
Aman Amith Shastry Scientific Computation Mcp
A NumPy-backed server that gives Claude linear algebra and vector calculus operations through a tensor store. You create named matrices and vectors, then run operations like matrix multiplication, QR decomposition, SVD, eigenvalue computation, and basis transformations. The vector calculus tools compute gradients, curls, divergence, and directional derivatives from string expressions, plus there are plotting functions for 2D/3D visualization of vector fields and scalar functions. Good fit when you need symbolic and numerical computation without leaving the chat, especially for educational workflows or quick prototyping of linear transformations. Runs through Smithery's hosted infrastructure, so setup is just dropping config into Claude Desktop.
- GitHub stars
- 2
- tools
- 26
- auth
- Secret needed
- transport
- HTTP
- last updated
- Sep 12, 2025
Tools
26 toolsPublic tool metadata for what this MCP can expose to an agent.
create_tensorCreates a new tensor based on a given name, shape, and values, and adds it to the tensor store.
Creates a new tensor based on a given name, shape, and values, and adds it to the tensor store.
No parameter schema in public metadata yet.
view_tensorDisplay the contents of a tensor from the store .
Display the contents of a tensor from the store .
No parameter schema in public metadata yet.
delete_tensorDeletes a tensor based on its name in the tensor store.
Deletes a tensor based on its name in the tensor store.
No parameter schema in public metadata yet.
add_matricesAdds two matrices with the provided names, if compatible.
Adds two matrices with the provided names, if compatible.
No parameter schema in public metadata yet.
subtract_matricesSubtracts two matrices with the provided names, if compatible.
Subtracts two matrices with the provided names, if compatible.
No parameter schema in public metadata yet.
multiply_matricesMultiplies two matrices with the provided names, if compatible.
Multiplies two matrices with the provided names, if compatible.
No parameter schema in public metadata yet.
scale_matrixScales a matrix of the provided name by a certain factor, in-place by default.
Scales a matrix of the provided name by a certain factor, in-place by default.
No parameter schema in public metadata yet.
matrix_inverseComputes the inverse of the matrix with the provided name.
Computes the inverse of the matrix with the provided name.
No parameter schema in public metadata yet.
transposeComputes the transpose of the inverse of the matrix of the provided name.
Computes the transpose of the inverse of the matrix of the provided name.
No parameter schema in public metadata yet.
determinantComputes the determinant of the matrix of the provided name.
Computes the determinant of the matrix of the provided name.
No parameter schema in public metadata yet.
rankComputes the rank (number of pivots) of the matrix of the provided name.
Computes the rank (number of pivots) of the matrix of the provided name.
No parameter schema in public metadata yet.
compute_eigenCalculates the eigenvectors and eigenvalues of the matrix of the provided name.
Calculates the eigenvectors and eigenvalues of the matrix of the provided name.
No parameter schema in public metadata yet.
qr_decomposeComputes the QR factorization of the matrix of the provided name.
Computes the QR factorization of the matrix of the provided name.
No parameter schema in public metadata yet.
svd_decomposeComputes the Singular Value Decomposition of the matrix of the provided name.
Computes the Singular Value Decomposition of the matrix of the provided name.
No parameter schema in public metadata yet.
find_orthonormal_basisFinds an orthonormal basis for the matrix of the provided name.
Finds an orthonormal basis for the matrix of the provided name.
No parameter schema in public metadata yet.
change_basisComputes the matrix of the provided name in the new basis.
Computes the matrix of the provided name in the new basis.
No parameter schema in public metadata yet.
vector_projectProjects a vector in the tensor store to the specified vector in the same vector space
Projects a vector in the tensor store to the specified vector in the same vector space
No parameter schema in public metadata yet.
vector_dot_productComputes the dot product of two vectors in the tensor stores based on their provided names.
Computes the dot product of two vectors in the tensor stores based on their provided names.
No parameter schema in public metadata yet.
vector_cross_productComputes the cross product of two vectors in the tensor stores based on their provided names.
Computes the cross product of two vectors in the tensor stores based on their provided names.
No parameter schema in public metadata yet.
gradientComputes the gradient of a multivariable function based on the input function.
Computes the gradient of a multivariable function based on the input function.
No parameter schema in public metadata yet.
curlComputes the curl of a vector field based on the input vector field.
Computes the curl of a vector field based on the input vector field.
No parameter schema in public metadata yet.
divergenceComputes the divergence of a vector field based on the input vector field.
Computes the divergence of a vector field based on the input vector field.
No parameter schema in public metadata yet.
laplacianComputes the laplacian of a scalar function or a vector field.
Computes the laplacian of a scalar function or a vector field.
No parameter schema in public metadata yet.
directional_derivComputes the directional derivative of a function in a given direction u.
Computes the directional derivative of a function in a given direction u.
No parameter schema in public metadata yet.
plot_vector_fieldPlots a vector field; only 3d vector fields are supported and a 2d png perspective image is returned.
Plots a vector field; only 3d vector fields are supported and a 2d png perspective image is returned.
No parameter schema in public metadata yet.
plot_functionPlots a function in 2d or 3d based on the input variables.
Plots a function in 2d or 3d based on the input variables.
No parameter schema in public metadata yet.
Sponsors
Readme
Scientific Computation MCP
Installation Guide
The server speaks streamable HTTP. Add it from Smithery with the Smithery CLI (Node 20+):
npm install -g smithery@latest
smithery mcp add @aman-amith-shastry/scientific_computation_mcp --client claude
The namespace is lowercase. Smithery's registry lookup is case-sensitive, and the mixed-case spelling resolves to an empty record with no tools rather than failing outright, so a capitalized name looks like a server with no capabilities.
Details
- Repository
- github.com/aman-amith-shastry/scientific_computation_mcp
- Category
- Developer Tools
- Transport
- HTTP
- Auth
- Required
- Registry
- MCP registry, active
