1.0, 2.0, 2.5, 3.0, 3.5, 4.0, 5.0]) create_histogram([10, 20,...
Parameters* required
binsintegerNumber of histogram bins, e.g., 20default: 20
dataarrayList of numeric values to bin, e.g., [1.0, 2.0, 2.5, 3.0]
titlestringChart title string, e.g., 'Data Distribution'default: Data Distribution
plot_line_chartCreate a line chart from data points (requires matplotlib). Args: x_data: X-axis data points y_data: Y-axis data points title: Chart title x_label: X-axis label y_label: Y-axis label color: Line color (name or hex code, e.g., 'blue', '#2E86AB') show_grid: Whether to show grid...7 params
Create a line chart from data points (requires matplotlib). Args: x_data: X-axis data points y_data: Y-axis data points title: Chart title x_label: X-axis label y_label: Y-axis label color: Line color (name or hex code, e.g., 'blue', '#2E86AB') show_grid: Whether to show grid...
Parameters* required
colorvalueLine color (name or hex code, e.g., 'blue', '#2E86AB')
titlestringChart title string, e.g., 'Squares'default: Line Chart
x_dataarrayX-axis data points, e.g., [1, 2, 3, 4]
y_dataarrayY-axis data points, e.g., [1, 4, 9, 16]
x_labelstringX-axis label, e.g., 'Time'default: X
y_labelstringY-axis label, e.g., 'Distance'default: Y
show_gridbooleanWhether to display grid linesdefault: true
plot_scatter_chartCreate a scatter plot from data points (requires matplotlib). Args: x_data: X-axis data points y_data: Y-axis data points title: Chart title x_label: X-axis label y_label: Y-axis label color: Point color (name or hex code, e.g., 'blue', '#2E86AB') point_size: Size of scatter p...7 params
Create a scatter plot from data points (requires matplotlib). Args: x_data: X-axis data points y_data: Y-axis data points title: Chart title x_label: X-axis label y_label: Y-axis label color: Point color (name or hex code, e.g., 'blue', '#2E86AB') point_size: Size of scatter p...
Parameters* required
colorvaluePoint color (name or hex code, e.g., 'blue', '#2E86AB')
titlestringChart title string, e.g., 'Correlation Study'default: Scatter Plot
x_dataarrayX-axis data points, e.g., [1, 2, 3, 4]
y_dataarrayY-axis data points, e.g., [1, 4, 9, 16]
x_labelstringX-axis label, e.g., 'Variable X'default: X
y_labelstringY-axis label, e.g., 'Variable Y'default: Y
point_sizeintegerScatter point size in points^2, e.g., 50default: 50
plot_box_plotCreate a box plot for comparing distributions (requires matplotlib). Args: data_groups: List of data groups to compare group_labels: Optional labels for each group title: Chart title y_label: Y-axis label color: Box color (name or hex code, e.g., 'blue', '#2E86AB') ctx: FastMC...5 params
Create a box plot for comparing distributions (requires matplotlib). Args: data_groups: List of data groups to compare group_labels: Optional labels for each group title: Chart title y_label: Y-axis label color: Box color (name or hex code, e.g., 'blue', '#2E86AB') ctx: FastMC...
Parameters* required
colorvalueBox color (name or hex code, e.g., 'blue', '#2E86AB')
titlestringChart title string, e.g., 'Distribution Comparison'default: Box Plot
y_labelstringY-axis label, e.g., 'Values'default: Values
data_groupsarrayList of data groups to compare, e.g., [[1, 2, 3], [4, 5, 6]]
group_labelsvalueLabels for each group, e.g., ['Group A', 'Group B']
plot_financial_lineGenerate and plot synthetic financial price data (requires matplotlib). Creates realistic price movement patterns for educational purposes. Does not use real market data. Args: days: Number of days to generate (default: 30) trend: Market trend ('bullish', 'bearish', or 'volati...4 params
Generate and plot synthetic financial price data (requires matplotlib). Creates realistic price movement patterns for educational purposes. Does not use real market data. Args: days: Number of days to generate (default: 30) trend: Market trend ('bullish', 'bearish', or 'volati...
Parameters* required
daysintegerNumber of days to generate, e.g., 30default: 30
colorvalueLine color (name or hex code, e.g., 'blue', '#2E86AB')
trendstringMarket trend directiondefault: bullish
start_pricenumberStarting price value, e.g., 100.0default: 100
math-mcp-learning-server
Educational MCP server with 17 tools, persistent workspace, and cloud hosting. Built with FastMCP and the official Model Context Protocol Python SDK.
Available on the MCP Registry (io.github.clouatre-labs/math-mcp-learning-server) and PyPI.
Demo
See CONTRIBUTING.md for instructions to record your own demo.
Quick Start
Cloud (No Installation)
Connect your MCP client to the hosted server:
Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"math-cloud": {
"transport": "http",
"url": "https://math-mcp.fastmcp.app/mcp"
}
}
}
Local Installation
{
"mcpServers": {
"math": {
"command": "uvx",
"args": ["math-mcp-learning-server[scientific,plotting]"]
}
}
}
For other installation options (basic, scientific-only, plotting-only), see CONTRIBUTING.md.
Tools
| Category | Tool | Description |
|---|---|---|
| Workspace | workspace_save | Save calculations to persistent storage |
workspace_load | Retrieve previously saved calculations | |
| Math | calc_expression | Safely evaluate mathematical expressions |
calc_statistics | Statistical analysis (mean, median, mode, std_dev, variance) | |
calc_interest | Calculate compound interest for investments | |
calc_units | Convert between units (length, weight, temperature) | |
| Matrix | matrix_multiply | Multiply two matrices |
matrix_transpose | Transpose a matrix | |
matrix_determinant | Calculate matrix determinant | |
matrix_inverse | Calculate matrix inverse | |
matrix_eigenvalues | Calculate eigenvalues | |
| Visualization | plot_function | Plot mathematical functions |
plot_histogram | Create statistical histograms | |
plot_line_chart | Create line charts | |
plot_scatter | Create scatter plots | |
plot_box_plot | Create box plots | |
plot_financial_line | Create financial line charts |
Resources
math://workspace- Persistent calculation workspace summarymath://history- Chronological calculation historymath://functions- Available mathematical functions referencemath://constants/{constant}- Mathematical constants (pi, e, golden_ratio, etc.)math://catalog/tools- Tool catalog with metadata and usage examplesmath://variables- Active variables in the current workspacemath://test- Server health check
Prompts
math_tutor- Structured tutoring prompts (configurable difficulty)formula_explainer- Formula explanation with step-by-step breakdowns
See Usage Examples for detailed examples.
Development
See CONTRIBUTING.md for development setup, testing, and contribution guidelines.
Security
- OpenSSF Best Practices Silver - Fewer than 1% of open source projects reach this level
- REUSE/SPDX - License compliance for all files
- Signed Commits - GPG-signed commits required
- Dependency Scanning - Automated updates via Renovate
- pip-audit CVE Scanning - Automated dependency vulnerability checks
- gitleaks Secret Scanning - Detects secrets in code and history
- zizmor GitHub Actions Security - Workflow security scanning
- commitlint Enforcement - Conventional commit validation in CI
- OpenSSF Scorecard - Continuous open source security assessment
calc_expression safety
The calc_expression tool uses restricted eval() with a whitelist of allowed characters and functions, restricted global scope (only math module and abs), and no access to dangerous built-ins or imports. All tool inputs are validated with Pydantic models. File operations are restricted to the designated workspace directory. Complete type hints and validation are enforced for all operations.
Documentation
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →