"Hosting Supabase on Your Own Server" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Find and add animated SVG illustrations to your site from your coding agent. A free set, no account.
Create, read and edit architecture, flow and ER diagrams on a live canvas shared with your team.
Design quality gate for AI-generated UI: score any URL on 45 deterministic checks, A–F grade.
Slyd is an open source carousel maker with a remote MCP server, so Claude, ChatGPT, Cursor and other agents can create carousels for you. What agents can do • create_carousel: turn a topic, post or article into a designed 5–10 slide carousel • get_carousel_guide: learn the layouts, templates, palettes and fonts • read_carousel_link: open a carousel you shared and revise it • carousel_from_text: a ready-made prompt that turns any text into slides What you get • 9 templates, 8 layouts (cover, point, list, quote, photo, stat, CTA, blank) • Palettes, font pairs, film-grain textures, highlights and your brand kit • Photos described in words, matched to free stock images • An editable result, not a flat image: change anything, then export PNG, PDF or ZIP • Formats: 1:1, 4:5, 3:4, 9:16, 16:9 Private by design: the server is stateless and stores nothing. Your projects stay in your browser. Server URL: https://tryslyd.vercel.app/mcp (Streamable HTTP, no auth) Setup guide: https://tryslyd.vercel.app/agents Source: https://github.com/venukumaraitech/slyd
Search and pull 620+ React and Tailwind sections into your project over MCP.
A coding agent searches the Icons8 library by keyword and style, then adds the selected icon or illustration to the project. Icons8 draws all of it: 420,000+ icons (130+ styles) and 110,000+ illustrations (340+ styles), so one project doesn't end up with mixed looks. The server lives at https://mcp.icons8.com/mcp/ and signs people in through their Icons8 account in the browser. Downloading PNG is free as long as the project links back to Icons8. SVG is on the paid plan, and that plan makes the link optional.
Build it. Rehearse it. Own the room. The hosted MCP server for Kadal Deck (deck.kadal.cc), which has your back for the whole talk, from the first idea to the last applause. Connect once with OAuth and your AI agent can list and inspect your decks, read a talk in progress (current slide, who is watching, polls and questions by votes), check analytics, change titles, visibility and passcodes, roll back versions, create share links, and quick-edit and publish decks through the web builder, with conflict-safe publishing that never overwrites newer work. Pair it with the local server (npx @kadal/deck mcp) to write, check and build decks on your machine. Open source.
Find, price and license fonts from foundries; agents pay per licence in USDC via x402 on Base.
Design your mobile app UI with AI, then have your coding agent build the real app from it.
Create PDF documents from HTML and CSS or 50+ ready templates: invoices, quotes, receipts, reports, contracts, letters, CVs and certificates. Its own page layout engine handles page numbers, headers and footers, tables of contents with page numbers, footnotes, tables that continue across pages, QR codes and barcodes, fillable forms and tagged PDF/UA. Every document gets an edit link to the ReflowPDF editor, and the assistant reads your edits before the next change. Existing PDFs can be opened in the editor too. Works without an account; OAuth sign-in is optional.
Create and manage coloring books, generate pages, and export PDFs. Tokens are bought on the website.
Pixel art for your game, from your coding agent. Generate sprites, items and tiles in your game's style (64 to 1024 px), make variants, reskins and N/E/S/W directions, then edit everything in a full pixel art editor that syncs into your project. Works with Claude, Claude Code, Cursor and ChatGPT; sign in with OAuth, no API key.
Build, check and report on MIDAS CIVIL NX bridge models and design tendons, with MIDAS IT plugins.
Convert a Figma frame into a native WordPress builder layout from Claude, Cursor or VS Code: Elementor containers, Gutenberg blocks, Oxygen 6, Oxygen Classic, Etch or HTML. A spatial layout engine computes it, not an LLM. Same frame, same output, every time. Your Figma token is never stored.
Packaging dielines (FEFCO/ECMA), 3D box and bag mockups, and your Drint projects in the chat.
Icons that match, in your colors. Your AI finds them for your website or slides, in 10 languages.
Data visualization design, delivered per API call as an atom service on Conduit Atoms.
