impeccable
The design vocabulary for your coding agent. Steer with polish and bolder, review with critique and audit, catch AI slop before it ships.
Run a custom-merch store from an agent: design, build products, list on every channel, fulfill.
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 | 20/80 | 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 | 8/8 | 上次检查时云端端点有响应 |
| 使用分 | 40/100 |
质量: 基础检查通过 5/5 项(仅展示,不用于排序) · 上升势头: 43 (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 ApparelHub。按照 https://mcp.popnx.com/i/apparelhub-ai-apparelhub-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 5/5 项检查 · 你的提问会经过开发者的服务器(mcp.apparelhub.ai) · ✓ 命令已检查 2026年11月19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 · 约 2 分钟
不需要密钥,不用安装程序 · 在 claude.ai 或桌面应用设置一次,即可在聊天中使用 · 免费账户可添加 1 个 · Team/Enterprise 方案由所有者(Owner)添加
CustomizeConnectors
把这里的内容复制到 Claude 中同名的输入框,然后点击 Continue
ApparelHubhttps://mcp.apparelhub.ai在 Claude 检测到的登录设置页点击 Continue · Authentication 按作者说明选择(Sign in now、Sign in when needed 或 No sign in),然后点击 Add
+ConnectorsApparelHub
用 ApparelHub 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 ApparelHub,或回答中出现 ApparelHub 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
能否连接 ChatGPT 取决于方案
完整 MCP:网页版 ChatGPT Business、Enterprise 或 Edu · Pro:以读取/获取权限连接,修改数据的工具可能用不了 · Plus:官方文档尚未确认,如果在插件页看到添加自定义 MCP 的选项可以试试 · 仅限网页
Plugins+Add custom MCP server
输入名称,在 Connection 下粘贴地址,勾选风险提示,然后点击 Create as a plugin
ApparelHubhttps://mcp.apparelhub.ai开启新聊天,输入前先从插件列表中选择 ApparelHub
用 ApparelHub 告诉我你能帮我做什么,然后做一件给我看✓ 如果 ChatGPT 说正在使用 ApparelHub,或回答中出现 ApparelHub 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 OpenAI 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Claude Code · 约 2 分钟
不需要密钥,不用安装程序
Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell
claude mcp add --transport http --scope user apparelhub https://mcp.apparelhub.ai应能看到 ApparelHub 在列表中并显示已连接
用 ApparelHub 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 ApparelHub,或回答中出现 ApparelHub 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 · 约 2 分钟
不需要密钥,不用安装程序
用 ApparelHub 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 ApparelHub,或回答中出现 ApparelHub 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 · 约 2 分钟
不需要密钥,不用安装程序
用 ApparelHub 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 ApparelHub,或回答中出现 ApparelHub 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
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
通过网页连接的应用使用的地址
https://mcp.apparelhub.aiJSON 设置在下方“开发者专用”中
Claude Code
claude mcp add --transport http --scope user apparelhub https://mcp.apparelhub.aiCursor (~/.cursor/mcp.json)
{
"mcpServers": {
"apparelhub": {
"url": "https://mcp.apparelhub.ai"
}
}
}VS Code (mcp.json)
{
"servers": {
"apparelhub": {
"type": "http",
"url": "https://mcp.apparelhub.ai"
}
}
}Claude Code
claude mcp add --scope user apparelhub --env APPARELHUB_API_KEY=your-value -- npx -y @apparelhub/mcp-serverClaude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"apparelhub": {
"command": "npx",
"args": [
"-y",
"@apparelhub/mcp-server"
],
"env": {
"APPARELHUB_API_KEY": "your-value"
}
}
}
}Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"apparelhub": {
"command": "npx",
"args": [
"-y",
"@apparelhub/mcp-server"
],
"env": {
"APPARELHUB_API_KEY": "your-value"
}
}
}
}VS Code (mcp.json)
{
"servers": {
"apparelhub": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@apparelhub/mcp-server"
],
"env": {
"APPARELHUB_API_KEY": "your-value"
}
}
}
}APPARELHUB_API_KEY 机密 必填 env说明为自动翻译,变量名保持原样;不确定时请查看原文。
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。
通过互联网连接,适用于
ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast
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
服务器要求先登录,才会列出它的工具。
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 ApparelHub-AI 验证,该账户拥有此仓库
代码最后更新于昨天
使用 MIT
在 722 毫秒内响应(HTTP 401)
声明支持 OAuth 登录,你的 AI 应用可以带你去登录
尚未检查;我们会在检查端点时读取工具列表
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/apparelhub-ai-apparelhub-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 5 项适用的基础检查中通过了 5 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。
你需要填写:APPARELHUB_API_KEY
两种方式都可以:安装在你的电脑上,或者连接云端版本。
GitHub 仓库最后更新于昨天,最新版本(0.24.0)于昨天进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,因此也能用于接受远程 MCP 的应用,例如网页版 ChatGPT(Business 及以上为完整 MCP;Pro 为只读)。
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 ApparelHub | HyperFrames by HeyGen | Pascal 3D Editor | draw.io | Figma MCP Server | Remocn: Remotion MCP server | |
|---|---|---|---|---|---|---|
| 运行位置 | 云端或安装在电脑上都可以 | 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 | 是 | 否 | 否 | 否 | 否 | 否 |
| 可在 Claude 中按 + 添加 | 否 | 是 | 否 | 否 | 是 | 否 |
| 基础检查 | 5/5 | 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。
Workflow-level MCP tools that let an AI agent run an ApparelHub store end to end: set it up, design apparel, build products, list them across sales channels, and work the orders and listings that come back. Each tool wraps the ApparelHub Agent API and bakes in the platform's hard-won production lessons, so the agent gets correct behavior for free instead of learning the gotchas itself.
There are two ways to run it: a hosted connector you authorize with OAuth (recommended, no API key to handle) and this npm package you run yourself with a key. Both serve the identical tool surface.
Status: early access. The npm package is pre-1.0 while the surface stabilizes. The
agent-facing tool surface is v1 and is the contract we keep stable (see
CHANGELOG.mdand Versioning).
A thin wrapper around a REST API just renames HTTP calls. These tools are at the workflow level: one ship_product call resolves variants, generates and waits for a mockup (through the waiting until its images are actually published), creates the product with the right field names, adds every variant, associates it with a store, and syncs to fulfillment and channels in the correct order, refusing a negative-margin price and warning on known variant traps along the way. The scar tissue lives in the code, not in your agent's context.
Prefer the hosted connector. Authorizing it provisions the API key for you, so there is no credential to create, paste, rotate, or leak into a config file. Reach for the self-run package only when your client cannot speak remote MCP or OAuth, or when you specifically want the server running on your own machine.
| Hosted connector (OAuth) | Self-run package (API key) | |
|---|---|---|
| Credential | Provisioned for you on approval | You create and paste an API key |
| Local prerequisites | None | Node.js 20+, Python 3 + Pillow, optionally tesseract |
| Transport | Remote MCP over HTTP | stdio |
| Best for | Any client that supports remote MCP | Clients without remote/OAuth support, local control, development |
https://mcp.apparelhub.ai
Add that URL to any MCP client that supports remote servers, sign in to ApparelHub, and approve. You never handle an API key. Approving the grant provisions a connector key on your account (or reuses the one you already have), and the hosted server resolves your session to it on every call. Nothing to paste, nothing to rotate by hand, nothing sitting in a dotfile.
The hosted server also carries the imaging toolchain the design and quality tools need, so transparency keying, image statistics, and OCR all work with no local dependencies at all: no Node, no Python, no Pillow, no tesseract.
Claude Code
claude mcp add --transport http apparelhub https://mcp.apparelhub.ai
Then run /mcp and choose Authenticate.
Any client that reads an MCP config file
{
"mcpServers": { "apparelhub": { "type": "http", "url": "https://mcp.apparelhub.ai" } } }
claude.ai — add it as a custom connector under Settings → Connectors, paste the same URL, then authorize when prompted.
The bare origin above is the server's canonical address: it is the resource identifier its own OAuth metadata advertises. A path is not routed on, so an existing config pointing at https://mcp.apparelhub.ai/mcp keeps working and needs no change.
Standard OAuth 2.1, nothing custom for you to configure. Your client discovers the authorization server from /.well-known/oauth-protected-resource (RFC 9728), registers itself dynamically, and runs an authorization-code flow with PKCE (S256) for the mcp scope against https://api.apparelhub.ai. Refresh tokens and revocation are supported. Access tokens are opaque: the hosted server exchanges yours for your connector key server-side, so the key is never in your client, your config, or your chat history.
One connector key is minted per account and shared across every chat surface you grant, and it counts against your plan's API key allowance. The Free plan includes API access with one slot, so if that slot is already taken by a self-service key the consent screen says so and offers to free it or upgrade. To revoke, disconnect from the client that holds the grant, or delete the connector key at https://apparelhub.ai/developer/api-keys.
Requirements:
The server reads your key from the APPARELHUB_API_KEY environment variable at startup and speaks MCP over stdio. It never accepts the key as a tool argument, and the API host is pinned (no override).
