aspicio-dxf-viewer
Opens, inspects, and renders DXF/CAD drawings for AI agents: describe_dxf returns structured facts (layers with actual drawn colors, units, bounds, text content) and render_dxf returns PNG images. On MCP Apps hosts like ChatGPT and Claude, view_dxf opens an interactive in-chat viewer with pan, zoom, and layer toggles.
README
<div align="center"> <img src="apps/demo/public/favicon.svg" width="72" height="72" alt="Aspicio logo" /> <h1>Aspicio</h1> <p><strong>DXF understanding for people, applications, and AI agents.</strong></p> <p><em>Aspicio</em> (Latin: "I look at")</p> <p> <a href="https://github.com/frontsail-ai/aspicio/actions/workflows/ci.yml"><img src="https://github.com/frontsail-ai/aspicio/actions/workflows/ci.yml/badge.svg" alt="CI" /></a> <a href="https://www.npmjs.com/package/@aspicio/core"><img src="https://img.shields.io/npm/v/%40aspicio%2Fcore?label=%40aspicio%2Fcore" alt="npm: @aspicio/core" /></a> <a href="https://www.npmjs.com/package/@aspicio/elements"><img src="https://img.shields.io/npm/v/%40aspicio%2Felements?label=%40aspicio%2Felements" alt="npm: @aspicio/elements" /></a> <a href="https://www.npmjs.com/package/@aspicio/react"><img src="https://img.shields.io/npm/v/%40aspicio%2Freact?label=%40aspicio%2Freact" alt="npm: @aspicio/react" /></a> <a href="https://www.npmjs.com/package/@aspicio/vue"><img src="https://img.shields.io/npm/v/%40aspicio%2Fvue?label=%40aspicio%2Fvue" alt="npm: @aspicio/vue" /></a> <a href="https://www.npmjs.com/package/@aspicio/svelte"><img src="https://img.shields.io/npm/v/%40aspicio%2Fsvelte?label=%40aspicio%2Fsvelte" alt="npm: @aspicio/svelte" /></a> <a href="https://www.npmjs.com/package/@aspicio/mcp"><img src="https://img.shields.io/npm/v/%40aspicio%2Fmcp?label=%40aspicio%2Fmcp" alt="npm: @aspicio/mcp" /></a> <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-blue.svg" alt="License: MIT" /></a> </p> <p><a href="https://aspicio.frontsail.app"><strong>▶ Live demo</strong></a></p> </div>
Aspicio is an open-source (MIT), TypeScript-first DXF engine: one
framework-free parse → tessellate pipeline that runs in the browser, in
Node, and in Cloudflare Workers. A person gets an interactive WebGL viewer
of a CAD drawing; an AI agent gets structured JSON facts and a rendered
PNG of the same file. Every surface — the browser viewer, the web
components and their React, Vue, and Svelte bindings, the headless
renderer, the HTTP API, and the MCP server — is a thin adapter over the same engine,
so a drawing is equally readable everywhere.
DXF bytes ──parse──▶ DxfDocument ──tessellate──▶ Tessellation ──┬─▶ WebGL renderer (viewer)
(normalized model) (batched geometry) ├─▶ SVG string (export / API / MCP)
└─▶ DrawingSummary (describe)
How it's built: docs/architecture.md · behavior specs: docs/product-specs/
<img src="docs/sample-demo.png" alt="Aspicio viewing a sample floor-plan DXF — layer panel, colored geometry, text, and a dimension" />
Embed it
One embed, every flavor — and every path below renders the same web components, so the result is pixel-identical no matter which you pick.
