# How to let Claude Code, Codex or Cursor build a robot simulation

> Source: <https://dev.to/pranay_argon/how-to-let-claude-code-codex-or-cursor-build-a-robot-simulation-4fnk>
> Published: 2026-11-20 08:01:08+00:00

**Recommendation:** Give coding agents tool-level simulation operations and errors with an explicit fix field, then verify each run with sim.check()["ok"] before trusting the result.
More in the playbook "Designing agent systems": <https://wpnews.pro/playbooks/agent-architecture>

Coding agents are good at writing Python, but robot simulation is a hard place for them: scenes fail in confusing ways, the first run compiles for minutes, and a simulation that quietly blew up can look like a success. This walkthrough sets up [Alloy](https://github.com/argonrobotics-ai/alloy), an open-source physics engine for robot learning, so an agent like Claude Code, Codex or Cursor can build and run simulations on its own, either through plain Python or through an MCP server.

```
pip install alloy-engine
```

The package ships its docs, examples and a quick start written for agents. An agent can find them itself:

```
python -m alloy.docs          # prints three paths: the docs, the examples and AGENTS.md
python -m alloy.docs agents   # prints AGENTS.md, a quick start for agents
```

A good first prompt is simply: "Install alloy-engine, run `python -m alloy.docs agents`, and build me a scene where a robot arm pours water into a cup."

Alloy includes an MCP server, so the agent gets operations such as `scene`, `build`, `run`, `state`, `check` and `render` as tools instead of writing code. For Claude Code:

```
claude mcp add alloy -- alloy mcp
```

Other MCP clients (Cursor, Codex and so on) take the same command, `alloy mcp`, as a local stdio server.

Two habits make agent-built simulations reliable: read the error's fix, and check the world after every run.

``` python
import alloy

scene = alloy.Scene(dt=0.01)
scene.add_ground()
scene.add_box("block", size=(0.05, 0.05, 0.05), pos=(0, 0, 0.1))
try:
    scene.add_box("thin", size=(0.05, 0.05))          # a typical agent mistake
except alloy.AlloyAPIError as e:
    print(e.message)
    print(e.fix)
sim = alloy.build(scene, device="cpu")
sim.run(0.5)
print(sim.check()["ok"], round(float(sim.state(world=0)["block.pos"][2]), 3))
size needs 3 finite numbers, got (0.05, 0.05)
pass size=(..., ..., ...) in m
True 0.025
```

Every error carries a `message` and a `fix` that names what to pass, so the agent can correct itself without guessing. After the run the block rests on the ground with its centre at 0.025 m, and `sim.check()["ok"]` is `True`.

`sim.check()["ok"]` after every run: a frozen, broken world looks calm in a render.
