impeccable
The design vocabulary for your coding agent. Steer with polish and bolder, review with critique and audit, catch AI slop before it ships.
Slice, preview and diagnose 3D prints in Anycubic Slicer Next, then send and watch them
作者提供的原文
教 AI 做这类工作的 Skill,可与本项一起使用
The design vocabulary for your coding agent. Steer with polish and bolder, review with critique and audit, catch AI slop before it ships.
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.
Create beautiful slides on the web using a coding agent's frontend skills
列表按使用分(满分 100)排序,由以下部分组成
| 热度 | 0/80 | GitHub 星标或每周下载量:较大的计 60,较小的计 20 |
|---|---|---|
| 新鲜度 | 12/12 | 30 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 | 12/100 |
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)
选择你使用的 AI 应用,然后复制设置。
用一句话让 AI 帮你安装
请帮我安装 Anycubic Slicer MCP。按照 https://mcp.popnx.com/i/pri-te-sh-anycubic-slicer-mcp.md 操作,先把命令给我看,等我同意后再运行。粘贴到能在你电脑上工作的 AI(如 Claude Code、Cursor)。它会读取我们的步骤,先给你看命令,等你同意。无需密钥,无需注册。 · 查看 AI 会读取的全文
通过 3/3 项检查 · 在你的电脑上运行 · ✓ 命令已检查 2026年11月18日
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
可连接 Claude,但需要先准备
需要先在电脑上安装 Python (uv)(只需一次) · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用
把这段话复制到 Claude 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 Claude 安装 MCP server Anycubic Slicer MCP,按顺序:1) 用 uv --version 检查是否有 uv。没有的话,请让我从 https://docs.astral.sh/uv/getting-started/installation/ 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):{ "mcpServers": { "anycubic-slicer": { "command": "uvx", "args": [ "anycubic-slicer-mcp" ] } } } 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 Anycubic Slicer MCP 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
uv --versionMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: uv 没有点选式安装程序。从 uv 官方页面复制适合你系统(macOS 或 Windows)的一行命令,粘贴到终端 · 不需要单独安装 Python,uv 会在需要时自动下载
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: uv --version
安装一次,所有需要 uv 的工具都能用
SettingsDeveloperEdit Config
{
"mcpServers": {
"anycubic-slicer": {
"command": "uvx",
"args": [
"anycubic-slicer-mcp"
]
}
}
}用 Anycubic Slicer MCP 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude 说正在使用 Anycubic Slicer MCP,或回答中出现 Anycubic Slicer MCP 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
ChatGPT 暂时无法连接 Anycubic Slicer MCP
Anycubic Slicer MCP 需要安装在你的电脑上,而 ChatGPT 只能连接在网上运行的服务器
A · 使用能连接 Anycubic Slicer MCP 的应用
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
可连接 Claude Code,但需要先准备
需要先在电脑上安装 Python (uv)(只需一次)
把这段话复制到 Claude Code 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 Claude Code 安装 MCP server Anycubic Slicer MCP,按顺序:1) 用 uv --version 检查是否有 uv。没有的话,请让我从 https://docs.astral.sh/uv/getting-started/installation/ 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):claude mcp add --scope user anycubic-slicer -- uvx anycubic-slicer-mcp 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 Anycubic Slicer MCP 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
uv --versionMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: uv 没有点选式安装程序。从 uv 官方页面复制适合你系统(macOS 或 Windows)的一行命令,粘贴到终端 · 不需要单独安装 Python,uv 会在需要时自动下载
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: uv --version
安装一次,所有需要 uv 的工具都能用
Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell
claude mcp add --scope user anycubic-slicer -- uvx anycubic-slicer-mcp应能看到 Anycubic Slicer MCP 在列表中并显示已连接
用 Anycubic Slicer MCP 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude Code 说正在使用 Anycubic Slicer MCP,或回答中出现 Anycubic Slicer MCP 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Cursor,但需要先准备
需要先在电脑上安装 Python (uv)(只需一次)
把这段话复制到 Cursor 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 Cursor 安装 MCP server Anycubic Slicer MCP,按顺序:1) 用 uv --version 检查是否有 uv。没有的话,请让我从 https://docs.astral.sh/uv/getting-started/installation/ 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):{ "mcpServers": { "anycubic-slicer": { "command": "uvx", "args": [ "anycubic-slicer-mcp" ] } } } 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 Anycubic Slicer MCP 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
uv --versionMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: uv 没有点选式安装程序。从 uv 官方页面复制适合你系统(macOS 或 Windows)的一行命令,粘贴到终端 · 不需要单独安装 Python,uv 会在需要时自动下载
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: uv --version
安装一次,所有需要 uv 的工具都能用
用 Anycubic Slicer MCP 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Cursor 说正在使用 Anycubic Slicer MCP,或回答中出现 Anycubic Slicer MCP 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同
可连接 VS Code,但需要先准备
需要先在电脑上安装 Python (uv)(只需一次)
把这段话复制到 VS Code 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 VS Code 安装 MCP server Anycubic Slicer MCP,按顺序:1) 用 uv --version 检查是否有 uv。没有的话,请让我从 https://docs.astral.sh/uv/getting-started/installation/ 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):{ "servers": { "anycubic-slicer": { "type": "stdio", "command": "uvx", "args": [ "anycubic-slicer-mcp" ] } } } 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 Anycubic Slicer MCP 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
