Log inSubmit server
Mathmethods MCP logo

Mathmethods MCP

by agmonetti

MCP tools for root finding, integration, ODEs, interpolation, Monte Carlo methods, and dynamical-system analysis.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Mathmethods MCP

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "agmonetti-mathmethods-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@agmonetti/mathmethods-mcp"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

agmonetti/mathmethods-mcp exposes a vendored numerical-methods core through MCP tools that an AI client can call from chat. It covers root finding, numerical integration, finite differences, ODE solvers, interpolation, Monte Carlo estimation, and one- and two-dimensional dynamical systems. Inputs use Python/SymPy-style mathematical expressions, with optional PNG plots when the visualization extra is installed. Reach for it when an agent needs to calculate or compare standard numerical methods without embedding a separate math implementation.

Use cases

  • Compare root-finding methods for the same equation
  • Estimate definite and multidimensional integrals
  • Solve initial-value ODE problems with standard schemes
  • Analyze equilibria and phase behavior in dynamical systems
  • Generate numerical-method plots for an MCP client

Key features

  • Bisection, Newton–Raphson, fixed-point, and Aitken root finding
  • Composite quadrature and finite-difference differentiation
  • Euler, Heun, and fourth-order Runge–Kutta ODE solvers
  • Monte Carlo estimation and convergence analysis
  • One- and two-dimensional dynamical-system tools
  • Optional PNG plots returned with MCP results

Tools29

What Mathmethods MCP lets your agent do. Expand a tool for its parameters.

Self-reported~442 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 3d ago

Recent health check succeeded.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 12d ago via OSV.dev · @agmonetti/mathmethods-mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars1Stargazers on the source repository.
npm downloads257Package downloads in the last 30 days.
Last commit7d agoMost recent push to the default branch.
Tools exposed29Callable tools this server registers over MCP.
Directory activity7 viewsConfig copies, upvotes, and views on AllMCPs.

How Mathmethods MCP works

What agmonetti/mathmethods-mcp does

agmonetti/mathmethods-mcp makes a collection of numerical-analysis routines available as Model Context Protocol tools. Its scope includes four root-finding approaches, several quadrature rules, numerical differentiation, initial-value ODE solvers, Lagrange interpolation, Monte Carlo estimators, and dynamical-system analysis.

The dynamic-system tools extend beyond numerical stepping. They can find and classify one-dimensional equilibria, inspect bifurcations, analyze linear and nonlinear two-dimensional systems, check conservative behavior, solve a Lanchester combat model, and handle non-homogeneous linear systems with time-dependent forcing.

How it works

The server runs over the standard MCP server workflow and can be launched on demand with npx, installed as a global npm command, or started through Python's uvx. Its mathematical core is included in the repository, so the server does not depend on a separately checked-out academic project at runtime.

Expressions use Python/SymPy conventions such as x**2, sin(x), exp(x), sqrt(x), and log(x). Common alternatives including e^x, sen(x), ln(x), and ^ for exponentiation are also accepted. Tools can return structured JSON results. Each tool also accepts a plot option; when enabled, the response can include a rendered PNG MCP image content block in addition to the JSON.

Setup and configuration

The npm package can be registered with Claude Code using:

Terminal
claude mcp add mathmethods npx -y @agmonetti/mathmethods-mcp

Claude Desktop and Cursor can use an MCP entry whose command is npx and whose arguments are -y and @agmonetti/mathmethods-mcp. A global installation provides the mathmethods-mcp command directly. Python-oriented clients can launch uvx mathmethods-mcp instead. For local development, clone the repository, install its dependencies with uv sync --extra dev, and run uv run server.py.

Plotting is an optional dependency. Install the viz extra with pip, uvx, or the checkout's uv environment before requesting plot=True. Without it, a plotting request returns an installation error rather than a plot. Clients that cannot display MCP images still receive the JSON response.

Tools and capabilities

  • Root finding: bisection, Newton–Raphson with a numerical derivative, fixed-point iteration, Aitken acceleration, and side-by-side comparison.
  • Integration: composite midpoint, trapezoidal, Simpson 1/3, Simpson 3/8, and comparison of the four rules.
  • Differentiation and interpolation: forward, backward, and central first- and second-order finite differences, plus Lagrange interpolation.
  • ODE solving: explicit Euler, Heun predictor–corrector, and fourth-order Runge–Kutta.
  • Monte Carlo: one-, two-, and three-dimensional mean-value estimates, one-dimensional hit-or-miss estimation, replicated statistical experiments, and convergence tracking.
  • Dynamical systems: equilibrium and stability analysis, phase portraits, time series, bifurcation diagrams, nullclines, eigenvalues, analytic linear solutions, energy behavior, and Lanchester-model analysis.

Several comparison tools impose method-specific interval-count requirements: Simpson 1/3 needs an even count, Simpson 3/8 needs a count divisible by three, and the combined integration comparison needs a count divisible by six.

Limitations and notes

Plot output requires the optional Matplotlib-based visualization extra and a client capable of displaying MCP image content. The hit-or-miss one-dimensional estimator is described as correct for sign-changing functions. Mathematical expressions are processed through the server's expression-validation layer, so callers should use the supported syntax and function names rather than arbitrary programming expressions.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Mathmethods MCP

agmonetti/mathmethods-mcp is an MCP server that connects AI clients to a numerical-methods core through tools for root finding, integration, differentiation, ODE solving, interpolation, Monte Carlo estimation, and dynamical-system analysis. It accepts Python/SymPy-style expressions and can optionally return plots with the visualization extra installed.

Install it with `npx`, globally from npm, or through `uvx`. For on-demand use, register `npx -y @agmonetti/mathmethods-mcp` with an MCP client. Global npm installation exposes the `mathmethods-mcp` command, while Python users can run `uvx mathmethods-mcp`.

Yes, both Claude Desktop and Cursor can launch it through an MCP JSON configuration using `npx` and the `@agmonetti/mathmethods-mcp` package. The same server can also be registered with Claude Code and run from a local checkout for development.

Install the optional `viz` extra and set the tool's `plot` option to `true`. The response includes the normal JSON result and may include a rendered PNG MCP image content block. Clients without image rendering still receive the JSON data.

Use Python/SymPy-style expressions such as `x**2`, `sin(x)`, `exp(x)`, `sqrt(x)`, and `log(x)`. The server also accepts common shorthand including `e^x`, `sen(x)`, `ln(x)`, and `^` for powers.

Related MCP servers

All in Data Science Tools All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewMathmethods MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/agmonetti-mathmethods-mcp?style=directory)](https://allmcps.com/mcp/agmonetti-mathmethods-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/agmonetti-mathmethods-mcp"><img src="https://allmcps.com/api/badge/agmonetti-mathmethods-mcp?style=directory" alt="Mathmethods MCP on AllMCPs" /></a>