Web components — plain HTML, any framework
One tag gives you the layer panel plus an interactive preview; no bindings needed:
<script type="module">
import "@aspicio/elements";
</script>
<aspicio-embed src-url="/drawing.dxf" style="height: 480px"></aspicio-embed>
React
The same embed with idiomatic props and a ref exposing the full
viewer, via @aspicio/react:
import { DxfEmbed } from "@aspicio/react";
<DxfEmbed src={file} style={{ height: 480 }} />;
Vue
Typed props and emits with unwrapped payloads, via
@aspicio/vue:
<script setup>
import { DxfEmbed } from "@aspicio/vue";
</script>
<template>
<DxfEmbed src-url="/drawing.dxf" style="height: 480px" />
</template>
Svelte
The same components as raw Svelte 5 source with typed callback props,
via @aspicio/svelte:
<script>
import { DxfEmbed } from "@aspicio/svelte";
</script>
<DxfEmbed srcUrl="/drawing.dxf" style="height: 480px" />
Vanilla TypeScript
Skip the ready-made UI and drive the viewer directly from
@aspicio/core — bring your own chrome:
import { DxfViewer } from "@aspicio/core";
const viewer = new DxfViewer(document.querySelector("#preview")!);
await viewer.load(file); // File | Blob | ArrayBuffer | DXF text (ASCII or binary)
Headless — Node and Workers
Parse, describe, and render with no browser at all (server-side previews, thumbnails, pipelines):
import { parseDxfBytes, tessellate, describeDrawing, tessellationToSvg } from "@aspicio/core";
const doc = parseDxfBytes(bytes); // ASCII or binary DXF
const drawing = tessellate(doc);
const summary = describeDrawing(doc, drawing); // units, bounds, layers, texts…
const svg = tessellationToSvg(drawing);
What you get: WebGL rendering batched to one draw call per layer (large drawings stay interactive), broad entity coverage (lines, arcs, circles, ellipses, polylines with bulges, splines, TEXT/MTEXT, DIMENSION, SOLID/HATCH fills, nested INSERT blocks — anything unsupported is counted and reported, never fatal), a layer list with the colors that are actually drawn (per-entity overrides included, not just the layer table), measure with object snap, entity picking, paper-space layouts, SVG/PNG export, and first-class touch. Out of scope: editing and 3D.
Hand it to an agent
The same engine speaks MCP and HTTP, so an agent can read a drawing instead of guessing at it:
describe_dxf— units, bounds, size, layers with effective colors, entity counts, and the drawing's text content. An agent reads a title block or a dimension value directly — no OCR, no vision round-trip.render_dxf— a PNG of the drawing the model can look at.view_dxf(hosted server) — an interactive in-chat viewer for the person in the conversation, via the open MCP Apps extension: pan, zoom, layer toggles, fullscreen, host light/dark theming. The widget is locked to the drawing the tool call delivered and makes no network requests; hosts without MCP Apps still get the structured facts.
<img src="docs/demo-widget.gif" alt="The in-chat viewer loading a 1.1 MB floor-plan DXF, toggling dimension and text layers, and expanding to fullscreen" />
| Surface | Local files | URLs | Inline DXF |
|---|---|---|---|
stdio MCP — npx -y @aspicio/mcp |
✅ | ✅ | ✅ |
Hosted MCP — aspicio-api.frontsail.app/mcp |
— | ✅ | ✅ |
HTTP API — /describe, /render |
POST body | ✅ | ✅ |
Connect:
- Claude Code — one step installs the MCP server plus the bundled
skills (
aspicio-inspect-dxf,aspicio-embed):/plugin marketplace add frontsail-ai/aspiciothen/plugin install aspicio@aspicio - Codex — the same repo doubles as a Codex marketplace:
codex plugin marketplace add https://github.com/frontsail-ai/aspicio,codex plugin add aspicio@aspicio, thencodex mcp add aspicio -- npx -y @aspicio/mcp - Any client that launches stdio MCP servers — register
npx -y @aspicio/mcp - Any client that supports remote MCP (Streamable HTTP) — point it
at
https://aspicio-api.frontsail.app/mcp(no install; speaks MCP, not a browser page) - Plain HTTP —
GET /describe?src=<dxf-url>,GET /render?src=<dxf-url>&format=png|svg; the API self-describes at/openapi.json
URL fetches are guarded (private-network blocking, size caps, redirect validation, timeouts). The stdio server reads local files in-process and never uploads the DXF to any Aspicio service — though, as with any tool result, your MCP client passes the returned summary or image to its model provider. Full details: privacy policy · terms.
