设计类 MCP / Skill 推荐

Let AI drive Swing and JavaFX apps — see the UI, click, fill forms, read tables. No API needed.

Convert files between 110+ document, image, audio, video, archive and ebook formats from AI agents.

Spacecraft component specs from vendor datasheets: search, digests, facts, gaps, budgets, bus design

Generate image, video, audio, 3D and vector media with 100+ AI models. Pay per generation.

Prove you made it first. Blockchain Timestamp creative work via Claude or any MCP-enabled AI Agent.

Search Wind UI, Magic, Dusk, Telescope and Artisan documentation. Hosted, public, no auth.

Game numerical design & balance auditing MCP server — 17 deterministic tools, zero LLM guessing.

用于图像与视频理解及生成的 MCP 服务器（Gemini/OpenAI/Grok）。

Search 4,000+ live UX & product-design jobs from jobs.uxjobs.io. Read-only, no auth.

Landing-page CRO: audit pages, rewrite copy, answer buyer objections, design and build via MCP.

Personalised ceramic mugs from Germany: prices, delivery, FAQ search, mug-design tool with preview.

视觉差异与变更检测工具，帮助编码代理捕捉代理式 UI 的走样漂移。

Provides style context & tokens to design or restyle web UIs in any framework

Every Auvik endpoint as a command, plus the cross-client answers the Auvik UI and API cannot give

Literature, Zotero, PDF, citation, materials, and scientific image tools for research agents.

查找 UI 组件与主题、获取代码，并在开启时调用托管的 21st AI 生成代码。

Create, design and send event invitations, manage guest lists, and track RSVPs.

AI 服装设计 MCP：在你的 StyTrix 画布上实时生成概念、模特、面料与造型。

Pay-per-use API marketplace for AI agents: LLMs, image, TTS, search. Free trial, x402.

Screenshot, PDF and HTML-to-image rendering API so Claude and Cursor can see any web page.

Screenshot, PDF and HTML-to-image rendering API so Claude and Cursor can see any web page.

31 no-AI tools: image conversion and EXIF stripping, App Store assets, colour maths. No API key.

remote debug iOS/Android/Unity/Godot/Flutter/RN/Web on real-device.ui-tree/screenshots/taps,tests.

PDF, image, video, OCR, screenshot, SQL, QR and text tools for agents. No API key, no signup.

通过 5 个托管只读工具提供代理设计模式指导：Streamable HTTP、无需鉴权、单一 Release 版本。

Cited book knowledge for agents working on system design and implementation.

Text, image and reference-to-video across many AI video models. Musevate account required.

Convert any image into machine embroidery files (DST, PES…) or vector graphics (SVG, PDF, EPS, DXF).

GroupDocs.Redaction 的 MCP 服务器——由 AI 智能体遮盖文本、元数据、批注与图像区域。

带 Web 界面的 Git diff 与 Markdown 评审，并为 AI 智能体提供 MCP stdio 接入。

Coordination for AI coding agents: declare plans, catch design conflicts early, share team memory.

在 Base、HyperEVM 与 Monad 上兑换、转账、查看持仓并使用 Aave V3，FibX 应用充当 MCP Apps UI。

144 个确定性文件工具：PDF、图像、媒体、格式转换与分析；一键连接（OAuth）。

Capture tool workflows, save typed tools, and replay with human approval. Includes an MCP Apps UI.

Deterministic engineering solvers: biquad filter design, room eigenmodes, LLM VRAM fit.

用一张自拍生成 150 多种主题的 AI 照片，另含 19 种图像编辑与 AI 视频。

Harvest Keynote and PDF slide decks into previews, text, image assets, and a manifest for agents.

See a color or image as a colorblind person does; recolor images and make Ishihara plates.

Check if a palette or image is colorblind-safe, generate safe palettes, check WCAG contrast.

Shared TODO/backlog MCP server with claim tracking, web UI, and encrypted local storage.

Convert files between 400+ image, video, audio, document, ebook, archive and font formats.

专为 Claude 打造的 AI-only 广告评分：在花费预算之前，从 13 个维度评估图片、视频或文字广告。

597 motion/3D UI patterns as ready HTML/CSS/JS, served over MCP. The entire library is free.

Access and maintain design system docs, tokens, components, skills, and contexts across any project.

AI 设计工作室：从简报出发产出方向板、HTML 原型、图片与视频，使用 OAuth 登录。

安全访问专属的 Otherlay Mac，用于文件、终端、Git、构建与界面检查。

功能完整的 ADB MCP server——49 个模块共 209 个工具，覆盖从 UI 到基带的操作。

生物工艺设计：生成纯化路线、仿真发酵与分离过程、执行 TEA（技术经济分析）。