MCP server: One MCP server.

Nova3D

@raresenseRun by its publisher: served from their own domain, namespace checked by the registry.MCP server · External

Structured, part-aware 3D generation for AI agents. Named-part GLB, preview URL, Blender script.

Freeno charge per call

Runs on your machine from its package; the steps are below.

Robots harvesting on a Nova3D-generated farm, simulated in MuJoCo
From the README · 1 of 8

What it does

  1. Reads
  2. Writes
  3. High impact

At most: creates or changes data: records, files, settings.

What it costs

Free

Odel charges nothing per call. The publisher may charge for its own service.

Runs locally over stdio

This server isn't hosted — your MCP client launches it from a package registry. Use one of the commands below, or drop the config into your client (e.g. Claude Desktop).

PyPInova3d-mcpv0.4.0

Run

uvx nova3d-mcp

MCP client config

{
  "mcpServers": {
    "nova3d": {
      "command": "uvx",
      "args": [
        "nova3d-mcp"
      ]
    }
  }
}
README5 min read

Nova 3D: design workspace for programmable 3D

Website website · App open studio · Paper paper · Discord discord · X X · Issues issues

MIT


Robots harvesting on a Nova3D-generated farm, simulated in MuJoCo

A working farm, written by Nova3D from one prompt. Humanoids pick tomatoes, quadrupeds carry the harvest, drones scout. Simulated and filmed in MuJoCo.


Capabilities

  1. Executable source: represent assets and environments as programs that can be inspected, edited, and rebuilt.
  2. Parametric control: define dimensions, proportions, materials, physical properties, and motion through explicit parameters.
  3. Controlled variation: specify which parameters change and which remain fixed across design alternatives or experiments.
  4. Structural editing: change components, assemblies, layouts, clearances, and connections through their construction code.
  5. Reusable construction: reuse components and generation logic to build related designs, asset families, and environments.
  6. Programmable motion: define articulation, animation, interactive controls, and prescribed object trajectories.
  7. Geometry and motion checks: inspect dimensions, part relationships, pivots, and collisions, using checks appropriate to the design.
  8. Versioned development: preserve source, parameters, build outputs, and validation results as the project evolves.
  9. Target-specific exports: compile designs for CAD tools, 3D applications, and robotics simulators through dedicated export paths.

For robotics

  1. Controlled scenario generation: specify which geometric, physical, and temporal parameters change, and which remain fixed.
  2. Structural variation: change connectivity, obstacle arrangement, clearances, and mechanism configurations, not just textures or initial positions.
  3. Reproducible evaluation: preserve the environment source, parameters, simulator configuration, and experiment results.
  4. Failure-driven generation: eventually turn a failed rollout into a family of nearby scenarios to investigate the failure boundary.

Describe it. Build it. Keep going.

Start with an idea and keep shaping it. Change the geometry, add motion and behavior, and explore new versions.

  

A drill, an escalator and an oven, each built part by part: assembled, taken apart, and seen through to every piece inside.

The gardener bot's arm turns from a soil probe into a watering can
gardener_bot
Animate his arm changing from the probe into the can, and make him water the plants.
A ring, then a pair of earrings, then rose gold, then rising-star climbers
shooting_star
Make this ring. → Turn it into a pair of matching earrings. → Make the earrings rose gold. → Change the earring shape into a rising-star climber.
The harlequin doll's head unzips and a glowing moon floats out
harlequin_doll
Animate his head unzipping, and a bright glowing moon floating out of it.

Build it together.

People and AI agents work in the same world at the same time, each on their own branch. Then the branches merge into one world.

v1: a cottage with a glass tower
You: Build a cottage on the empty plot, with a glass tower.
v1 · 53 parts
v2: the back opened up
Maya: I want to see inside. Open up the back.
v2 · 19 new parts inside
v3: winter
Sam: What does it look like in winter?
v3 · snow, bare trees, frozen pond
v4: night
Sam: Now make it night.
v4 · 9 lamps and the fire lit
v5: the two branches merged
You: Merge Maya's open back with Sam's winter night.
v5 · no conflicts
v6: the gardener bot waters the plants
Maya: Send the gardener bot in to water the plants.
v6 · in through the open back

worlds

Robots at work.

Every world below started as a text prompt, was generated as an executable scene program, compiled to MuJoCo, and populated with robots. Doors open on real hinges, produce carries labeled masses, floors carry measured friction. The environment is code, so every physical property is authored, not painted on.


Café · Unitree G1 waiters clear tables; a Go2 serves from its back (learned walking policy, full physics)

Mall · Spot patrols, H1 delivers parcels, Stretch restocks, a Skydio X2 flies the atrium

Farm · Apptronik Apollo picks tomatoes into a basket; ANYmal hauls the crate

Apartment · a G1 tidies a generated home, object by object

Orbital lab · a UR5e throws a sample across the module in zero g; a Franka Panda catches it in flight

Traction hall · one walking policy, three floors: ice μ 0.02, steel μ 0.30, rubber μ 1.05

Simulate. Test. Revise.

Run your designs in simulation to check movement, collisions, and interactions. Find what fails, revise the design, and test it again.

Test 1: the Husky robot is stopped by the tree's low limb
Test 1 · failed
Husky, pick the ripe apples off this tree.
The low limb stops it at 50 cm.
Test 2: the arm snags on branches
v2 · the low limb tied up 20°
Test 2 · failed: the arm snags on branches, 0 of 3 apples picked.
Test 3: the arm picks the ripe apples into the bin
v3 · 6 branches pruned out of the arm's path
Test 3 · passed: 3 ripe apples in the bin, nothing knocked.

A Clearpath Husky with a UR10e arm and a Robotiq 2F-85 gripper, in an old orchard grown as code. Asked to adapt this tree for this robot and keep every apple, Nova revises the tree and tests again. Every move is the MuJoCo run: branches bend and spring back, stems snap only when pulled or lifted.

Photo of the real kitchen
The real kitchen
The scene was built from 8 phone photos.
Test 1: Stretch bumps the bar stool
Test 1 · failed
Stretch, get the milk off the island.
It bumps the bar stool, 1.1 m short.
Test 2: Stretch gets the milk
v2 · adapted for Stretch, design kept
Test 2 · passed: 4 things moved out of its path, milk in hand at 11 s.

physics

Physics, defined in source.

Mass, inertia, friction, and joint limits are explicit and editable alongside the geometry. Change the conditions and simulate the result. Below, the same scene runs with one parameter changed: gravity, from 0 to 9.81 m/s².


g = 0 · a Booster T1 pushes off the hatch with its legs and floats the length of the module, carried only by the momentum of that push

The ramp tilts slowly, and the blocks let go in order of grip: the ice block slides at just 4.6°, steel at 15°, aluminium at 20°, oak at 26°, and the rubber block holds on to the very end. Nobody animated any of this. Each block slips at exactly the angle where physics says its grip runs out.

Build on common ground.

Bring assets, scenes, and behavior together in one programmable project. Build from the same source for design tools, game engines, and simulators.

One source, every engine: MuJoCo, Isaac Sim, Gazebo, PyBullet, Omniverse, Unity, Unreal, Godot, Roblox, Minecraft, the web, glTF, Blender, OpenUSD, Rhino

License

MIT © RareSense.

Built on the same engine powering FormaNova for specialized jewelry CAD.

Similar modules

Browse 3D modelling & CAD