Jaxonomy — hybrid dynamical systems on JAX MCP Server

by machinavitalis Your server? Claim it

local only

Jaxonomy — hybrid dynamical systems on JAX runs on your own machine — the client starts it, so there is no endpoint to ping. 706 installs a week from pypi. Last commit 28 Oct 2026.

Build, simulate and calibrate JAX block-diagram models of hybrid dynamical systems.

Installs per day peak 401 · avg 38 · +503% w/w

a month agotoday

706

Installs / week

pypi · jaxonomy

Stars

0 open issues

28 Oct 2026

Last commit

from GitHub

MIT

License

Python

What the code does

We read the source, 5 d ago · rules 995398eba69f

Evidence

Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.

Runs commands and sends data out [пакет] jaxonomy/dashboard/project.py:735

                        exec(f.read(), _globals)

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Builds a file path from a variable jaxonomy/cli/cli_run.py:118, jaxonomy/cli/model_interface.py:64, [пакет] jaxonomy/cli/cli_run.py:118 и ещё 1

    with open(os.path.join(modeldir, model_json), encoding="utf-8") as f:

Unsafe deserialization jaxonomy/cli/run_fit_sindy.py:99, jaxonomy/cli/run_jaxonomy.py:435, [пакет] jaxonomy/cli/run_fit_sindy.py:99 и ещё 1

            pickled_kwargs = pickle.load(f)

Executes code built at runtime jaxonomy/dashboard/project.py:735, jaxonomy/dashboard/serialization/block_interface.py:659, jaxonomy/dashboard/serialization/from_model_json.py:328 и ещё 17

                        exec(f.read(), _globals)

Builds a database query by concatenation jaxonomy/models/compact_ev.py:333, [пакет] jaxonomy/models/compact_ev.py:333

        batt_ccv = batt_resistance_vdrop + ocv

Runs an external command jaxonomy/simulation/provenance.py:393, [пакет] jaxonomy/simulation/provenance.py:393

        result = subprocess.run(

Long encoded blob in source jaxonomy/acausal/index_reduction/archive/Sargent-Copy1.ipynb:85, jaxonomy/acausal/index_reduction/archive/abstract.ipynb:6, jaxonomy/acausal/index_reduction/archive/blt_test.ipynb:99 и ещё 2

      "image/png": "iVBORw0KGgoAAAANSUhEUgAAApQAAAHzCAYAAACe1o1DAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8g+/7EAAAACXBIWXMAAA9hAAAPYQGoP6dpAABcC0lEQVR4nO3de3yU9Z3+/2sMDJEEI4NEkoBACUcJRK3gWaso2nqsiIpaVFgRxPJVXCsq0SoFbaEKCB6KNoAC3UVlF7Xr…

Reads files and sends them to the network jaxonomy/dashboard/project.py:434, [пакет] jaxonomy/dashboard/project.py:434

            for root, dirnames, files in os.walk(directory):

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

We found things in this code

Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch Jaxonomy — hybrid dynamical systems on JAX and you get told the day something new turns up.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add jaxonomy -- uvx jaxonomy

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "jaxonomy": {
      "command": "uvx",
      "args": [
        "jaxonomy"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.jaxonomy]
command = "uvx"
args = ["jaxonomy"]

.cursor/mcp.json

{
  "mcpServers": {
    "jaxonomy": {
      "command": "uvx",
      "args": [
        "jaxonomy"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "jaxonomy": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "jaxonomy"
      ]
    }
  }
}

Alternatives to Jaxonomy — hybrid dynamical systems on JAX

same job, measured the same way

BlockWerk

by blockwerk

Build, run and analyse block-diagram simulations: PID, Bode, FFT, optimisation and code export.

42 tools answering

Raptor Studio

by openpowershift

Build, validate and simulate reliability block diagrams (RAM analysis) from an AI assistant.

436 installs/wk local only

Whatif

by pflow-sim

Conversational what-if simulation: build, diagnose and compare Petri-net models; CC0 catalog.

59 tools answering

Molecular MCP

by andylbrummer

GPU-accelerated MCP server for molecular dynamics, N-body simulations, and particle systems

109 installs/wk local only

RASON

by frontlinesystems

Build, solve, and analyze RASON optimization, simulation, data science, and decision models

80 installs/wk local only

HVAC Builder

by hvacbuilder

Design, solve and simulate HVAC systems from real components, weather years and buildings.

answering

Magicweave Fastmcp

by fortunecasablancas

Author, validate, simulate, and one-click-build game economies on the Magicweave platform.

answering

Diagrid Catalyst

by diagrid

Build and operate Dapr Workflows and Durable Agents on Diagrid Catalyst. Sign-in required.

answering

Jaxonomy — hybrid dynamical systems on JAX — questions

Answers built from our own checks of this server.

Why is there no uptime for Jaxonomy — hybrid dynamical systems on JAX?

Jaxonomy — hybrid dynamical systems on JAX runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package jaxonomy was installed 706 times last week.

How do I connect Jaxonomy — hybrid dynamical systems on JAX?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls jaxonomy straight from pypi; nothing to host, nothing to sign up for.

How many people use Jaxonomy — hybrid dynamical systems on JAX?

The pypi package jaxonomy was installed 706 times in the last week. Week over week that is +503%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Jaxonomy — hybrid dynamical systems on JAX open source?

Yes — it is published under the MIT licence, written in Python and 22 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.