uv --versionMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: uv 没有点选式安装程序。从 uv 官方页面复制适合你系统(macOS 或 Windows)的一行命令,粘贴到终端 · 不需要单独安装 Python,uv 会在需要时自动下载
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: uv --version
安装一次,所有需要 uv 的工具都能用
用 Anycubic Slicer MCP 告诉我你能帮我做什么,然后做一件给我看✓ 如果 VS Code 说正在使用 Anycubic Slicer MCP,或回答中出现 Anycubic Slicer MCP 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同
Claude Code
claude mcp add --scope user anycubic-slicer -- uvx anycubic-slicer-mcpClaude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"anycubic-slicer": {
"command": "uvx",
"args": [
"anycubic-slicer-mcp"
]
}
}
}Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"anycubic-slicer": {
"command": "uvx",
"args": [
"anycubic-slicer-mcp"
]
}
}
}VS Code (mcp.json)
{
"servers": {
"anycubic-slicer": {
"type": "stdio",
"command": "uvx",
"args": [
"anycubic-slicer-mcp"
]
}
}
}这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
在你的电脑上运行,适用于
ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
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。
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20日
注册名称已通过 GitHub 账户 pri-te-sh 验证,该账户拥有此仓库
代码最后更新于前天
使用 MIT
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
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
尚未检查
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/servers/pri-te-sh-anycubic-slicer-mcp)提问、分享技巧或报告无法使用。按“有帮助”数量排序。
还没有评价
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。
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。
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)。
GitHub 仓库最后更新于前天,最新版本(1.4.1)于前天进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Python (uv)。
同一分类中有:HyperFrames by HeyGen, Pascal 3D Editor, draw.io, Figma MCP Server, Remocn: Remotion MCP server
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
Official HyperFrames by HeyGen: the best AI video editor in chat. Captions, motion graphics, MP4.
Create, inspect, validate, and save editable 3D building scenes with Pascal's MCP server.
Create draw.io diagrams in chat from Mermaid or XML, shown live and interactive. 10,000+ shapes.
The Figma MCP server brings Figma design context directly into your AI workflow.
Hosted MCP for Remotion videos: search Remocn components, read docs, plan a video, preview it.
| 本项 Anycubic Slicer MCP | HyperFrames by HeyGen | Pascal 3D Editor | draw.io | Figma MCP Server | Remocn: 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 | 3/3 | 4/4 | 5/5 | 4/4 | 4/4 | 4/4 |
| 许可证 | MIT | Apache-2.0 | MIT | Apache-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 |
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。
Website · Install · Tools · FAQ · Contribute
Anycubic Slicer MCP is an open-source Model Context Protocol server for Anycubic Slicer Next on Windows and macOS. It lets Claude, Cursor, Codex, Antigravity, DeepSeek Harness or any other MCP client slice STL, 3MF, OBJ and STEP files, preview the G-code and plan a print before you commit filament to it.
You can ask for things like:
The server drives the slicer's own command line on your computer, so you check the preview before anything is printed. It can also send a print to your printer and watch it: directly over LAN mode, or through the slicer window when the printer stays on Anycubic Cloud. Anything that starts, pauses or stops a print waits for your yes in the chat.
slice_model takes preset names (or the selection in the slicer window) and any setting override by name: infill, walls, supports, brim, layer height, temperatures. It handles rotation, scale, copies and multi-colour plates, and writes both a .gcode file and a printer-ready .gcode.3mf.
A real run on the example gear, with a Kobra X and 0.4 mm nozzle: 30m 48s, 9.66 g of PLA, 45 layers at 0.2 mm.
| One layer, coloured by feature | Every layer, shaded by height | Shareable print card |
|---|---|---|
preview_gcode also draws a side view for checking overhangs and supports. animate_layers saves a GIF of the print building up.
Your agent reads the spool label (brand, material, colour, temperature ranges, weight) and create_filament_profile turns it into a preset that inherits from the closest one your printer already has. It shows a preview first and saves only when you confirm. Spools can go into a small local inventory, so the agent can tell you which one has enough left for the next print.
Send photos of a failed print. The agent matches what it sees to one of 13 defects (stringing, warping, layer adhesion, first layer, under and over extrusion, elephant foot, ringing, overhangs, bridging, top surface, layer shift and seams). diagnose_print then suggests setting changes based on the presets you used. When two fixes would push the same setting in opposite directions, it reports the conflict and leaves that setting alone.
