# TechDraw AI

TechDraw AI is a Claude Code MCP server that turns a part photo or written description into technical drawings, CAD files, and 3D models. Ask it to draft a drawing, trace DXF contours, or render a product.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 5 repo stars
- Author: MeltFlexDevs
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/MeltFlexDevs/techdrawai-skills
- Updated: 2026-10-13
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/techdraw-ai

## What it does

TechDraw AI creates dimensioned drawings from part photos or written descriptions. It can also convert images into DXF or DWG, build 3D models, and render products. Other tools make an STL from flat artwork or identify an object in a photo.

Files go to `./techdrawai-output/` by default, or to a folder supplied in the request; the agent receives their paths. A known measurement anchors the scale. Without one, dimensions are estimates marked as nominal.

Use requires a Studio subscription and a personal `TECHDRAWAI_API_KEY`; generations draw on account credits. The server runs `techdrawai-mcp` through `npx` and calls the TechDraw AI API.

## Requirements
- Needs: Node.js (commands run via npx)
- Environment variables: `TECHDRAWAI_API_KEY` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add techdrawai -e TECHDRAWAI_API_KEY=<TECHDRAWAI_API_KEY> -- npx -y techdrawai-mcp
```
Replace <…> with your own values

### Codex

**Platform CLI**
```bash
codex mcp add techdraw-ai --env TECHDRAWAI_API_KEY=<TECHDRAWAI_API_KEY> -- npx -y techdrawai-mcp
```
Replace <…> with your own values

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "techdraw-ai": {
            "command": "npx",
            "args": [
                "-y",
                "techdrawai-mcp"
            ],
            "env": {
                "TECHDRAWAI_API_KEY": "<TECHDRAWAI_API_KEY>"
            }
        }
    }
}
```
Replace <…> with your own values

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "techdraw-ai": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "techdrawai-mcp"
            ],
            "env": {
                "TECHDRAWAI_API_KEY": "<TECHDRAWAI_API_KEY>"
            }
        }
    }
}
```
Replace <…> with your own values

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add -e TECHDRAWAI_API_KEY=<TECHDRAWAI_API_KEY> techdraw-ai npx -y techdrawai-mcp
```
Replace <…> with your own values

## When to use it
- draft a dimensioned drawing from a part photo
- convert an image or drawing into DXF or DWG
- turn flat artwork into a printable STL
- build a 3D model from a photo or technical drawing
- render a product from its technical drawing

## Example prompts
- Create a dimensioned drawing from this part photo and save it in the project folder.
- Convert `drawing.png` into a DXF with a width of 120 mm.
- Build a textured 3D model from `bracket.jpg`.

## Similar
- [Context7](https://affpapa.org/en/nevibecode/mcp/context7.md) — MCP server · 5563 installs
- [Search Google Flights](https://affpapa.org/en/nevibecode/mcp/search-google-flights.md) — MCP server · 2595 installs
- [Math-MCP](https://affpapa.org/en/nevibecode/mcp/math-mcp.md) — MCP server · 5958 installs
- [pipeworx gateway](https://affpapa.org/en/nevibecode/mcp/pipeworx-gateway.md) — MCP server · 419019 installs
- [SparkForge](https://affpapa.org/en/nevibecode/mcp/sparkforge.md) — MCP server · 219896 installs
- [OpenWebSearch](https://affpapa.org/en/nevibecode/mcp/openwebsearch.md) — MCP server · 494 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
