# DWG

> Use this tool when you need to read and inspect AutoCAD DWG files with AI agents, solving problems such as accessing drawing contents and querying object properties. It provides a read-only interface for opening files, listing object types, and fetching objects, with inputs including file paths and object handles, and outputs including drawing contents and object properties. Ideal for use cases requiring efficient in-memory document indexing and management of AutoCAD files.

Canonical page: https://skillsregistry.net/skills/dimitrovakulenko-dwg  
JSON: https://api.skillsregistry.net/v1/skills/dimitrovakulenko-dwg

## Description

DWG is an MCP server for reading and inspecting AutoCAD DWG files with AI agents. It provides read-only access to drawing contents through tools for opening files, listing object types, fetching objects by handle, and querying properties, scopes, and references. The server uses a Rust worker process backed by LibreDWG for efficient in-memory document indexing, managed by a Python MCP host.

## Trust

- **Trust score (0–1):** 0.34
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-01

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/dimitrovakulenko-dwg)
- **Repository:** <https://github.com/dimitrovakulenko/dwg-mcp-server>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "dimitrovakulenko-dwg"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/dimitrovakulenko-dwg` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/dimitrovakulenko-dwg/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt
