"Searching PubMed references and formatting them in Markdown" matching MCP servers:

Enables an agent, before it designs anything, to pull a short set of curated directions from award winners, editor-picked galleries, winning ads and top posts, plus live picks and deeper curations for the medium at hand. Users can then choose a reference, save links or screenshots to a personal library, and have later suggestions lean toward what they keep picking.

Converts Figma to Markdown. Strips out visual noise to drastically reduce LLM token consumption.

Enables driving Inkscape headlessly from an MCP client, with verified SVG editing, rendering, optimization, and animation tools.

Enables an MCP-capable AI client to drive a locally installed, licensed Autodesk Inventor through its COM API for local modeling tasks. It supports creating and updating a rectangular plate and a parametric quickchanger concept assembly, opening and inspecting parts and assemblies, and returning viewport previews.

Local MCP server inside 8 Autodesk apps (Revit, AutoCAD, Civil 3D, Advance Steel, Navisworks, Inventor, 3ds Max, Robot; 2023–2027): 480+ read/write actions, one-click setup for Claude, ChatGPT/Codex and Cursor. Commercial, free 14-day trial. Formerly HMK Pilot.

MCP server for creating and editing diagrams using draw.io. Allows generating diagrams from Mermaid or XML, searching shapes, and opening them in draw.io for export.

Enables searching thousands of device and print mockups and rendering screenshots or uploaded images into them via the Mockuuups Studio API.

Enables searching, downloading, and placing b-roll assets (images, stock video, etc.) onto an editor timeline in DaVinci Resolve, Premiere, or via universal formats.

Enables searching the Refero design catalog in plain English and generates DESIGN.md files for any project.

Enables evidence-grounded web design analysis by searching GDWEB references and generating isolated, per-reference DESIGN_INDEX specification documents for LLM-driven frontend development.

Searches design platforms for UI references and extracts design tokens such as colors, typography, spacing, and shadows from live websites.

Enables developers to generate polished, customizable React UI components from natural language prompts and add them directly to projects in supported IDEs.

Captures visual changes made with VisBug in the browser and exposes them to Claude Code via MCP, allowing developers to apply design modifications to source files directly from natural language.

Lets AI tools create and edit Excalidraw diagrams in a CanvasKeep workspace: generate diagrams from nodes and edges with auto-layout, organize them into workspaces and folders, and read or save full scenes.

Enables AI agents to design and critique websites using 2026 trend reports, motion code recipes, design principles, palettes, type systems, section skeletons, references, and DESIGN.md tokens, with performance and reduced-motion handling built in.

A lightweight sketch canvas that lets users draw ideas and sync them in real-time to AI via MCP, enabling visual communication without exports.

Enables AI hosts to validate, write to disk, hot-reload, preview, and export single-file HTML prototypes built to the Spark OP design spec, serving them locally at 127.0.0.1:5179 by slug. Also bundles the triggering skill, spec references, templates, and CSS tokens so agents can create, revise, and hand off development-ready prototype HTML through one controlled output path.

Enables generating UI design rules, fetching color palettes, and retrieving brand design references from over 328 brands.

Enables Claude to analyze reference images precisely — splitting turnaround sheets into views, removing backgrounds, aligning them to one scale, overlaying grids, measuring marked points, extracting contours and colours, segmenting parts, and comparing renders against references. This lets Claude build and iteratively correct 3D models in Blender and Cinema 4D from those references.

Enables LLM agents (and humans at a terminal) to drive FreeCAD through 280+ structured tools for parametric mechanical design, drawings, FEM/CFD and other simulations, and manufacturing checks. Also supports multi-agent orchestration, letting a team of agents split one product into components, build them in parallel, and merge them back together with fitting joints.

Imports public websites and extracts UI components and design tokens, making them available via MCP for AI coding agents to reuse in implementations.

Converts Markdown content into beautifully designed knowledge cards with customizable styles and sizes. Also supports fetching and converting WeChat public account articles to Markdown.

Enables AI assistants to automate Adobe InDesign publishing workflows, including document creation, text formatting, image placement, PDF export, and more via 35+ professional tools.

Enables AI assistants to create custom merchandise on SUZURI, including uploading images, generating text designs, and placing them on 450+ items, as well as searching and managing products.

Provides a hosted remote connection to Mobbin's library of real-world app and web design references over Streamable HTTP, requiring nothing to install or run locally. Access is authorized through an OAuth browser sign-in on first use, with per-client setup and tool listings documented externally.

Enables agents to create, inspect, and edit self-contained HTML presentation decks through semantic tools, validate them against the htmldeck/v1 contract, hand them to a local visual editor, and export them as standalone HTML, PDF, or per-slide PNG.

Enables coding agents to ground UI work in real product screens by returning concrete screen references as inline images, along with fonts, icons, and design-system details for a chosen screen. Also serves bundled design-skill documents and connection diagnostics so agents can settle, build, and verify interface work against existing tokens and components.

Enables Claude Code to research design references per page section across galleries like Awwwards, Dribbble and Mobbin, render the user's page in multiple style directions with live 3D components, and collect votes on a local board. It then produces a PDF report and iteratively builds and refines the actual page, dashboard prototype or mobile screens from that feedback.

Enables coding agents to ground UI work in real product screens by retrieving real screen references, fonts and icons, and recorded design systems, while also serving bundled design-workflow resources, playbook prompts, and connection diagnostics without a token.

Enables AI assistants to create Material Maker node graphs from natural language, validate them against the node catalog, and render them headlessly to PBR texture maps and editable .ptex files.