Autocad-MCP: Instructions file for Claude Code

CLAUDE.md

Autocad-MCP CLAUDE.md is an instructions file for Claude Code from U-C4N/Autocad-MCP. It costs 3,593 tokens per session, scanned A, original, MIT.

A project guide for an AutoCAD automation server that lets coding agents work with AutoCAD or edit drawing files without opening AutoCAD.

In plain words
What is it for?
Running the server through agent clients, choosing between live Windows/AutoCAD access and headless file editing, installing optional features, and running tests.
Why use it?
It puts setup, connection modes, installation options, and test commands in one place, so developers do not have to infer how the server works.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is U-C4N/Autocad-MCP's own configuration. It tells Claude Code how to work on Autocad-MCP itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Autocad-MCP configures →

Reuse

Borrowing it

Nothing to install: this file belongs to U-C4N/Autocad-MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/U-C4N/Autocad-MCP/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/U-C4N/Autocad-MCP

Made for: Claude Code.

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.

agentmods badge for Autocad-MCP CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/u-c4n/autocad-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/u-c4n/autocad-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/u-c4n/autocad-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/u-c4n/autocad-mcp/claude-md/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.

agentmods 80×15 button for Autocad-MCP CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/u-c4n/autocad-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/u-c4n/autocad-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,593 This file is loaded in full into every session.
When invoked 3,593 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.03593 $0.03593
Opus 5 $0.01796 $0.01796
Sonnet 5 $0.00719 $0.00719
Haiku 4.5 $0.00359 $0.00359

Measured 9d ago against content hash b66b7f000397, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

Autocad-MCP CLAUDE.md 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 9d 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.

CLAUDE.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

AutoCAD MCP Pro is a FastMCP 3.0 server that exposes ~154 tools, 6 resources, and 5 prompt templates for AutoCAD automation. (The exact tool count is reported dynamically by system_status / system_about — never hardcode it.) It runs with a dual-engine architecture: a live COM backend (Windows/AutoCAD required) and a headless ezdxf backend (works anywhere).

Running the Server

# STDIO mode (default, for MCP clients like Claude Desktop)
python server.py

# HTTP mode
fastmcp run server.py:mcp --transport http --port 8000

# Force a specific backend
AUTOCAD_MCP_BACKEND=ezdxf python server.py   # headless file ops
AUTOCAD_MCP_BACKEND=com python server.py     # live AutoCAD (Windows only)
AUTOCAD_MCP_BACKEND=auto python server.py    # auto-detect (default)

Installation

# Core (ezdxf backend only)
pip install -e .

# With COM backend (Windows + AutoCAD)
pip install -e ".[com]"

# With PDF/screenshot support via matplotlib
pip install -e ".[pdf]"

# Everything
pip install -e ".[full]"

Running Tests

pytest
pytest tests/test_specific.py::test_name   # single test
pytest -x                                   # stop on first failure

Uses pytest-asyncio for async test support.

Architecture

Dual-Backend Pattern

The server uses a strategy pattern with an abstract base:

  • backends/contracts/ — the interface, one module per domain (drawing.py, layouts.py, entity_creation.py, …). Split in v1.5.0 out of a single 1854-line ABC; some slices (premium, gdt, settings) also carry shared concrete implementations, so they are mixins rather than pure interfaces.
  • backends/capability.py — the refusal vocabulary (UnsupportedCapabilityError) plus @capability(key, reason=...), which marks a contract method optional and gives it a default that raises that refusal. Use it only for genuine engine boundaries, never for an unfinished method; @abstractmethod stays the default. Every key used must be declared in both capability maps — tests/test_capability_contract.py fails otherwise, which is what stops the decorator becoming a way to ship undeclared holes.
  • backends/base.py — shared dataclasses (EntityInfo, LayerInfo, BlockInfo, DrawingInfo, CapabilityMap) and the AutoCADBackend composition of every contract. Import surface is unchanged: from backends.base import AutoCADBackend, UnsupportedCapabilityError still works.
  • backends/ezdxf_backend.pyEzdxfBackend: file-based DXF operations using the ezdxf library. All sync ezdxf calls are wrapped with asyncio.to_thread via _async(). Transactions are implemented as full DXF snapshots on an _undo_stack.
  • backends/com_backend.pyComBackend: live AutoCAD control via pywin32 COM. All COM calls are routed through a ThreadPoolExecutor with a single thread to satisfy AutoCAD's STA (Single-Threaded Apartment) COM requirement.

Read the full file on GitHub · 176 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.

  1. 9d ago First seen · 176 lines · 3,593 tokens per session scan A b66b7f000397

Subscribe to this mod's changes

Autocad-MCP CLAUDE.md is an instructions file published in the GitHub repository U-C4N/Autocad-MCP (74 stars, last pushed 1mo ago), licensed MIT. It adds 3,593 tokens to every session, about $0.0180 per session on Opus 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 2026-08-30.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens