# Jaxonomy — hybrid dynamical systems on JAX

Jaxonomy runs differentiable simulations of hybrid dynamical systems on JAX. It helps engineers design control loops and optimize trajectories through differential equations.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 21
- Author: machinavitalis
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/machinavitalis/jaxonomy
- Updated: 2026-08-12
- HTML: https://affpapa.org/en/nevibecode/mcp/jaxonomy-hybrid-dynamical-systems-on-jax

## What it does

Jaxonomy builds block-diagram models for hybrid dynamical systems. It merges continuous differential equations with discrete switching logic. Execution relies on JAX. Simulations benefit from JIT compilation and `vmap` batching with automatic differentiation.

The library includes over 150 components. Engineers get access to LQR controllers and Kalman filters. It also provides tools for reduced-order modeling and FMI file exchange.

Running this package requires Python 3.10+. Note that `jx.simulate` records no trajectories silently. If you omit the `recorded_signals` dictionary, output fields evaluate to `None`.

## Requirements
- Needs: Python and uv (commands run via uvx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add jaxonomy -- uvx jaxonomy
```
uvx runs the command named after the package; if the README names another one, use uvx --from jaxonomy <command>

### Codex

**Platform CLI**
```bash
codex mcp add jaxonomy-hybrid-dynamical-systems-on-jax -- uvx jaxonomy
```
uvx runs the command named after the package; if the README names another one, use uvx --from jaxonomy <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "jaxonomy-hybrid-dynamical-systems-on-jax": {
            "command": "uvx",
            "args": [
                "jaxonomy"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from jaxonomy <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "jaxonomy-hybrid-dynamical-systems-on-jax": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "jaxonomy"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from jaxonomy <command>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add jaxonomy-hybrid-dynamical-systems-on-jax uvx jaxonomy
```
uvx runs the command named after the package; if the README names another one, use uvx --from jaxonomy <command>

## When to use it
- simulate hybrid physical systems with discrete transitions
- compute exact parameter gradients across ODE integration steps
- tune feedback loops with LQR or Model Predictive Control
- interchange simulation models using the FMI standard

## Example prompts
- Construct a double integrator plant with an LQR controller in Jaxonomy and simulate the response.
- Configure `recorded_signals` to capture position and control inputs during the JAX simulation run.
- Set up a parameter sensitivity analysis for the dynamical model using `jaxonomy.uq`.

## Similar
- [Zotero MCP](https://affpapa.org/en/nevibecode/mcp/zotero-mcp.md) — MCP server · ★ 5548
- [arxiv-mcp-server](https://affpapa.org/en/nevibecode/mcp/arxiv-mcp-server.md) — MCP server · ★ 3231
- [PaperBanana](https://affpapa.org/en/nevibecode/mcp/paperbanana.md) — MCP server · ★ 2417
- [MATLAB MCP Server](https://affpapa.org/en/nevibecode/mcp/matlab-mcp-server.md) — MCP server · ★ 1716
- [Hex Research](https://affpapa.org/en/nevibecode/mcp/hex-research.md) — MCP server · ★ 583
- [DocsAgent — Zotero, Obsidian & Apple Notes MCP Server](https://affpapa.org/en/nevibecode/mcp/docsagent-zotero-obsidian-apple-notes-mcp-server.md) — MCP server · ★ 578

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md