Numpy MCP server

Read from the package source without running it. The installed server may list more.

• np_abs

  Calculate the absolute value of array elements.

• np_add

  Element-wise addition of two arrays.

• np_arangewrite action

  Create an array with evenly spaced values within a given interval.

• np_arccos

  Inverse cosine, element-wise.

• np_arcsin

  Inverse sine, element-wise.

• np_arctan

  Inverse tangent, element-wise.

• np_argmax

  Return the indices of the maximum values along an axis.

• np_argmin

  Return the indices of the minimum values along an axis.

• np_arraywrite action

  Create a NumPy array from a list.

• np_concatenate

  Join a sequence of arrays along an existing axis.

• np_corrcoef

  Return Pearson product-moment correlation coefficients.

• np_correlate

  Cross-correlation of two 1-dimensional sequences.

• np_cos

  Trigonometric cosine, element-wise.

• np_cosh

  Hyperbolic cosine, element-wise.

• np_cross

  Compute the cross product of two arrays.

• np_cumprod

  Return the cumulative product of the array along a given axis.

• np_cumsum

  Return the cumulative sum of the array along a given axis.

• np_det

  Compute the determinant of an array.

• np_diagwrite action

  Create a diagonal array or extract the diagonal of an array.

• np_diff

  Calculate the n-th discrete difference along the given axis.

• np_divide

  Element-wise division of two arrays.

• np_dot

  Compute the dot product of two arrays.

• np_dtype

  Return the dtype of an array.

• np_eig

  Compute the eigenvalues and eigenvectors of a square array.

• np_exp

  Calculate the exponential of all elements in the array.

• np_eye

  Return a 2D identity array.

• np_flatten

  Return a flattened copy of the array.

• np_fullwrite action

  Create an array filled with a constant value.

• np_histogram

  Compute the histogram of a set of data.

• np_inv

  Compute the (multiplicative) inverse of a matrix.

• np_linalg_norm

  Matrix or vector norm.

• np_linspacewrite action

  Create an array with evenly spaced numbers over a specified interval.

• np_log

  Natural logarithm, element-wise.

• np_log10

  Base-10 logarithm, element-wise.

• np_matmul

  Matrix product of two arrays.

• np_max

  Return the maximum of an array or maximum along an axis.

• np_mean

  Compute the arithmetic mean along the specified axis.

• np_min

  Return the minimum of an array or minimum along an axis.

• np_mod

  Element-wise modulo of two arrays.

• np_multiply

  Element-wise multiplication of two arrays.

• np_ndim

  Return the number of dimensions of an array.

• np_oneswrite action

  Create an array of ones.

• np_percentile

  Compute the q-th percentile of the array elements.

• np_power

  Element-wise exponentiation of array elements.

• np_quantile

  Compute the q-th quantile of the array elements.

• np_rand

  Random values in a given shape.

• np_randint

  Return random integers from low (inclusive) to high (exclusive).

• np_randn

  Return a sample (or samples) from the "standard normal" distribution.

• np_random_choice

  Generates a random sample from a given array.

• np_repeat

  Repeat elements of an array.

• np_reshape

  Give a new shape to an array without changing its data.

• np_shape

  Return the shape of an array.

• np_shuffle

  Modify a sequence in-place by shuffling its contents.

• np_sin

  Trigonometric sine, element-wise.

• np_sinh

  Hyperbolic sine, element-wise.

• np_size

  Return the total number of elements in an array.

• np_solve

  Solve a linear matrix equation, or system of linear equations.

• np_split

  Split an array into multiple sub-arrays.

• np_sqrt

  Return the non-negative square root of an array element-wise.

• np_squeezewrite action

  Remove single-dimensional entries from the shape of an array.

• np_std

  Compute the standard deviation along the specified axis.

• np_subtract

  Element-wise subtraction of two arrays.

• np_sum

  Sum of array elements over given axis(es).

• np_svd

  Singular Value Decomposition.

• np_tan

  Trigonometric tangent, element-wise.

• np_tanh

  Hyperbolic tangent, element-wise.

• np_tile

  Construct an array by repeating the input array the given number of times.

• np_trace

  Return the sum along the main diagonal of the array.

• np_transpose

  Reverse or permute the axes of an array.

• np_var

  Compute the variance along the specified axis.

• np_zeroswrite action

  Create an array of zeros.

• npastype

  Copy of the array, cast to a specified type.

• Code scan4 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitylocal package, no credentials required12/15
• Maintenancelast push 159 days ago8/15
• Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Safety score

82/100

higher than 63% of 48,273 servers

Tools

72

the typical server has 7

Tools that change things

11%

typical: 0%. Fewer write tools means less an agent can break

Downloads a week

14

more than 4% of 11,915 servers with a package

Numpy: common questions

Is Numpy MCP server safe?

Mostly: it is graded B (82/100). Read the Numpy safety report

How do I install Numpy?

It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.

Does Numpy need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is Numpy maintained?

The last commit was 195 days ago (2026-04-21). The latest release is v0.1.0.

How does Numpy compare with other MCP servers?

safety score 82/100 (higher than 63% of 48,273 servers); tools 72 (the typical server has 7); tools that change things 11% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.