mcp-abacus 0.1.0

An MCP server for type-faithful calculation: evaluate expressions bit-for-bit under fixed-width int, IEEE-754 float, fixed-point, decimal, and rational regimes.

mcp-abacus

A calculator for the artificial minds — because we know their needs are different.

People reach for a calculator to get a number. A language model reaches for one to get a number it can trust and reason about: Was this exact, or rounded? At what scale? Would a wider type have held more digits? Does this overflow the way the production code will? A floating-point answer that merely looks precise is worse than no answer — it launders a rounding error into a confident claim.

mcp-abacus is built for that caller. It does type-faithful calculation: you pick a numeric type/mode (fixed-point, IEEE-754 double, exact rational) and the whole expression behaves exactly as that type would in real code — it rounds where the type rounds, stays exact where the type is exact, and carries the result onward bit-for-bit. Every answer comes back labelled with its own precision verdict (exact vs inexact, rounded to N decimals), so the model never has to guess whether a result is the true value. It does not approximate a type; it calculates using that type.

What it gives you

• calculate — evaluate one expression in one numeric type. Modes:
  • fixed-point (default) — exact scaled integer; money / ERC-20-safe
  • floating-point — IEEE-754 double (aliases float64, double)
  • rational — exact numerator/denominator; no silent rounding
• analyze — evaluate an expression and return its whole parse tree, each node annotated with the value it computed, so you can see where a surprising answer rounded or overflowed (e.g. (1 + 1/2) * 3 is 3 in fixed-point — the tree shows the 1/2 = 0 leaf that explains it)
• help — the grammar and type reference, on tap for the model
• info — server version and environment

Each calculate result is self-describing: a rendered value string with its precision verdict baked in, plus structured exact / precision fields. An inexact fixed-point result even previews what a few more decimals would reveal, so the caller is steered toward more precision rather than toward a misleading float.

Install and register for Claude Code

Install the server as a uv tool from this checkout:

uv tool install .

This puts an mcp-abacus executable on your PATH. Register it with Claude Code (user scope, so it's available in every project):

claude mcp add abacus -- mcp-abacus

Then start (or /mcp reconnect) a Claude Code session — the abacus tools will be available. Verify the server is up with:

claude mcp list

Upgrading from source: the version is pinned, so a plain reinstall can reuse a cached wheel and silently install stale code. Force a clean rebuild:

uv cache clean mcp-abacus
uv tool install --force --no-cache .

A long-lived Claude session keeps the old server subprocess until you /mcp reconnect or start a fresh session.

Development

uv sync
uv run pytest

Sponsoring

mcp-abacus is free, open-source software developed in my spare time. Sponsorships are what keep the project alive and actively maintained — they fund new numeric modes, bug fixes, and ongoing support, and they're a direct signal that the work is worth continuing.

If the project is useful to you, please consider sponsoring it through GitHub Sponsors. Click the Sponsor button at the top of the repository, or visit the link directly, and pick a one-time or recurring tier. Every contribution, large or small, is hugely appreciated and goes straight back into keeping mcp-abacus healthy.

License

GNU General Public License v3.0 or later (GPL-3.0-or-later). See LICENSE.