Jaxonomy — Claude Code MCP server: what it does, how to install
Jaxonomy runs differentiable simulations of hybrid dynamical systems on JAX. It helps engineers design control loops and optimize trajectories through differential equations.
claude mcp add jaxonomy -- uvx jaxonomyWhat Jaxonomy — hybrid dynamical systems on JAX 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.
What it helps with
- 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 for the agent
- Construct a double integrator plant with an LQR controller in Jaxonomy and simulate the response.
- Configure
recorded_signalsto capture position and control inputs during the JAX simulation run. - Set up a parameter sensitivity analysis for the dynamical model using
jaxonomy.uq.
How to install Jaxonomy — hybrid dynamical systems on JAX
Platform CLI
claude mcp add jaxonomy -- uvx jaxonomyuvx runs the command named after the package; if the README names another one, use uvx --from jaxonomy <command>
Platform CLI
codex mcp add jaxonomy-hybrid-dynamical-systems-on-jax -- uvx jaxonomyuvx runs the command named after the package; if the README names another one, use uvx --from jaxonomy <command>
Config file
{
"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>
Config file
{
"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>
Platform CLI
gemini mcp add jaxonomy-hybrid-dynamical-systems-on-jax uvx jaxonomyuvx runs the command named after the package; if the README names another one, use uvx --from jaxonomy <command>
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about Jaxonomy — hybrid dynamical systems on JAX
How to install Jaxonomy in Claude Code?
Run claude mcp add jaxonomy -- uvx jaxonomy in your terminal. You can also register the longer identifier: claude mcp add jaxonomy-hybrid-dynamical-systems-on-jax -- uvx jaxonomy.
What is Jaxonomy used for?
It simulates hybrid dynamical systems with JAX, combining physical equations with control algorithms. Everything can be differentiated or batched across parameter grids.
Why does my simulation output return None?
The jx.simulate function only stores variables declared in recorded_signals. If that dictionary is missing, results.time and results.outputs remain empty.