Pre-press for DTF and textile printing: check whether an image prints well at a given size, remove backgrounds with clean edges, upscale to print size at 300 dpi, knock out colors, make halftones for dark garments and nest designs on gang sheets, plus print sizes by garment and advice on print techniques. Works in any language. Sign in with OAuth (or use a PigmentaLab API key); the free plan includes daily credits.
Run accessibility, contrast, and design token audits and file QA issues from your AI coding tool.
BAKO Architect Pro includes a native Model Context Protocol (MCP) server over SSE and HTTP. Give Cursor, Claude Desktop, or custom agentic systems the tools to inspect and retrieve your 3D architecture directly.
Audience contract design audit, delivered per API call as an atom service on Conduit Atoms.
Dreamship's official print on demand MCP server. Ask your AI assistant to create products with mockups from your artwork and publish them to Shopify, Etsy, WooCommerce, BigCommerce, TikTok Shop and Walmart, check what an order costs shipped to your customer, search the catalog's colors, sizes and stock, draft orders, track every order and shipment, and export your data. Drafts wait for you to review, submit and pay on Dreamship: the connector can't submit or cancel an order, charge your account, or delete anything. With coding agents like Claude Code and Codex it works in bulk, turning a folder of artwork and a spreadsheet into products, or a spreadsheet of orders into an Order Import file. Free on every Dreamship plan. Works with ChatGPT, Claude, Gemini, Grok, Perplexity, Claude Code and Codex.
Find, price and license fonts from foundries; agents pay per licence in USDC via x402 on Base.
Curated TikTok slideshows and Instagram carousels for your brand on autopilot
Flavo builds websites and apps the way a dedicated designer would. Pick from several finished designs, then build and host it on Flavo, with a database and sign-in included.
Lets your AI build and edit websites in Xodia, a visual website builder for real code (Vite, React, Tailwind CSS or plain HTML in your own git repo): read and write site files, create pages and CMS collections, run typecheck, design and link checks, take screenshots, manage forms and translations, and pick up change requests the user sends from the visual editor. Sign in once with your Xodia account (OAuth). Free plan, no card needed. Setup: https://xodia.ai/ai/mcp
Well Told's official MCP server for designing custom glassware, tumblers and bottles in chat. Find products that fit a quantity, budget and date, upload a logo, and get a proof with a 3D preview in either of Well Told's two designs: Map + logo or Logo Only. Then get a quote with volume pricing and continue to welltolddesign.com with the design in the cart. No sign-in needed. It never takes payment; checkout happens on welltolddesign.com.
Preview Google Search, PMax, Display, YouTube, Meta and LinkedIn ad mockups in chat, no sign-in. Save one with a free account to get a share link your client can comment on.
Your AI designs live on the UX Pilot canvas or runs its design agent: reviews, React, video, media
Find design references and video breakdowns for your next post. Free account: 100 credits a month.
Search and download licensed stock images, SVG illustrations and packs, brand logos, sound effects, low-poly 3D game models and videos from ImgSearch. Sign in with a free ImgSearch account over OAuth; searching is free and downloads use your plan's allowance.
Assemble motion-design launch films for software from ready-made pieces, with your brand read from your site; check, preview, finish in the editor.
EasyGerber brings AI printed circuit board (PCB) design, layout, and routing to MCP-compatible assistants. Describe a circuit or start from firmware pin assignments, search published electronic components, and build schematics using catalog parts with their footprints and available 3D models. Create and revise boards, generate layouts with automatic component placement and routing, inspect previews, and check saved layouts for blocking design issues. Export manufacturing ZIPs containing Gerber and drill files, a bill of materials, and component placement data, or download an editable EasyGerber (.egb) file. Start without signing up. Your agent uses one private board reference to create and continue a board, including catalog access, edits, layout, checks, previews, and exports, without a separate guest setup step or token to manage. To keep the board in your account or work with permitted saved personal or organization boards, complete EasyGerber sign-in and OAuth consent, then resume the same task. Account permissions, plan limits, and generation billing apply; support depends on your MCP client and installed integration.
Create, animate and export mascots from your coding agent, as Lottie, SVG or transparent clips.
MCP server for print on demand and digital products. AI designs, printables, mockup products and stores from any AI agent. Publish to Shopify, TikTok Shop and Etsy (via one-click review).
