mcpField
U
Ultimath Mcp

Ultimath Mcp

Local
ultimath.aiScience & Education0Updated 9w ago

About Ultimath Mcp

Ultimath MCP evaluates mathematical expressions with eight independent engines and returns their results and error assurances side by side. It is for users who need to assess numerical reliability, including when engines disagree.

Key features

  1. 01Evaluate expressions with eight engines
  2. 02Compare results and error assurances
  3. 03Return exact symbolic forms
  4. 04List supported functions by category
  5. 05Handle arithmetic, trig, and complex expressions

Use cases

  1. 01Check whether a numerical result is reliable
  2. 02Compare precision across calculation engines
  3. 03Retrieve a function list before evaluating

MCP support

Provides an `evaluate` tool for running expressions through eight engines and a `list_functions` tool to MCP clients. The server requires an Ultimath API key.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"ultimath": {
"command": "npx",
"args": [
"-y",
"ultimath-mcp"
],
"env": {
"ULTIMATH_API_KEY": "<ULTIMATH_API_KEY>"
}
}
}
}
Run commandnpx -y ultimath-mcp
Environment variables to set
ULTIMATH_API_KEYSecret

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmultimath-mcp

Tools

2

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
expressionstringYesMath expression, e.g. '0.1 + 0.2', 'sin(pi/4)', 'sqrt(2)^2 - 2', '2*pi', '2*(3+4)', 'factorial(10)'
precisionintegerNoDecimal digits of precision (default 50). The free beta caps at 50; higher values are rejected server-side.
formatenumNoOutput format (default 'fixed')fixed | scientific | auto

Details

From the project README

Ultimath MCP

Stop hallucinating numbers. An MCP server that runs every math expression through eight independent engines in parallel — exact symbolic, ball, interval, three different arbitrary-precision floats, deferred symbolic and IEEE 754, each with its own failure modes — and returns all eight readings side by side, so when they disagree you know the answer is numerically unreliable.

EngineWhat it does
Exact symbolicExact arithmetic: decides a value instead of approximating it
MultiprecisionBall arithmetic, rigorous radius carried through
IntervalRigorous lower/upper bounds (guaranteed enclosure)
Binary floatArbitrary-precision binary floats, no GMP below
PARI/GPBuilt without GMP: its own integer and transcendental kernels
NTL RRExact integer mantissa × 2^e; only operations round
Deferred symbolicRewrites before evaluating: a cancellation never rounds
IEEE-754 doubleStandard hardware floating point

What each engine stands behind

Reading eight numbers is only half the answer. Each engine also says how far it underwrites its own — and the three answers are not degrees of one another:

FieldWhat the engine is saying
"exact": trueIt holds the value. The reading is a truncation of it: every further digit you ask for is a digit of the number, not a closer approximation.
"digits": NIts own error bound covers the first N significant digits. 0 is a real answer — that is what catastrophic cancellation does to a value.
neitherIt carries no error bound. It printed as many digits as you asked for and can say nothing about any of them.

That last row is not 0, and it is the reason the other engines exist. Five of the eight are there by construction.

On exp(pi*sqrt(163)) - 262537412640768744, one engine prints 63 digits of which 34 are right — and says nothing about it. Two others prove 33 and stop. One holds the value exactly. Reading the eight numbers alone would not tell you which was which.

No engine is ever asked about another: each statement is about itself.

The exact engine

calcium settles an equality rather than comparing digits, reaches poles the others can only approach (tan(pi/2) is uinf), and when the printed digits are just a truncation it also returns the closed form — sqrt(2)+1 comes back with Add(Sqrt(2), 1), in plain form and in LaTeX, and acosh(0.5) with Div(Mul(NumberI, Pi), 3) — the named value, not the field element it is stored in.

The closed form is opt-in on the HTTP API ("closed_form": true) because proving one costs more than reading the digits. This client always asks for it: quoting an exact value is what its output schema promises.

Tools

  • evaluate — evaluate an expression on all eight engines and compare. Supports arithmetic, trig (sin, cos, tan), exp/log (exp, ln, log), roots and powers (sqrt, x^y), factorial, complex numbers (3+2i), alternate bases (0xFF, 0b1010), and constants (pi, e, golden ratio PHI).
  • list_functions — list every function the engines expose (name, arity, category, description). Optionally filter by category.

Comparisons do not mean the same thing on every engine. On the enclosure engines, !=, < and > are true only once proven; ==, <= and >= are true as soon as they are not disproven. A true == there is not a proof of equality — calcium decides that one exactly — but a true != is a proof of difference.

Multiplication must be explicit: write 2*pi, 2*sin(x), (a+b)*(c+d). Adjacency is not a product (2pi is an error). Expressions are purely mathematical — no type casts or constructors; write a complex number as 1+2i.

Setup

  1. Get a free API key at https://ultimath.ai.
  2. Add the server to your MCP client config (example for Claude Desktop):
{
  "mcpServers": {
    "ultimath": {
      "command": "npx",
      "args": ["-y", "ultimath-mcp"],
      "env": {
        "ULTIMATH_API_KEY": "your_api_key_here"
      }
    }
  }
}

That's it — npx fetches and runs the server on demand.

Requirements

  • Node.js ≥ 18
  • An Ultimath API key (ULTIMATH_API_KEY)

Links

Under the hood

Ultimath's engines build on FLINT/Arb, Calcium, GMP/MPFR and MPFI — full credits at https://ultimath.ai/credits.

Privacy

Ultimath stores only a hash of your API key and basic usage metrics to run and secure the service; expressions are evaluated, not retained for training. Full policy: https://ultimath.ai/privacy/

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.