Skip to main content
Glama
beiming183-cloud

AutoCAD MCP Server - Codex Edition

drawing

Manage CAD file lifecycle: create, open, save, export DXF/PDF, audit, and control state via undo/redo and system variables.

Instructions

Drawing file management.

Operations: activate - Activate a known document without changing window focus. data: {doc_id, expected_revision, lease_token?, worker_generation?} create — Create a new empty drawing. data: {name?} open — Open an existing drawing. data: {path} info — Get drawing extents, entity count, layers, blocks. save — Save current drawing. data: {path?} (saves to path if given, else QSAVE) save_as_dxf — Export as DXF. data: {path} plot_pdf — Plot to PDF. data: {path} render_preview — Native deterministic preview. data: {path, paper?, orientation?, plot_style?} Optional visual_style: Conceptual, Realistic, Shaded, or ShadedWithEdges. The style is applied only for the render and restored by default. workspace — Show the managed output workspace and folder layout. deliver — Build a validated DWG/DXF/PDF job with audits and SHA-256 checksums. audit — Structured drawing audit. data: {limit?, include_entities?, changed_only?, layer?, space?} audit_dxf — Parse an existing DXF into normalized JSON. data: {path, limit?, include_entities?} setup_mechanical — Create the seven monochrome GB/T mechanical-drafting layers. purge — Purge unused objects. get_variables — Get system variables. data: {names: [...]} set_variables — Safely set whitelisted system variables. data: {values: {...}} audit_geometry — Run line/polyline geometry DRC and return structured findings. undo — Undo last operation. redo — Redo last undone operation.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dataNo
operationYes
include_screenshotNo
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With only readOnlyHint: false in annotations, the description carries the load and does so well. It discloses specific behaviors such as activate 'without changing window focus', save behavior ('else QSAVE'), and render_preview's style restoration. These details go beyond the annotation and help the agent predict side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a well-organized, front-loaded list. While lengthy, every line introduces a distinct operation with a brief explanation, avoiding filler or redundancy. The monospaced operation names aid quick scanning, and the overall structure is appropriate for a tool with many sub-functions.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity and minimal schema/no output schema, the description covers each operation's purpose and most data inputs, which is substantial. It lacks details on return values and doesn't explain concepts like 'managed output workspace', but the operation list is largely sufficient for an agent to invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema provides no descriptions (0% coverage). The description compensates by specifying data structures for many operations (e.g., activate's doc_id, expected_revision; open's path; audit's filters), and implicitly defines operation values. However, include_screenshot is never mentioned, and not all operations have their data payloads fully specified, leaving gaps.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states 'Drawing file management' and then enumerates 17 distinct operations (create, open, save, plot_pdf, etc.), each with a specific verb and resource. This clearly distinguishes the tool from siblings like entity, layer, and product, leaving no ambiguity about its scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus sibling tools, nor on how to choose among the many operations. The list of operations is self-explanatory as a menu, but there are no contextual triggers, prerequisites, or exclusions, leaving the agent to infer usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/beiming183-cloud/AutoCAD-MCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server