# Spatial Compiler by Applied Manifold > The spatial compute cloud for 3D reality. Applied Manifold builds cloud infrastructure for 3D physical reality, starting with Spatial Compiler. Spatial Compiler (`@spatial-compiler/mcp`, CLI `spatial-compiler`): Headless GPU compilation for 3D geometry and physics. Turn raw AI-generated meshes into production-ready, simulation-ready assets with one API call, delivered natively via MCP and REST. Its pyro module bakes fire, smoke, explosion and dust flipbook sheets for Godot 4 from `.pyro.toml` specs. Version 0.1.0. The hosted MCP server is https://mcp.spatialcompiler.dev, the local MCP server is the npm package `@spatial-compiler/mcp`, and the REST API host is https://api.spatialcompiler.dev. The local `spatial-compiler` program installs as a Claude plugin and builds from source on Windows. Every page is available as markdown (links below), or by requesting the HTML URL with `Accept: text/markdown`. ## Set up with your agent Give this to your agent (Claude Code, Codex, Cursor, others): ``` Install the Spatial Compiler skill. If you're in Claude Code, run `claude plugin marketplace add applied-manifold/skills`, then `claude plugin install spatial-compiler@applied-manifold`. If you're in another agent, run `npx skills add applied-manifold/skills --skill spatial-compiler`. You can read the skill directly at https://github.com/applied-manifold/skills/blob/main/skills/spatial-compiler/SKILL.md (raw: https://raw.githubusercontent.com/applied-manifold/skills/main/skills/spatial-compiler/SKILL.md). Then use the Spatial Compiler skill when working on this project. ``` ## Connect over MCP or REST Hosted MCP server (https://mcp.spatialcompiler.dev, OAuth 2.1 browser login, no key in the config): ```json { "mcpServers": { "spatial-compiler": { "type": "http", "url": "https://mcp.spatialcompiler.dev" } } } ``` Local MCP server (`@spatial-compiler/mcp` over stdio, API key in `SPATIAL_API_KEY`): ```sh SPATIAL_API_KEY=sk_test_spatial_sandbox npx -y @spatial-compiler/mcp ``` ```json { "mcpServers": { "spatial-compiler": { "command": "npx", "args": [ "-y", "@spatial-compiler/mcp" ], "env": { "SPATIAL_API_KEY": "sk_test_spatial_sandbox" } } } } ``` REST, with the API key as a bearer token: ```sh curl -X POST https://api.spatialcompiler.dev/v1/compile \ -H "Authorization: Bearer sk_test_spatial_sandbox" \ -F "file=@model.glb" \ -F 'options={"target_tris":15000,"dry_run":true}' ``` `sk_test_spatial_sandbox` is an example key; replace it with your own. Sandbox keys include 500 free credits. Full guide: https://appliedmanifold.com/docs/index.md (sections "Install via MCP", "MCP tools", "REST overview", "Operations reference"). ## Install the local program Add the Claude plugin (Claude Code): ``` /plugin marketplace add applied-manifold/spatial-compiler /plugin install spatial-compiler@applied-manifold ``` Build the program from source (Windows, Visual Studio 2022 with the C++ workload, Python 3), from a clone of the repository: ``` python scripts\fetch_third_party.py scripts\build.bat scripts\install.bat ``` `install.bat` copies the program to `%USERPROFILE%\.spatial-compiler\bin`, where the plugin finds it. Bake and wire: ``` spatial-compiler bake .pyro.toml --out spatial-compiler wire --scene .tscn ``` Verified: Vulkan on one NVIDIA GeForce RTX 2070 Super under Windows: 19 tests, and the six pyro examples bake at final quality. ## Overview - [Home](https://appliedmanifold.com/index.md): The landing page covers MCP and REST setup, the Claude plugin install, who Spatial Compiler is built for, the thesis, the product stack with the pyro module, unit economics and the FAQ. ## Docs - [Docs](https://appliedmanifold.com/docs/index.md): What