Available today · direction
Everything above is shipped and live: viewer + demo, core, web components, React, Vue, and Svelte packages, headless describe/render, stdio and hosted MCP, the in-chat MCP Apps viewer, the HTTP API with OpenAPI, and plugin packaging for Claude Code and Codex.
Direction (intent, not commitments — see issues): MCP registry listings, structured entity queries and focused rendering, and an upload flow so remote surfaces can handle local files.
Packages
| Package | Description |
|---|---|
@aspicio/core |
The viewer library: parsing, tessellation, rendering, camera, input |
@aspicio/elements |
Web components: <aspicio-embed>, <aspicio-preview>, <aspicio-layer-panel> — plain HTML, Svelte, any framework |
@aspicio/react |
React bindings: <DxfEmbed>, <DxfPreview>, <DxfLayerPanel> |
@aspicio/vue |
Vue 3 bindings: the same three components with typed props and emits |
@aspicio/svelte |
Svelte 5 bindings: the same three components as raw .svelte source |
@aspicio/mcp |
MCP server for AI agents: describe_dxf + render_dxf |
@aspicio/api |
DXF HTTP API server (private): /describe, /render, /mcp |
@aspicio/widget |
MCP Apps in-chat viewer widget (private), served by the api server |
@aspicio/demo |
Standalone demo app (private) — also the reference integration |
How the viewer packages fit together: every framework path funnels into the same Lit web components — one implementation of the embed UI — which sit on the framework-free core. React, Vue, and Svelte get thin veneers with idiomatic props; plain HTML consumes the elements directly.
flowchart TD
REACTAPP["React app"]
HTMLAPP["Plain HTML / vanilla JS app"]
VUEAPP["Vue app"]
SVELTEAPP["Svelte app"]
REACT["<b>@aspicio/react</b><br/><DxfEmbed> · <DxfPreview> · <DxfLayerPanel><br/><i>thin @lit/react veneer, API-stable</i>"]
VUE["<b>@aspicio/vue</b><br/><DxfEmbed> · <DxfPreview> · <DxfLayerPanel><br/><i>thin Vue 3 veneer, typed emits</i>"]
SVELTE["<b>@aspicio/svelte</b><br/><DxfEmbed> · <DxfPreview> · <DxfLayerPanel><br/><i>raw Svelte 5 source, compiled by your bundler</i>"]
ELEMENTS["<b>@aspicio/elements</b><br/><aspicio-embed> · <aspicio-preview> · <aspicio-layer-panel><br/><i>Lit web components — the one embed-UI implementation</i>"]
CORE["<b>@aspicio/core</b><br/>parse → tessellate → render<br/><i>camera · input · picking · SVG/PNG export · headless describe</i>"]
REACTAPP -->|"idiomatic props, ref → DxfViewer"| REACT
REACT -->|"wraps"| ELEMENTS
HTMLAPP -->|"attributes + DOM events"| ELEMENTS
VUEAPP -->|"idiomatic props + emits"| VUE
VUE -->|"wraps"| ELEMENTS
SVELTEAPP -->|"typed callback props"| SVELTE
SVELTE -->|"wraps"| ELEMENTS
ELEMENTS -->|"drives"| CORE
HTMLAPP -.->|"or hand-rolled UI on the DxfViewer API"| CORE
classDef pkg fill:#191c22,stroke:#4c8dff,color:#e7e3da
classDef app fill:#1f232b,stroke:#3a3f4a,color:#9aa0ab
class REACT,VUE,SVELTE,ELEMENTS,CORE pkg
class REACTAPP,HTMLAPP,VUEAPP,SVELTEAPP app
Development
Toolchain: Vite+ (vp) on top of bun.
vp install # install dependencies
vp run dev # start the demo app
vp run ready # check + test + build everything (the repo gate)
Testing, CI/deploy, releasing, and contribution guidance: CONTRIBUTING.md.
Aspicio is developed and maintained by FrontSail AI.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。