原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。使用 Google 登录即可撰写评价。原型 · 每 30 分钟更新
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

Lambdacad MCP

注册名称io.github.Psalmustrack/lambdacad-mcp

安装方法

What it does

AI drafting, design review and a drawing memory in BricsCAD on Linux: 128 tools, pure AutoLISP

  • Connects –
  • Account or key No key needed
  • Category 设计、图片与音频

可搭配使用

教 AI 做这类工作的 Skill,可与本项一起使用

impeccable

The design vocabulary for your coding agent. Steer with polish and bolder, review with critique and audit, catch AI slop before it ships.

作者:pbakaus★ 112,5441 个 skill

Skill · 操作手册

diagram-design

Editorial diagram design for Claude Code, Codex, GitHub Copilot, Cursor, Factory Droid, Qoder, and Pi. 45 diagram types. Self-contained HTML + SVG. No shadows. No Mermaid slop.

作者:cathrynlavery★ 68,0691 个 skill

Skill · 操作手册

frontend-slides

Create beautiful slides on the web using a coding agent's frontend skills

作者:zarazhangrui★ 32,5141 个 skill

Skill · 操作手册

为什么排在这里

列表按使用分(满分 100)排序,由以下部分组成

热度7/80GitHub 星标或每周下载量:较大的计 60,较小的计 20
新鲜度3/1230 天内有发布或代码更新得满分
仍在响应0/8上次检查时云端端点有响应
使用分10/100

质量: 基础检查通过 3/3 项(仅展示,不用于排序) · 上升势头: 暂无数据 (只用于“上升中”标签)

安装

选择你使用的 AI 应用,然后复制设置。

通过 3/3 项检查 · 在你的电脑上运行

第一步:你用哪个 AI?

选择你用的应用,步骤会显示在下方。

Claude 暂时无法连接 Lambdacad MCP

开发者尚未在 MCP 注册表中填写安装方式

ChatGPT 暂时无法连接 Lambdacad MCP

开发者尚未在 MCP 注册表中填写安装方式

你可以改用这些方式

B · 设计、图片与音频 类中能连接 ChatGPT 的其他服务器

从同类中使用较多的里挑选,仅限用地址即可连接、无需密钥的

Claude Code 暂时无法连接 Lambdacad MCP

开发者尚未在 MCP 注册表中填写安装方式

Cursor 暂时无法连接 Lambdacad MCP

开发者尚未在 MCP 注册表中填写安装方式

VS Code 暂时无法连接 Lambdacad MCP

开发者尚未在 MCP 注册表中填写安装方式

其他支持 MCP 的应用(如 Windsurf、Zed、Gemini CLI)添加方式各不相同,请在应用列表中查看

查看所有支持 MCP 的应用 →

JSON 设置在下方“开发者专用”中

卡住了?问问正在用 Lambdacad MCP 的人💬 讨论 →

一览

每周下载量i
不在 npm/PyPI 上
许可证i
Apache-2.0
连接方式
–
最新版本i
1.3.0
发布到注册中心i
2026年8月16日
代码最后更新i
2026年8月16日
作者
Psalmustrack
注册状态
活跃

它能做什么

它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。

基础检查i

我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月19日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 Psalmustrack 验证,该账户拥有此仓库

  • ✓ 通过

    仍在维护

    代码最后更新于3个月前

  • ✓ 通过

    有许可证

    使用 Apache-2.0

  • – 不适用

    端点有响应

    它在你的电脑上运行,没有互联网端点

  • – 不适用

    使用 OAuth 登录

    在你的电脑上运行,改用本地设置

  • … 尚未检查

    工具描述中没有隐藏指令

    它在你的电脑上运行;我们只能读取互联网端点的工具列表

我们检查什么 → · JSON

作者:申请重新检查或报告信息错误
给作者:在 README 中加徽章

如果你是作者,可把这段代码贴到 README。徽章会链接回本页。

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/psalmustrack-lambdacad-mcp.svg)](https://mcp.popnx.com/en/servers/psalmustrack-lambdacad-mcp)

讨论

提问、分享技巧或报告无法使用。按“有帮助”数量排序。

还没有帖子,欢迎第一个提问或分享。

此处内容由用户撰写,不代表 PopNx 团队。

登录后发帖

用户评价

还没有评价

登录后写评价

与“设计、图片与音频”中的其他服务器比较i

  • 星标数多于此分类中其他 3275 个服务器的 88%
  • 发布到注册中心的时间比此分类中其他 3275 个服务器的 19% 更新
  • 基础检查结果等于或优于此分类中其他 3275 个服务器的 99%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。

常见问题

Lambdacad MCP 安全吗?

它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。

它需要哪些密钥或代码?

注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端?

它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。

它还在维护吗?

GitHub 仓库最后更新于3个月前,最新版本(1.3.0)于3个月前进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。

有什么可以替代它?

同一分类中有:HyperFrames by HeyGen, Pascal 3D Editor, draw.io, Figma MCP Server, Remocn: Remotion MCP server

功能相近的其他选择

同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。

如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Pascal 3D Editor

Create, inspect, validate, and save editable 3D building scenes with Pascal's MCP server.

作者:pascalorg广泛使用↓ 1037/周★ 2.6万 整个仓库的星标昨天更新

电脑或云端✓ 服务方 · pascal.app

draw.io

Create draw.io diagrams in chat from Mermaid or XML, shown live and interactive. 10,000+ shapes.

作者:jgraph广泛使用★ 5848前天更新

在云端运行✓ 服务方 · draw.ioPopNx 团队已实际试用

Figma MCP Server

The Figma MCP server brings Figma design context directly into your AI workflow.

作者:figma广泛使用★ 220713个月前更新

在云端运行✓ 服务方 · mcp.figma.com
与相似项目对比
本项
Lambdacad MCP
HyperFrames by HeyGenPascal 3D Editordraw.ioFigma MCP ServerRemocn: Remotion MCP server
运行位置需要安装在电脑上在云端运行,无需安装云端或安装在电脑上都可以在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装
需要密钥否否否否否否
可在 Claude 中按 + 添加否是否否是否
基础检查3/34/45/54/44/44/4
许可证Apache-2.0Apache-2.0MITApache-2.0–MIT
价格登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

λ lambdacad-mcp

Let AI draw in your CAD. An MCP server for any AutoLISP-capable CAD — no COM, no SDK, no plugins. Pure AutoLISP. The reference adapter drives BricsCAD on Linux: the first MCP server for a professional DWG CAD on Linux.

*"Draw a DN80 flange: front view, hatched section, dimensions — then model it in 3D."*

*Real-time capture, unedited: front view with bolt circle, hatched section, radial/diameter dimensions, leader, title block — then the same flange modeled as a 3D solid with an AI-written parametric AutoLISP loop and one boolean subtraction. ~20 seconds, 12 tool calls.*

Complete 2D drawing, drawn by Claude3D solids with booleansClean render for AI vision

Why this exists

Every other MCP server for a professional DWG CAD (multiCAD-mcp, autocad-mcp, CAD-MCP, ...) talks to the CAD through Windows COM — none of them can run on Linux, and none of them does real 3D.

BricsCAD is the professional DWG CAD that *does* run natively on Linux. This server drives it through a mechanism that needs no API at all: an AutoLISP file bridge. The MCP server writes LISP expressions to a file, triggers a tiny MCP command inside the CAD, and reads the result back. That's the whole trick — and it unlocks everything the CAD can do, including 3D solid modeling.

Because the bridge is plain AutoLISP + standard DXF entmake + AutoCAD-compatible commands, it is portable by construction: AutoCAD, ARES Commander (also Linux-native!), ZWCAD, GstarCAD and the IntelliCAD family all speak the same language. Porting means swapping the autoload file name and the keystroke trigger — adapters welcome.

MCP client (Claude, Cursor, ...)            BricsCAD (Linux)

│ │ ▼ ▼ server.py (FastMCP, 128 tools) c:MCP AutoLISP command │ writes LISP ──► /tmp/mcp_bricscad.in │ triggers via xdotool ──► reads, evals line by line │ reads result ◄── /tmp/mcp_bricscad.out

What it can do

  • Full 2D drafting — lines/arcs/polylines/splines, line weights per layer (0.50 walls / 0.35 edges / 0.18 dimensions — measured on the plotted page, not just set), real HATCH (with islands), dimensions incl. radius/diameter/angular, leaders, linetypes (chain/hidden), text styles, trim/extend/fillet/chamfer/offset/mirror/arrays, blocks
  • Semantic shapes — slot, bolt_circle, rounded_rect, polygon, center_mark: one call, the server does the math
  • 3D solid modeling — box/cylinder/sphere/cone/wedge/torus, extrude/revolve/sweep, union/subtract/intersect, slice, fillet/chamfer on solid edges, 3D move/rotate around any axis — and `flatshot_view`: auto-generate correct 2D drawing views from the 3D model
  • Batch & atomic — draw_batch executes N operations in one round-trip, wrapped in one undo group (one batch = one Ctrl+Z)
  • Talk about what the user selected — get_selection reads the GUI pickfirst set; select_by/select_window highlight what the AI found *before* acting; modify tools accept "selection"
  • Verification without screenshots — bounding boxes, key points, exact lengths/areas, intersection checks (collision detection), solid volume/centroid
  • Design review — tools that answer an engineering question, not just run a command *(new in 1.2)* — boolean_verified cuts *and measures* the change against the volume you expected (a cut that lands short reads SHORT, not success); overhang_report reads the STL mesh and says whether a part prints without supports, scoring all six orientations; contact_report over an assembly (assembly_place/assembly_list/assembly_clear) says who touches whom, who interferes, and who is an orphan — a part touching nothing, because its job was superseded and nobody noticed; hole_report physically probes every hole and says which are actually open (a drawing lies about its holes until something checks); graph_build/graph_trace read the 2D geometry as a connectivity graph — separate networks, exact run lengths, and the open ends that are real breaks vs T-junctions, with the joining tolerance *emerging from the drawing* instead of hardcoded
  • The drawing REMEMBERS *(new in 1.3, beta)* — memory_enable puts a journal beside the .dwg that the CAD writes by itself, catching the edits the *human* makes in the GUI while no tool is running; tag_entity gives entities semantic roles ("muro-nord", "asta-principale") keyed to handles, which survive save and reopen; world_report answers *what is here, what did I call it, what changed since I last looked* — and revalidates every claim against the live drawing before answering (an entity erased behind the AI's back reads DEAD (erased since tagging), reported, never hidden). The next prompt — or the next session — starts knowing the drawing instead of re-surveying it
  • Instructions in the protocol *(new in 1.2)* — the server ships the rules that cannot be learned by trying (OK is not evidence; calibrate before trusting; booleans keep the first handle; one line is one complete expression; consult the drawing's memory first), plus a lambdacad://traps resource that costs nothing until read
  • Eyes when needed — render_view: BricsCAD's internal PNG render (clean, no UI, ~30 KB) for vision models
  • Sheets, at a real scale — create_sheet (A4…A0, margins zeroed so paper mm = sheet mm), add_viewport (ask for 1:50 and it *is* 1:50 — measured back off the entity, and parked on a non-plotting layer), fit_viewport (measures what is drawn and picks the largest STANDARD scale that fits — 1:37 is not a scale), title_block (border + ISO 7200 cartouche, sized from the sheet), export_sheet_pdf, which checks its own work by measuring the page of the PDF it just wrote
  • Deliverables — save DWG, export DXF, PDF and STL (export_stl: 3D solids straight to the slicer, parked on the origin)
  • Several drawings open — list_documents shows which one the tools are pointing at (plus unsaved changes and read-only), use_document picks another; every reply says which drawing answered, and warns when it changes underfoot
  • Escape hatch — run_lisp evaluates arbitrary AutoLISP (multi-line, multi-expression): capable models write parametric code and love it

