Mojulo MCP server

Mojulo

Mojulo is a 3D compiler for coding agents: a local MCP server where the agent you already run (Claude Code, Codex, any MCP host) builds objects, walkable worlds and games by conversation, and what gets stored is source, not a mesh. Every artifact is a small deterministic recipe on your own disk: a few hundred bytes of JSON that a kernel compiles back to the same geometry on every read, byte for byte, and that emits to Godot, Blender, Unity, Unreal, glTF, OpenUSD, or print-ready STL / 3MF at true scale. A compiler, not a generator: you edit and diff the recipe like code, and renders are disposable. No API key, no account, no telemetry. Your agent does the thinking; mojulo holds the state and does the geometry.

Quickstart

npx mojulo init

Needs Node 22.12+ and an MCP-capable coding agent (Claude Code or Codex; Claude Desktop works too). init finds the hosts on your machine, asks once per host, and opens the dashboard at http://localhost:3001. Everything lands in ~/.mojulo/. Then open a fresh agent session and ask: "what is this?"

The first install is the big one: npx pulls a ~27 MB tarball whose native dependencies land at about 885 MB on disk, and the first launch fetches a ~130 MB embedding model. Most of that is onnxruntime-node (the local search model) and puppeteer-core (local headless Chrome for stills). Nothing in the list reaches the network on its own; the per-dependency sheet is in docs/tech-requirements.md. Verified on macOS (Apple Silicon); Linux runs the test suite in CI; Windows was verified natively under Claude Code.

Wire it by hand instead

# Claude Code (--scope user makes mojulo available in every project):
claude mcp add --scope user mojulo -- npx -y mojulo

# Codex: add to ~/.codex/config.toml
[mcp_servers.mojulo]
command = "npx"
args = ["-y", "mojulo"]

// Claude Desktop: add under "mcpServers" in claude_desktop_config.json, then restart.
// If it fails with "spawn npx ENOENT", replace "npx" with the absolute path from `which npx`.
"mojulo": { "command": "npx", "args": ["-y", "mojulo"] }

Open the dashboard on its own with npx -y -p mojulo mojulo-ui. The same bin is a CLI over the tool registry: npx mojulo tools, npx mojulo help mint_solid, npx mojulo call version.

Five things to say to it

Each one is a sentence to your agent, the tool it reaches for, and the recipe that gets stored. Every example below runs keyless and offline.

1. "Make me a coffee mug, 90 mm tall"

The agent calls mint_solid { kind: 'workbench' }. This is the whole stored recipe: a lathe for the body, a sweep for the handle, real centimetres.

{ "units": "cm",
  "lathes": [ { "axisFrom": { "x": 0, "y": 0, "z": 0 }, "axisTo": { "x": 0, "y": 0, "z": 9 },
                "profile": [ { "t": 0, "radius": 3.6 }, { "t": 0.15, "radius": 4 }, { "t": 1, "radius": 4 } ],
                "tint": "#b8342c", "material": "satin" } ],
  "sweeps": [ { "path": [ [3.8, 0, 2.2], [6.2, 0, 3.2], [6.6, 0, 5.2], [5.4, 0, 7.0], [3.8, 0, 7.4] ],
                "radius": 0.6, "tint": "#b8342c", "material": "satin" } ] }

Shortened. The full README is on GitHub.