MCP SERVER · OFFICIAL PROJECTEvaluate expressions, run matrix algebra and draw charts from the conversation — and save a result under a name so the next session can load it back.
LABSCO SUMMARY
Routing calculation to a tool removes a familiar failure: the numbers come from an evaluator rather than from a language model's arithmetic, and the workspace keeps a named result available across sessions rather than in the transcript. Install the scientific and plotting extras if you want the matrix and chart tools at all — without NumPy and matplotlib those calls raise. One tool to read carefully: the financial line chart generates synthetic price movement for teaching, not real market data.
A maths and plotting toolkit with a workspace that persists. Expressions, statistics, unit conversion and linear algebra return numbers; the plot tools return images; saved calculations survive a restart under the name you gave them.
Nothing to authorize. Hosted over Streamable HTTP at https://math-mcp.fastmcp.app/mcp for zero install, or locally over stdio as uvx math-mcp-learning-server[scientific,plotting] — those two extras are what bring in the dependencies the optional tools need, since the matrix tools require NumPy and every plot tool requires matplotlib, and they raise rather than degrade without them. Apache-2.0.
One command — uvx "math-mcp-learning-server[scientific,plotting]"
USE CASES
Send the expression to an evaluator and get the value back, then run descriptive statistics over a data set without transcribing it anywhere.
Compute compound interest from principal, rate, term and compounding frequency, and save the result under a name you will recognise later.
Multiply or transpose matrices, and get the determinant, inverse or eigenvalues of a square one.
Draw a histogram of the distribution, or box plots side by side when the question is how several groups compare.
Plot the function over a range, or chart the x and y data as a line or scatter with axis labels and a title.
Load the saved result by name; the workspace outlives the server restart, so the figure does not have to be recomputed or re-pasted.
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
calc_expressionSafely 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 descriptive statistics over a list of numbers, use the statistics tool instead.
Examples:
calc_interestCalculate compound interest for investments.
Formula: A = P(1 + r/n)^(nt) Where:
Examples: compound_interest(10000, 0.05, 5) # $10,000 at 5% for 5 years → $12,762.82 compound_interest(5000, 0.03, 10, 12) # $5,000 at 3% compounded monthly → $6,744.25
calc_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.
Examples: statistics([1.0, 2.5, 3.0, 4.5, 5.0], "mean") # Returns 3.2 statistics([1.0, 2.5, 3.0, 4.5, 5.0], "std_dev") # Returns ~1.58
calc_unitsConvert between different units of measurement.
Supported unit types:
Examples: convert_units(5, "km", "mi", "length") # 5 kilometers → 3.11 miles convert_units(150, "lb", "kg", "weight") # 150 pounds → 68.04 kilograms
matrix_determinantCalculate the determinant of a square matrix.
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
matrix_eigenvaluesCalculate the eigenvalues of a square matrix.
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
matrix_inverseCalculate the inverse of a square matrix.
Note: Requires NumPy. Raises ValueError if NumPy is unavailable.
Examples: matrix_inverse([[1, 2], [3, 4]]) matrix_inverse([[2, 0], [0, 2]]) # Diagonal matrix
matrix_multiplyMultiply two matrices (A × B).
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]])
matrix_transposeTranspose a matrix (swap rows and columns).
Note: Requires NumPy. Raises ValueError if NumPy is unavailable.
Examples: matrix_transpose([[1, 2, 3], [4, 5, 6]]) matrix_transpose([[1], [2], [3]])
plot_box_plotCreate a box plot for comparing distributions (requires matplotlib).
Examples: plot_box_plot([[1, 2, 3, 4, 5], [2, 4, 6, 8, 10]], group_labels=["A", "B"]) plot_box_plot([[10, 20, 30], [15, 25, 35], [5, 15, 25]], title="Comparison")
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.
Note: Use for time-series price data with optional moving average overlay. For general XY data, use plot_line_chart instead.
Examples: plot_financial_line(days=60, trend='bullish') plot_financial_line(days=90, trend='volatile', start_price=150.0, color='orange')
plot_functionGenerate mathematical function plots (requires matplotlib).
Examples: plot_function("x**2", (-5, 5)) plot_function("sin(x)", (-3.14, 3.14))
plot_histogramCreate statistical histograms (requires matplotlib).
Examples: plot_histogram([1.0, 2.0, 2.5, 3.0, 3.5, 4.0, 5.0]) plot_histogram([10, 20, 30, 40, 50], bins=5, title="Test Scores")
plot_line_chartCreate a line chart from data points (requires matplotlib).
Note: Use for general XY data. For time-series price data with optional moving average, use plot_financial_line instead.
Examples: plot_line_chart([1, 2, 3, 4], [1, 4, 9, 16], title="Squares") plot_line_chart([0, 1, 2], [0, 1, 4], color='red', x_label='Time', y_label='Distance')
plot_scatterCreate a scatter plot from data points (requires matplotlib).
Examples: plot_scatter([1, 2, 3, 4], [1, 4, 9, 16], title="Correlation Study") plot_scatter([1, 2, 3], [2, 4, 5], color='purple', point_size=100)
workspace_loadLoad previously saved calculation result from workspace.
Examples: load_variable("portfolio_return") # Returns saved calculation load_variable("circle_area") # Access across sessions
workspace_saveSave 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)
BEFORE YOU INSTALL
17 tools when we connected. The documented install includes the scientific and plotting extras; a bare install of math-mcp-learning-server may not expose all 17.
uvx on PATH
CONTEXT COST
Rated by the size of the 17 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
uvx "math-mcp-learning-server[scientific,plotting]"https://math-mcp.fastmcp.app/mcpAdd this hosted endpoint to your MCP client.
MCP servers
HeetVekariya
manasp21
HarperZ9
Garoth