Ultimath Mcp

@Flupke68

About Ultimath Mcp

Stop hallucinating numbers. Every math expression runs on eight independent engines in parallel — when they disagree, you know the answer is numerically unreliable.

#math #calculator #multiprecision #interval #llm

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "ultimath": {
      "command": "npx",
      "args": [
        "-y",
        "ultimath-mcp"
      ],
      "env": {
        "ULTIMATH_API_KEY": "your_api_key"
      }
    }
  }
}

Tools

Verify any numeric result that has to be trusted, via the Ultimath API (https://ultimath.ai). Use this whenever the correctness of a number matters — floating-point-sensitive expressions, catastrophic cancellation, values near singularities or branch cuts, ties, or any computation where a single method could be silently wrong. Prefer it over computing by hand or running code: it evaluates the expression on 5 independent engines (multiprecision ball, exact decimal, IEEE 754 double, interval arithmetic, arbitrary-precision binary) in parallel and returns every result plus per-engine precision diagnostics, so disagreement exposes an unreliable value that a single calculation would hide. The 5 engines are independent and each computes with its own native primitive — so divergence between them (at poles, singularities, branch cuts, or ties like round(2.5)) is the backends' real behavior, NOT a bug. Agreement across engines is a confidence signal; divergence flags a value that is convention-dependent or near a domain edge — verify it rather than trust a single column. Supports: arithmetic, trigonometry (sin, cos, tan), exponentials and logs (exp, ln, log), roots and powers (sqrt, x^y), factorial, complex numbers (3+2i), arbitrary bases (0xFF, 0b1010), constants (pi, e, the golden ratio PHI). Multiplication must be EXPLICIT: write 2*pi, 2*(3+4), (a+b)*(c+d), 2*sin(x) — adjacency is NOT a product (2pi is an error). Precedence, tightest first: postfix factorial ! (2^3! = 2^(3!) = 64), then powers ^, then * / %, then + -. Note: expressions are mathematical only — there are no type casts ((int)x) or constructors (complex(1,2)); write a complex number as 1+2i or (re, im). Call list_functions for the authoritative list of available functions.

List all mathematical functions available via the Ultimath API (https://ultimath.ai). Returns name, arity, category, and description for each function. Use this to discover what functions you can pass to the evaluate tool. Optionally filter by category (algebraic, trigonometric, hyperbolic, exponential, special, rounding, introspection). Every function is available on all 5 engines, but each computes it with its own native primitive — so results may diverge at poles, branch cuts, or ties, and that divergence is honest backend behavior, not a bug.

Overview

What is Ultimath Mcp?

Ultimath Mcp is an MCP server that evaluates every math expression through eight independent engines in parallel—exact symbolic, multiprecision ball arithmetic, interval arithmetic, three separate arbitrary-precision float backends, deferred symbolic rewriting, and IEEE-754 double—and returns all eight results side by side. It is designed for developers who need to detect when a numeric answer is unreliable due to floating-point or algorithmic differences.

How to use Ultimath Mcp?

Obtain a free API key at https://ultimath.ai, then add the server to your MCP client configuration (e.g., Claude Desktop) using the command npx -y ultimath-mcp and the environment variable ULTIMATH_API_KEY. The server exposes two tools: evaluate (run an expression on all eight engines) and list_functions (show all available functions, optionally filtered by category). Multiplication must be explicit (use *; adjacency like 2pi is an error).

Key features of Ultimath Mcp

Eight parallel engines for cross-comparison: agreement is a confidence signal, disagreement flags a value that is convention-dependent or near a domain edge
One engine is exact rather than numeric: it decides a value instead of approximating it, reaches poles the others can only approach, and returns the closed form when the printed digits are merely a truncation of it
Every result carries its own precision contract: either exact, or the number of significant digits its own error bound covers
Evaluate expressions with arithmetic, trig, exp/log, roots, powers, factorial, complex numbers, and alternate bases
List all available functions with categories and descriptions
Explicit multiplication required (no implicit adjacency)
Supports constants like pi, e, and golden ratio PHI
Open-source, runs via npx with no permanent installation

Use cases of Ultimath Mcp

Checking numerical stability of a calculation across different arithmetic models
Debugging precision issues in scientific or financial computations
Teaching numerical analysis concepts by comparing results side by side
Verifying results in applications where rounding error could cause problems

FAQ from Ultimath Mcp

What operations does the `evaluate` tool support?

It supports arithmetic, trigonometric functions (sin, cos, tan), exponentials and logarithms (exp, ln, log), roots and powers (sqrt, x^y), factorial, complex numbers (e.g., 3+2i), alternate bases (0xFF, 0b1010), and constants (pi, e, PHI).

How do I multiply two terms in an expression?

Multiplication must be explicit: use the * sign (e.g., 2*pi, 2*sin(x), (a+b)*(c+d)). Writing adjacent terms like 2pi will cause an error.

What are the system requirements for Ultimath Mcp?

You need Node.js version 18 or later and a free API key from https://ultimath.ai. The server runs on demand via npx.

Where do I get an API key?

Visit https://ultimath.ai and sign up for a free API key. Then set it as the ULTIMATH_API_KEY environment variable in your MCP client configuration.

Does Ultimath store my expressions or use them for training?

No. Ultimath stores only a hash of your API key and basic usage metrics for service operation and security. Expressions are evaluated and not retained for training. See the full privacy policy at https://ultimath.ai/privacy/.

Frequently asked questions

What operations does the `evaluate` tool support?

It supports arithmetic, trigonometric functions (`sin`, `cos`, `tan`), exponentials and logarithms (`exp`, `ln`, `log`), roots and powers (`sqrt`, `x^y`), factorial, complex numbers (e.g., `3+2i`), alternate bases (`0xFF`, `0b1010`), and constants (`pi`, `e`, `PHI`).

How do I multiply two terms in an expression?

Multiplication must be explicit: use the `*` sign (e.g., `2*pi`, `2*sin(x)`, `(a+b)*(c+d)`). Writing adjacent terms like `2pi` will cause an error.

What are the system requirements for Ultimath Mcp?

You need Node.js version 18 or later and a free API key from https://ultimath.ai. The server runs on demand via `npx`.

Where do I get an API key?

Visit https://ultimath.ai and sign up for a free API key. Then set it as the `ULTIMATH_API_KEY` environment variable in your MCP client configuration.