// ~/.claude/mcp.json (or a project .mcp.json)
{ "mcpServers": { "apparelhub": { "command": "npx", "args": ["-y", "@apparelhub/mcp-server"], "env": { "APPARELHUB_API_KEY": "your-key-here" } } } }
// .cursor/mcp.json
{ "mcpServers": { "apparelhub": { "command": "npx", "args": ["-y", "@apparelhub/mcp-server"], "env": { "APPARELHUB_API_KEY": "your-key-here" } } } }
# .aider.conf.yml
mcp-servers: apparelhub: command: npx args: ["-y", "@apparelhub/mcp-server"] env: APPARELHUB_API_KEY: your-key-here
Same shape everywhere: run npx -y @apparelhub/mcp-server with APPARELHUB_API_KEY in its environment.
| Variable | Purpose |
|---|---|
APPARELHUB_API_KEY | Required. Your ApparelHub API key. Not needed on the hosted connector. |
APPARELHUB_MCP_TELEMETRY | Set to off to disable the coarse usage signal (see Privacy). |
APPARELHUB_MCP_PYTHON | Path to the Python 3 interpreter for the local image tools (default python3). |
127 tools. docs/TOOLS.md walks through the core groups; call tools/list from your agent for the authoritative live schemas.
check_setup_readiness (what the account has, what it needs, the single next action), list_connectable_providers, connect_fulfillment_provider and connect_sales_channel (API-token providers connected entirely in chat), plus start_channel_connect / check_connection_status for the browser-based ones (Printful, Shopify, TikTok Shop, Fourthwall).list_my_workspaces, list_my_stores, list_my_designs, get_design_collection, list_my_products, list_my_orders, get_order_details.browse_catalog, get_garment_details, find_garments (search every connected provider at once for a capability), recommend_garment, list_catalog_providers.design_apparel, iterate_design, upload_design (bring artwork the merchant already owns), fit_aspect (quota-free reshape), design lifecycle (archive_design, restore_design, delete_design), and split primitives generate_image, process_transparency, verify_design_text.ship_product, update_product, delete_product, unsync_from_channel, diagnose_tiktok_listings, and split primitives create_product, add_variants, sync_to_fulfillment, sync_to_channel.approve_order, unapprove_order, hold_order, cancel_order, confirm_order, submit_order_to_fulfillment, check_order_status, reconcile_order), draft edits (add_order_item, remove_order_item), and design-approval holds (list_order_holds, approve_order_hold, request_hold_changes).report_fulfillment_issue (report a defect on an order), list_fulfillment_issues (per-order or workspace-wide inbox), check_fulfillment_issue (full issue plus the provider-ready problem report), resolve_fulfillment_issue (record the provider filing, close with a resolution, or create a replacement order).channel_performance, channel_opportunities, channel_coverage, listing_changes (did the last edit actually work), describe_listing_attributes, set_listing_attributes, set_channel_settings, import_size_measurements.import_channel_catalog (start; returns the run already going if there is one), get_catalog_import_run (poll), list_tracked_listings (the listings plus each channel's catalog_read and last run). Nothing is written to the merchant's store and those products keep shipping as today. Shopify, WooCommerce, Wix and TikTok Shop. To have ApparelHub fulfil one, bind_tracked_listing binds it to an ApparelHub product (their listing is not changed); unbind_tracked_listing undoes it.analytics_summary, analytics_timeseries, analytics_breakdown, analytics_ops, analytics_portfolio.list_collections, get_collection, create_collection, update_collection, delete_collection, add_products_to_collection, remove_product_from_collection, sync_collection.copy_product_to_workspace, move_product_to_workspace, check_product_move, and the design equivalents.create_workspace, update_workspace, delete_workspace, check_workspace_deletion, assign_workspace_member, unassign_workspace_member, move_store_to_workspace, get_role_matrix) and team (get_account_overview, list_account_members, remove_member, invite_member, list_invites, revoke_invite, resend_invite, accept_invite).get_store_settings, update_store_settings, create_store, archive_store, unarchive_store, activate_store), order payment/ops (record_order_payment, mark_order_no_payment, set_order_payment_method, sync_orders, estimate_order_costs, get_orders_summary, list_pending_fulfillments), and archive_product / restore_product.analyze_what_works, auto_optimize_listings, cascade_price_change, set_prices_by_margin, recover_from_outage.verify_design_quality, verify_mockup_quality, check_design_compliance.get_api_reference (discover the full agent API from the live OpenAPI spec), then api_get (read-only GET), api_create (POST), api_update (PATCH/PUT) and api_delete (DELETE) to call any /agents/v1 endpoint when no dedicated tool fits.Read tools are read-only. Product and design tools default to draft, never live, enforce pricing floors, and guard known variant traps. Systems-of-action mutations default to a dry run and only take safe actions (archive, never delete) when applied. Every product/order/store result carries a view_url back into apparelhub.ai. Errors come back in a consistent shape ({error: {code, message, retry_after?, suggestion?}}) — tools never throw across the MCP boundary.
get_api_reference also reports what the server you are actually talking to serves — its version, tool count, and every tool name — so an agent c