Tell it how the part is loaded (tension, compression, bending, impact or torsion) and in which direction. analyze_strength looks for thin waists in the shape and recommends an orientation and settings. find_best_orientation ranks ways to lay the model on the bed for least support, speed, strength, bed adhesion or a balance of them.
On a single-nozzle printer every colour change flushes filament. In a test on a Kobra X with two 15 mm cubes, one black and one white, 8.31 g of a 9.99 g print went to colour changes. optimize_multicolor measures that waste for your model, tests settings that might reduce it, and recommends one only if every colour is kept and it saves filament. It also suggests layout changes.
Point the agent at a folder or a .zip of parts. plan_project finds every model and reads counts from names like clip_x4.stl and from a README. It lays each part in its best orientation and packs the parts onto plates. You can group for the fewest plates or by colour, cap each plate at a number of hours, and keep parts that need supports together.
It doesn't guess when the files are unclear. It returns questions for the agent to put to you, and the blocking ones must be answered before slice_project will run:
lid_v1, lid_v2): which to print?Each plate is sliced as its own .gcode.3mf. If the slicer can't fit everything on a plate, the extras move to the next one. In a test with an 11-file kit, three questions settled it and the result was one plate of 14 pieces: 2h 32m 23s and 71.62 g.
A Kobra X runs either in LAN mode or on Anycubic Cloud, not both: with LAN mode on, the cloud and the phone app's remote control stop. The server works with either.
LAN mode (printer screen: Settings > Network > LAN Mode). The server talks to the printer directly over your network, using the protocol the community has documented for the Kobra X, S1 and Kobra 3 family. No Anycubic account is involved.
printer_status reports the state, the job's progress and time left, nozzle and bed temperatures against their targets, the filament in each slot, how the last print ended, and any error code with Anycubic's meaning and a link to the fix.printer_camera_snapshot takes a photo with the built-in camera so the agent can look at the bed.send_print uploads a sliced .gcode.3mf and starts it. First it shows what will happen: the file's time and weight, which slot each filament comes from, and whether the printer is idle and is the model the file was sliced for. It refuses a filament that doesn't match the slot's material.control_print pauses, resumes or stops the current print.Anycubic Cloud (LAN mode off, so the phone app keeps working). Anycubic doesn't publish a cloud API, so the server goes through the slicer window, which is already signed in to your account. The server never sees your login.
cloud_printer_status reads the window's Workbench screen: state, job, progress, layer, time left, temperatures, part fan, firmware and the loaded slots, plus a screenshot. With camera=True it also starts the Workbench camera and returns a picture of the bed, then stops the stream again.print_from_slicer opens the window's Start Print dialog for the plate you sliced there and reads it back: task, time, weight, filament, printer and whether it can take the job. It presses Start Print only after you confirm, and only if the dialog still shows the same plate.Starting, pausing, resuming and stopping always go in two steps: the tool previews what it will do, the agent asks you, and it acts only after you say yes in the chat.
Tested on a Kobra X with firmware 2.0.2.8 and Anycubic Slicer Next 2.0.0.3 on macOS:
| Tested on the real printer | Not yet tested on the real printer | |
|---|---|---|
| LAN mode | finding it, status, camera, the send_print preview, refusing PETG into a PLA slot, refusing to pause an idle printer | the actual upload and start; pause, resume and stop (tested against a simulated printer) |
| Anycubic Cloud | reading a live print from the Workbench, the camera, reading the Start Print dialog, refusing to start while the printer is busy, starting a first-layer test and following it through download, levelling and printing to the end | pausing or ending from the Workbench |
Some things only the window does, so the agent can use it too (macOS for now):
restart_slicer closes the window the normal way and reopens it with the presets you chose selected and a file open. The window only loads new presets when it starts. It never force-quits: if the window is asking whether to save a project, it tells the agent to ask you.slicer_screenshot returns a picture of just the slicer's window and the text in it.slicer_click clicks a button by its label, for example Slice plate or Cancel. Clicks only land inside the slicer window, and only while it's in front. Buttons that start, send, pause, stop, delete or discard something are refused unless you've said yes to that exact click.Screenshots need Screen Recording permission and clicks need Accessibility permission for the app that runs the server (System Settings > Privacy & Security). Both are your call.
make_calibration_print generates and slices a temperature tower (it changes the nozzle temperature at each block for you), flow-ratio cubes, retraction towers, or five first-layer squares spread across the bed.
compare_slices runs up to eight variants side by side. estimate_cost adds electricity and any labour or markup. check_bed_fit says whether a model fits and suggests a 45° turn, scaling, laying it down or splitting it if it doesn't.
You need:
Then install the server:
uv tool install --python 3.13 anycubic-slicer-mcp
That puts an anycubic-slicer-mcp command on your PATH (uv tool dir --bin prints where).
To try it without installing, any MCP client can also run it straight from PyPI with `u