mcp-numpy

> An MCP server that exposes NumPy functionality

[](https://pypi.org/project/mcp-numpy/) [](https://pypi.org/project/mcp-numpy/) [](https://codecov.io/gh/daedalus/mcp-numpy) [](https://github.com/astral-sh/ruff)

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 array
• np_zeros - Create zeros array
• np_ones - Create ones array
• np_full - Create array filled with value
• np_arange - Create array with range
• np_linspace - Create evenly spaced array
• np_eye - Create identity matrix
• np_diag - Create diagonal array

• np_reshape - Reshape array
• np_transpose - Transpose array
• np_concatenate - Concatenate arrays
• np_split - Split array
• np_tile - Tile array
• np_repeat - Repeat elements
• np_squeeze - Remove single-dimensional entries
• np_flatten - Flatten array

• np_sum, np_mean, np_std, np_var - Summary statistics
• np_min, np_max, np_argmin, np_argmax - Min/max operations
• np_dot, np_matmul, np_cross - Matrix operations
• np_trace, np_cumsum, np_cumprod, np_diff - Array operations

• np_inv - Matrix inverse
• np_det - Matrix determinant
• np_eig - Eigenvalues and eigenvectors
• np_svd - Singular value decomposition
• np_solve - Solve linear system
• `np_linalg_no