Full reference: docs/TOOLS.md · How it works: docs/ARCHITECTURE.md

Measured, not promised

MetricResult
Tool calls for a complete dimensioned flange200 → 22 (9× fewer round-trips vs primitive-per-call)
Trigger latency0.25 s per call
Error reportingper-line LISP errors (msg=L2: ...) → models self-correct without screenshots
Exactnessentity_length on an r=20 circle: 125.664 / 1256.637 (2πr, πr² exact)

Details and model-behavior notes (Sonnet writes parametric LISP, Haiku uses typed tools): docs/BENCHMARKS.md

Tests

BRICS_DISPLAY=:0 python tests/test_tools.py     # ~135 checks incl. review + memory groups, ~2-4 min

python tests/test_tools.py 3d edges export # or just some groups python tests/test_tools.py --list

An integration suite: it drives the CAD you already have running, then measures what came out — closed-form volumes, bounding boxes, the value stored inside a dimension, triangle counts read out of the STL. Never "no error".

That distinction is the whole point. The bridge answers OK whenever the CAD accepted the command, which is not the same as the CAD having done what was asked. Every bug found so far was of that shape: the classic CHAMFER silently switching to *all edges*; a layout that plots rotated 90°, so an A3 landscape sheet comes out portrait, the drawing falls off the paper and the export writes a perfectly valid, entirely empty page; and — the one that reached a release — running object snap dragging programmatic coordinates onto nearby geometry, so five blocks placed in a row each landed on the previous. A volume, a bounding box, a measured dimension and the page of a PDF are exact signatures: every one of those surfaced as arithmetic that did not add up.

The suite draws in a scratch region (x ≥ 50000), erases it afterwards, and fails if the entity count does not come back to where it started. It still works in the active drawing, so point it at a scratch one.

Usage telemetry (local only)

With 128 tools, the interesting question is which ones earn their place — and which fail often enough to signal a docstring or design problem. The server appends one JSON line per call to ~/.lambdacad/usage.jsonl:

{"t": 1786526823.4, "tool": "draw_batch", "ms": 198, "err": 0}

Tool name, duration, error flag. Never the arguments — no coordinates, no paths, no drawing data — and nothing ever leaves your machine. Disable with LAMBDACAD_TELEMETRY=0.

python scripts/usage_report.py              # per-tool calls, error rate, p50

python scripts/usage_report.py --core 95 # smallest set covering 95% of calls python scripts/usage_report.py --reset # archive the current log

The --core output is a data-driven candidate for CORE_TOOLS (compact mode): after a few weeks of real use, the choice of which tools deserve a place in a schema-limited client stops being a guess. Early signal from the integration suite itself: run_lisp alone is ~half of all calls — on clients that load schemas on demand (Claude Code's tool search), the long tail of typed tools costs nothing until used, so the rich docstrings stay.

Quick start

Requirements: Linux, BricsCAD (any recent version — tested on V26), Python 3.10+, xdotool.

git clone https://github.com/Psalmustrack/lambdacad-mcp

cd lambdacad-mcp ./install.sh

The installer creates a venv, installs the AutoLISP bridge into BricsCAD's Support/on_doc_load.lsp (idempotent, marker-delimited), and prints ready-to-paste config for Claude Code / Claude Desktop.

Then:

  1. Start BricsCAD and open a drawing (the bridge loads when a document opens).
  2. Start a new AI session — the bricscad tools appear.
  3. Ask: *"draw the plan of a 4×3 m room with a door and dimensions"*.
Configuration (env vars)
VariableDefaultPurpose
BRICS_DISPLAYsession $DISPLAYX display where BricsCAD runs (e.g. :77 for a nested Xephyr)
BRICS_COMPACToff1 = expose only 14 essential tools (~1k schema tokens instead of ~7k) for clients that inject every schema
BRICS_MCP_IN / BRICS_MCP_OUT/tmp/mcp_bricscad.{in,out}bridge file paths

Security note

run_lisp and run_command execute arbitrary code inside BricsCAD by design — that's what makes the server fully general. O

只显示了开头部分;其余内容请在仓库中阅读