Brings NumPy's entire numerical computing toolkit into Claude through MCP. You get all the essentials: array creation (zeros, ones, arange, linspace), manipulation (reshape, transpose, concatenate), mathematical operations (sum, mean, dot, matmul), linear algebra (inv, det, eig, svd), and random number generation. Also exposes element-wise operations like trig functions, logarithms, and arithmetic, plus statistics tools like percentile, histogram, and correlation. Install via pip, add the command to your MCP config, and you can start running matrix operations, solving linear systems, or computing eigenvalues without spinning up a separate Python environment. Solid choice when you need numerical computation without leaving your Claude workflow.
An MCP server that exposes NumPy functionality
pip install mcp-numpy
To use with Claude Desktop or other MCP clients, add to your mcp.json:
{
"mcpServers": {
"mcp-numpy": {
"command": "mcp-numpy"
}
}
}
The server exposes the following NumPy functionality as MCP tools:
np_array - Create a NumPy arraynp_zeros - Create zeros arraynp_ones - Create ones arraynp_full - Create array filled with valuenp_arange - Create array with rangenp_linspace - Create evenly spaced arraynp_eye - Create identity matrixnp_diag - Create diagonal arraynp_reshape - Reshape arraynp_transpose - Transpose arraynp_concatenate - Concatenate arraysnp_split - Split arraynp_tile - Tile arraynp_repeat - Repeat elementsnp_squeeze - Remove single-dimensional entriesnp_flatten - Flatten arraynp_sum, np_mean, np_std, np_var - Summary statisticsnp_min, np_max, np_argmin, np_argmax - Min/max operationsnp_dot, np_matmul, np_cross - Matrix operationsnp_trace, np_cumsum, np_cumprod, np_diff - Array operationsnp_inv - Matrix inversenp_det - Matrix determinantnp_eig - Eigenvalues and eigenvectorsnp_svd - Singular value decompositionnp_solve - Solve linear systemnp_linalg_norm - Matrix/vector normnp_rand - Random floatsnp_randn - Random normalnp_randint - Random integersnp_random_choice - Random choicenp_shuffle - Shuffle arraynp_percentile, np_quantile - Percentiles/quantilesnp_histogram - Histogramnp_correlate, np_corrcoef - Correlationnp_add, np_subtract, np_multiply, np_divide - Arithmeticnp_power, np_mod - Power and modulonp_sqrt, np_abs - Basic mathnp_exp, np_log, np_log10 - Logarithmsnp_sin, np_cos, np_tan - Trigonometrynp_arcsin, np_arccos, np_arctan - Inverse trignp_sinh, np_cosh, np_tanh - Hyperbolicnp_shape, np_ndim, np_size, np_dtype - Propertiesnpastype - Type conversiongit clone https://github.com/daedalus/mcp-numpy.git
cd mcp-numpy
pip install -e ".[test]"
# run tests
pytest
# format
ruff format src/ tests/
# lint
ruff check src/ tests/
# type check
mypy src/
mcp-name: io.github.daedalus/mcp-numpy