A skill for working with 2D CAD drawings through qcad-mcp, a tool connection for QCAD. It supports operations such as creating, converting, measuring, rendering, analyzing, and exporting drawing data, including DXF and SVG files.

Creating and modifying floor plans, generating SVG previews, analyzing rooms and building elements, exporting drawings, and using QCAD Pro for drafting tasks.

It gives a coding agent a structured way to work with CAD plans and QCAD instead of manually editing drawing files. The instructions also separate agent operations from actions a human performs in QCAD or a web app.

qcad-cad — Skill for Claude Code by sandraschi/qcad-mcp

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add sandraschi/qcad-mcp --skill qcad-cad

Clone the repo

git clone --depth 1 https://github.com/sandraschi/qcad-mcp

Made for: Claude Code.

Or install qcad-mcp, the plugin that ships this one along with the rest of its 2 skills, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/sandraschi/qcad-mcp/qcad-cad/github.svg)](https://agentmods.dev/skills/sandraschi/qcad-mcp/qcad-cad)

Your own site

<a href="https://agentmods.dev/skills/sandraschi/qcad-mcp/qcad-cad"><img src="https://agentmods.dev/badge/skills/sandraschi/qcad-mcp/qcad-cad/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/sandraschi/qcad-mcp/qcad-cad"><img src="https://agentmods.dev/badge/skills/sandraschi/qcad-mcp/qcad-cad.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 895 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00041	$0.00895
Opus 5.5	$0.00016	$0.00358
Sonnet 5.5	$0.00008	$0.00179
Haiku 4.5	$0.00004	$0.00089

Measured 11d ago against content hash 44dbf2da47fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

qcad-cad scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/qcad-cad/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

qcad-cad skill

Agent vs human routing

Agents: drive everything through MCP tools (plan_*, qcad_*) or the REST API (POST /api/v1/control/tool). Never hand-edit DXF XML.
Humans: use the webapp (port 11967) — Depot, Viewer, Extrude, Analyse, Pipeline pages — or QCAD Pro directly for fine drafting.

Tool catalog (40 ops, all verified against src/qcad_mcp/tools/)

Core engine ezdxf (no QCAD Pro needed): plan_info, plan_to_svg, plan_extrude, plan_stack, plan_obj, plan_glb, plan_drawings, plan_export, plan_analyse, plan_create, plan_depot, plan_convert, plan_modify. BIM/analysis: plan_auto_dimension, plan_building_meta, plan_to_ifc_data, plan_wall_data, plan_beam_analysis. QCAD Pro 3.x: qcad_status, plan_script, plan_render, plan_exec, plan_dimension, plan_measure, plan_text, plan_hatch, plan_block_insert, plan_array. Libraries: plan_blocks, plan_blocks_download, plan_scripts_search, plan_scripts_download. Agentic: plan_generate, plan_agentic, plan_transpile, cad_sampling. Meta: qcad_help, qcad_shutdown, show_qcad_status_card, show_depot_card, show_beam_analysis_card, show_building_meta_card. Resources: cad://depot, cad://depot/{filename}. Prompts: 3 registered in agentic_tools (@mcp.prompt()).

Always call qcad_status first when a workflow needs QCAD Pro — every Pro tool degrades or fails without it.

Workflow 1 — floor plan to 3D print

plan_depot → pick the DXF (or plan_create from primitives).
plan_info(file_name) → confirm wall layers exist.
plan_to_svg(file_name) → visual sanity check of walls/openings.
plan_analyse(file_name) → rooms, areas, doors/windows.
plan_extrude(file_name, wall_height=3.0, wall_thickness=0.3) → STL.
Ship the STL to freecad-mcp (POST /api/v1/freecad/solid) for solid work.

Workflow 2 — annotate an existing drawing (QCAD Pro)

qcad_status() → installed + running must both be true.
plan_dimension / plan_text / plan_hatch with explicit coordinates.
plan_render(file_name, format="pdf") → high-fidelity proof.
Never invent coordinates — read them from plan_measure or plan_info bounding boxes first.

Read the full file on GitHub · 69 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

11d ago First seen · 69 lines · 41 tokens per session scan A 44dbf2da47fe

Subscribe to this mod's changes

qcad-cad is a skill published in the GitHub repository sandraschi/qcad-mcp (17 stars, last pushed 9d ago), licensed MIT. It adds 41 tokens to every session and 895 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-10.

3d-extrusion Design and UX Hardware and IoT architecture-cad fastmcp-3 mcp-server qcad webapp

autonomous-modeling

Use this skill to autonomously design and model complex 3D objects in Blender. Perfect for generating chassis, robots, and environment props from natural language.

sandraschi/blender-mcp · 36 tokens

freecad-expert

FreeCAD MCP is a FastMCP 3.4+ server providing 46+ CAD/CAM/CAE tools. It operates through a TCP bridge to FreeCAD GUI or via FreeCADCmd subprocess fallback.

sandraschi/freecad-mcp · 0 tokens

streamdeck-designer

Design, theme, and author complete Stream Deck layouts for the user's hardware using the streamdeck-mcp tools. Use whenever the user wants a custom Stream Deck setup, asks for a themed deck (e.g. "hello-kitty Twitch deck", "retrowave music controls", "a dev deck for this repo"), wants buttons or dials configured for…

verygoodplugins/streamdeck-mcp · 167 tokens

qcad-cad