Spatial Compiler does, MCP install (hosted and local), the MCP tools, the REST overview, the operations reference, dry_run, cache and limits, the telemetry fields, the Claude plugin install, building from source, the pyro bake and wire commands, the spec, outputs and report, the verified setup, self-host and the machine-readable docs. - [Pyro module](https://appliedmanifold.com/modules/pyro/index.md): The pyro module: what goes in (a .pyro.toml spec), what comes out (sheets, previews, an animated preview and a JSON report), the six example bakes, the Godot six-way shader and wire, and the verified setup. - [Pricing](https://appliedmanifold.com/pricing/index.md): Tiers (Sandbox, Pro, Studio, Enterprise) with credits and per-compile cost, how credits work (1 credit = $0.01, standard compile = 5 credits) and what costs zero credits. - [FAQ](https://appliedmanifold.com/faq/index.md): Frequently asked questions with answers. ## Use cases - [Use cases](https://appliedmanifold.com/use-cases/index.md): Index of the four verticals Spatial Compiler is built for: Gen3D platforms, robotics and world models, e-commerce configurators, and AI gaming, UGC and AEC. - [Gen3D platforms](https://appliedmanifold.com/use-cases/gen3d/index.md): For text-to-3D and image-to-3D platforms: one MCP or REST call compiles each raw generation into a welded, budgeted, UV-packed, ORM-baked, collider-ready asset. - [Robotics & world models](https://appliedmanifold.com/use-cases/robotics-world-models/index.md): For robotics and world-model teams: sim-ready convex colliders, reproducible asset compilation for synthetic data, and VPC or air-gapped self-host. - [E-commerce configurators](https://appliedmanifold.com/use-cases/ecommerce-configurators/index.md): For e-commerce 3D and AR configurators: web-weight GLBs, LOD chains and baked materials per SKU within a page-weight budget, and unchanged SKUs as 0-credit cache hits. - [AI gaming, UGC & AEC](https://appliedmanifold.com/use-cases/gaming-ugc-aec/index.md): For AI game engines, UGC platforms and AEC tools: untrusted uploads and CAD/BIM geometry pre-flighted and compiled to engine budgets with spend caps, plus pyro effects wired into Godot 4. ## Company - [About](https://appliedmanifold.com/about/index.md): Company, tagline and architecture. - [Changelog](https://appliedmanifold.com/changelog/index.md): Release notes for every Spatial Compiler version, newest first. ## Agent discovery - [MCP server card](https://appliedmanifold.com/.well-known/mcp/server-card.json): the hosted MCP server at https://mcp.spatialcompiler.dev and the local server @spatial-compiler/mcp, tools compile_3d_asset, simulate_fx_vat, bake, check, schema, sweep and wire - [API catalog](https://appliedmanifold.com/.well-known/api-catalog): RFC 9727 linkset for the MCP server and the REST API - [OpenAPI](https://appliedmanifold.com/openapi/spatial-compiler.json): the REST endpoint for compile_3d_asset - [auth.md](https://appliedmanifold.com/auth.md): API keys (local MCP server in SPATIAL_API_KEY, REST as a bearer token) and the hosted server's OAuth 2.1 browser login - [Agent skills](https://appliedmanifold.com/.well-known/agent-skills/index.json): SKILL.md files for connecting over MCP, compiling assets, installing the local program and baking pyro effects - [AI catalog](https://appliedmanifold.com/.well-known/ai-catalog.json): ARD manifest ## Optional - [Full text](https://appliedmanifold.com/llms-full.txt): all pages in one markdown file - [Terms (draft)](https://appliedmanifold.com/terms/index.md): Placeholder marked DRAFT, NOT LEGAL TERMS. - [Privacy (draft)](https://appliedmanifold.com/privacy/index.md): Placeholder marked DRAFT, NOT LEGAL TERMS.