scicompute

scicompute

scicompute is a scientific-computation server built around one idea: a named, in-process tensor store. You create tensors under names, then run matrix algebra and vector operations by referring to those names. Everything is computed locally in pure TypeScript — no network, no external math library. One binary serves a command-line interface and a stdio MCP server.

This build is a labelled core subset of the documented tool set: tensor storage, linear algebra, and vector operations (14 tools). Eigen/SVD/QR decompositions, the vector-calculus tools, basis changes, and plotting from the wider documented set are not included; see the build report for the full omission list.

Install

npx @reneturcios/scicompute create-tensor T 2,2 1,2,3,4

Or run the container image:

docker run -i ghcr.io/cloudcorprecords/scicompute

The container defaults to the MCP server (see below). Pass CLI arguments to use it as a CLI instead.

CLI

scicompute create-tensor A 2,2 4,7,2,6
scicompute view-tensor A
scicompute determinant A
scicompute --version

The store is in-process, so a single CLI invocation holds its tensors only for its own lifetime; chained operations over several tensors belong to one MCP session, where the store persists across tool calls. Exit codes: 0 on success, 1 for a computation error (such as a shape mismatch or a singular matrix), 2 for usage errors.

Subcommands: create-tensor, view-tensor, delete-tensor, add, subtract, multiply, scale (--no-in-place to leave the stored matrix untouched), transpose, determinant, rank, inverse, dot, cross, project, and mcp.

MCP server

npx -y @reneturcios/scicompute mcp

MCP client configuration:

{
  "mcpServers": {
    "scicompute": {
      "command": "npx",
      "args": ["-y", "@reneturcios/scicompute", "mcp"]
    }
  }
}

Tools

Tool	Input	What it returns
create_tensor	name, shape, values (all required)	The stored tensor: name, shape, flat values, and nested data. values length must equal the shape product.
view_tensor	name (required)	The stored tensor under that name.
delete_tensor	name (required)	Confirmation that the tensor was deleted.
add_matrices	a, b (required), result (optional)	The element-wise sum matrix; stored under result when given.
subtract_matrices	a, b (required), result (optional)	The element-wise difference matrix.
multiply_matrices	a, b (required), result (optional)	The matrix product.
scale_matrix	name, factor (required), in_place (optional)	The scaled matrix. In place by default; stored matrix is untouched when in_place is false.
transpose	name (required), result (optional)	The transposed matrix.
determinant	name (required)	The determinant of a square matrix.
rank	name (required)	The matrix rank, from row-echelon reduction.
matrix_inverse	name (required), result (optional)	The inverse of a square, non-singular matrix.
vector_dot_product	a, b (required)	The dot product of two stored vectors.
vector_cross_product	a, b (required)	The cross product of two stored 3-vectors.
vector_project	a, b (required)	The projection of vector a onto vector b.

Algebra and vector operands are tensor names, not raw data. Matrices are 2-entry shapes and vectors are 1-entry shapes; shape mismatches, missing tensors, non-square determinant/inverse requests, singular inverses, and projections onto the zero vector are all errors rather than silent zeros.

Development

npm install
npm run build   # tsc -> dist/
npm test        # node test runner over test/*.test.ts, no network
npm run dev     # run the CLI from source via tsx

License

MIT — see LICENSE.