{
  "markdown": "# mcp-numpy\n\n> An MCP server that exposes NumPy functionality\n\n[![PyPI](https://img.shields.io/pypi/v/mcp-numpy.svg)](https://pypi.org/project/mcp-numpy/)\n[![Python](https://img.shields.io/pypi/pyversions/mcp-numpy.svg)](https://pypi.org/project/mcp-numpy/)\n[![Coverage](https://codecov.io/gh/daedalus/mcp-numpy/branch/main/graph/badge.svg)](https://codecov.io/gh/daedalus/mcp-numpy)\n[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)\n\n## Install\n\n```bash\npip install mcp-numpy\n```\n\n## Usage\n\n### As an MCP Server\n\nTo use with Claude Desktop or other MCP clients, add to your `mcp.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"mcp-numpy\": {\n      \"command\": \"mcp-numpy\"\n    }\n  }\n}\n```\n\n### Available Tools\n\nThe server exposes the following NumPy functionality as MCP tools:\n\n#### Array Creation\n- `np_array` - Create a NumPy array\n- `np_zeros` - Create zeros array\n- `np_ones` - Create ones array\n- `np_full` - Create array filled with value\n- `np_arange` - Create array with range\n- `np_linspace` - Create evenly spaced array\n- `np_eye` - Create identity matrix\n- `np_diag` - Create diagonal array\n\n#### Array Manipulation\n- `np_reshape` - Reshape array\n- `np_transpose` - Transpose array\n- `np_concatenate` - Concatenate arrays\n- `np_split` - Split array\n- `np_tile` - Tile array\n- `np_repeat` - Repeat elements\n- `np_squeeze` - Remove single-dimensional entries\n- `np_flatten` - Flatten array\n\n#### Mathematical Operations\n- `np_sum`, `np_mean`, `np_std`, `np_var` - Summary statistics\n- `np_min`, `np_max`, `np_argmin`, `np_argmax` - Min/max operations\n- `np_dot`, `np_matmul`, `np_cross` - Matrix operations\n- `np_trace`, `np_cumsum`, `np_cumprod`, `np_diff` - Array operations\n\n#### Linear Algebra\n- `np_inv` - Matrix inverse\n- `np_det` - Matrix determinant\n- `np_eig` - Eigenvalues and eigenvectors\n- `np_svd` - Singular value decomposition\n- `np_solve` - Solve linear system\n- `np_linalg_norm` - Matrix/vector norm\n\n#### Random\n- `np_rand` - Random floats\n- `np_randn` - Random normal\n- `np_randint` - Random integers\n- `np_random_choice` - Random choice\n- `np_shuffle` - Shuffle array\n\n#### Statistics\n- `np_percentile`, `np_quantile` - Percentiles/quantiles\n- `np_histogram` - Histogram\n- `np_correlate`, `np_corrcoef` - Correlation\n\n#### Element-wise Math\n- `np_add`, `np_subtract`, `np_multiply`, `np_divide` - Arithmetic\n- `np_power`, `np_mod` - Power and modulo\n- `np_sqrt`, `np_abs` - Basic math\n- `np_exp`, `np_log`, `np_log10` - Logarithms\n- `np_sin`, `np_cos`, `np_tan` - Trigonometry\n- `np_arcsin`, `np_arccos`, `np_arctan` - Inverse trig\n- `np_sinh`, `np_cosh`, `np_tanh` - Hyperbolic\n\n#### Array Properties\n- `np_shape`, `np_ndim`, `np_size`, `np_dtype` - Properties\n- `npastype` - Type conversion\n\n## Development\n\n```bash\ngit clone https://github.com/daedalus/mcp-numpy.git\ncd mcp-numpy\npip install -e \".[test]\"\n\n# run tests\npytest\n\n# format\nruff format src/ tests/\n\n# lint\nruff check src/ tests/\n\n# type check\nmypy src/\n```\n\nmcp-name: io.github.daedalus/mcp-numpy\n",
  "bytes": 3089,
  "sha": "b370ae4ba36570a83ab4203cbcbfa68c366a93356007f37d8f009671bba84627",
  "repo_slug": "daedalus/mcp-numpy",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_daedalus_mcp_numpy_42ff7448/readme"
}