# Aspicio [Health: Active]

**Category:** 📐 Architecture & Design  
**Repository:** https://github.com/frontsail-ai/aspicio  
**GitHub Stars:** 6  
**npm Downloads (last month):** 516  
**Views:** 0  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/aspicio

## Description
DXF drawings for AI agents: structured facts, PNG renders, and an interactive in-chat viewer.

## Tools
Capabilities this server exposes over MCP:

- **describe_dxf** — Return a structured JSON summary of a DXF drawing — units, bounding box, layers (with the color actually drawn), per-type entity counts, and any skipped/unsupported types. Use this to answer structural questions (what layers exist, how many parts, what size, is it to scale) without rendering an image. For a PDF use describe_pdf; if you do not know the format, use describe_doc. Covers the whole drawing by default, including every page of a multi-page PDF; pass `space` (a name from the reply's `spaces`) to scope it to one page or sheet.
- **render_dxf** — Render a DXF drawing to a PNG image you can look at. Use this to answer visual questions (what does it look like, where is a feature, does it look right) — it returns an image, not text. For structural facts, prefer describe_dxf. For a PDF use render_pdf; if you do not know the format, use render_doc. Renders the first page/sheet by default; pass `space` (a name from a describe reply's `spaces`) to render another one.
- **describe_pdf** — Return a structured JSON summary of a PDF drawing — units (points), bounding box, layers, per-type entity counts, the text it contains, and what was skipped (images, shadings, transparency). Use this for structural questions about a PDF without rendering it. For a DXF use describe_dxf; if you do not know the format, use describe_doc. Covers the whole drawing by default, including every page of a multi-page PDF; pass `space` (a name from the reply's `spaces`) to scope it to one page or sheet.
- **render_pdf** — Render a PDF drawing's vector content to a PNG you can look at. Images, shadings, and transparency are not drawn — they are reported by describe_pdf — so this shows line work and text, not a page facsimile. For a DXF use render_dxf; if you do not know the format, use render_doc. Renders the first page/sheet by default; pass `space` (a name from a describe reply's `spaces`) to render another one.
- **describe_doc** — Return a structured JSON summary of a drawing in any supported format (DXF or PDF), detected from its bytes rather than its name. Use this when you do not know which format you have; the reply names the format that was read. Covers the whole drawing by default, including every page of a multi-page PDF; pass `space` (a name from the reply's `spaces`) to scope it to one page or sheet.
- **render_doc** — Render a drawing in any supported format (DXF or PDF) to a PNG you can look at, detected from its bytes rather than its name. Use this when you do not know which format you have. Renders the first page/sheet by default; pass `space` (a name from a describe reply's `spaces`) to render another one.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "aspicio": {
    "command": "npx",
    "args": ["-y","@aspicio/mcp"]
  }
}
```

## Documentation

## What Aspicio MCP server does

Aspicio turns DXF and vector PDF drawing content into agent-readable outputs. Its MCP tools can describe a drawing as structured facts, render it for visual inspection, and, through the hosted service, present an interactive in-chat viewer. Supported inputs include local files, URLs, and inline DXF content, depending on the connection method.

The description output includes units, bounds, drawing size, layers and their effective colors, entity counts, and extracted text. This can expose title-block text or dimension values directly. Rendered output provides a PNG for model inspection; the hosted viewer adds pan, zoom, layer visibility controls, fullscreen mode, and host light/dark theme support.

## How it works

Aspicio parses the supplied bytes into a normalized drawing document, then tessellates that document into batched geometry. The same pipeline supports the MCP server, HTTP API, browser viewer, and headless rendering paths. DXF input can be ASCII or binary. Vector PDF content is supported when the PDF contains drawing artwork or dielines rather than a scanned image.

The stdio server processes local files in place and does not upload the DXF. The hosted MCP endpoint accepts URLs and inline DXF content. URL retrieval includes private-network protection, size limits, redirect validation, and timeouts. The interactive viewer is locked to the drawing returned by its tool call and makes no network requests.

## Setup and configuration

For clients that launch local stdio MCP servers, register:

```bash
npx -y @aspicio/mcp
```

Claude Code can install the server and bundled skills from the project marketplace:

```text
/plugin marketplace add frontsail-ai/aspicio
/plugin install aspicio@aspicio
```

Codex can add the marketplace and then register the MCP command:

```text
codex plugin marketplace add https://github.com/frontsail-ai/aspicio
codex plugin add aspicio@aspicio
codex mcp add aspicio -- npx -y @aspicio/mcp
```

For a client supporting remote MCP over Streamable HTTP, use `https://aspicio-api.frontsail.app/mcp`; no local installation is required. The related HTTP API exposes `/describe`, `/render`, and `/openapi.json`.

## Tools and capabilities

- `describe_dxf` returns drawing metadata, layer information, effective colors, entity counts, and text content.
- `render_dxf` produces a PNG representation of the drawing.
- `view_dxf` provides the hosted interactive viewer through the MCP Apps extension.
- HTTP access supports `/describe?src=<dxf-url>` and `/render?src=<dxf-url>&format=png|svg`.
- Drawing content may include lines, arcs, circles, ellipses, polylines, splines, text, dimensions, fills, hatches, and nested blocks. Unsupported entities are counted and reported rather than terminating processing.
- Multi-page PDFs and multi-sheet DXFs can be described as a whole or scoped to a specific space when using the underlying engine.

## Limitations and notes

Aspicio is for reading and rendering drawings, not editing them. Three-dimensional drawing workflows are out of scope. The hosted interactive viewer requires a host that supports the MCP Apps extension; hosts without that extension still receive structured facts from the tool. PDF support targets vector content, not scanned documents.

_Full upstream README: https://allmcps.com/mcp/aspicio/readme_