Put a map on a site with your AI: map your places, design the look, and get the code.
Print a photo or idea on a poster, canvas, mug, t-shirt, card or puzzle, with proof and price.
Photo mosaic maker and AI photo collage maker: turn your own photos into a mosaic or a collage.
Build, change and publish a business website from your AI assistant, with sign-in and saved data.
Search bilingual image prompts, upload reference images, and generate and download images from your AI agent. OAuth sign-in; image generation uses paid subscription credits. Setup: https://framepond.com/en/agent?utm_source=agent_directory&utm_campaign=agent_launch
Turn the reference images you collect into a written design taste your assistant can follow.
Your house in 3D from its plans, then finishes and furniture on it; every change waits for your yes.
Connect your AI assistant to Blender for 3D modeling, Geometry Nodes, materials, lighting, animation, rendering and export. Inspect real scenes and viewport images, refine the result and restore checkpoints. OAuth connects your chat to Blender Bridge Desktop on an online Windows 10/11 x64 computer running Blender 4.2+. The chat can run on another device. Requires an active Blender Bridge account; 7-day trial available. AI model access is separate.
Build and edit real websites from ChatGPT, Claude or Cursor in Swebsy's visual editor. Sign in with a free Swebsy account and your agent adds sections, edits text and styles, and manages pages in your open Swebsy Studio tab, where you see every change and can tweak it by hand. Export static HTML/CSS/JS or publish one site free. No install, no per-token fees.
Turn your data into map images of countries, states, counties and ZIP codes with Ultimaps MCP server. Each map comes with a link to Ultimaps Studio, where you can keep editing it, export it, or publish an interactive version. No account needed: 30 maps per hour, PNG up to 1600px, with Ultimaps attribution.
AETumi MCP - Three.js/WebGL 3D web scenes, components & templates you own the source of.
Turn a document or an AI draft into a publish-ready PDF, with an automatic cover, table of contents, pagination and your saved branding.
Edit and publish your FramerToNextJS sites (converted Framer or AI-built) from Claude, Cursor or Codex. 19 tools: read pages, rewrite copy, restyle elements, add sections and pages, design Studio sites, manage CMS collections and items, then publish to your own host. OAuth with a read-only option, and MCP runs no model on FNJ's side. Requires an FNJ plan (Lifetime or any AI builder plan).
Create and edit flowcharts, mind maps, wireframes, and docs in Whimsical, or search your workspace.
Design a logo from your brand name and style, review it in a panel, then generate final logo images.
Create 3D device mockups, App Store screenshot sets and launch videos from your AI. Showoff.dev puts your screenshots on real iPhones, Pixels, iPads and MacBooks, sets camera and background, and exports App Store and Google Play sizes. Works with Claude, ChatGPT, Cursor, Codex and any MCP client.
Create 3D device mockups, App Store screenshot sets and launch videos from your AI. Showoff.dev puts your screenshots on real iPhones, Pixels, iPads and MacBooks, sets camera and background, and exports App Store and Google Play sizes. Works with Claude, ChatGPT, Cursor, Codex and any MCP client.
Screenplay and storyboard in your AI assistant: import scripts, edit scenes, build shots.
Design presentations, landing pages and social ads with Deckly's tools, then share or export PDF. Your agent writes the slides itself (HTML and CSS), places photos, looks at the real rendering and fixes what is off. OAuth: connect with only the URL; free accounts included.
Drive Veltake Studio from any AI agent: create film and ad projects, have the Studio agent build scenes on the canvas, price and start renders, and export edited cuts. Also makes single images, video, speech and music in one call; every paid call runs only at the price it was quoted.
Flett is a shared online whiteboard. Connect it to Claude, ChatGPT or Cursor and the AI draws straight onto your boards: flowcharts, mind maps and architecture diagrams made of shapes and arrows, documents, slides and designed pages, charts, maps and files. Everyone on the board sees it appear live and can move, edit and comment on everything, then present it or export it to PNG, PDF, PowerPoint or HTML. Sign-in is OAuth; reading boards is free.
Your AI agent builds native Gutenberg blocks, pages and templates on your WordPress design system.
Generate pixel-art sprites, animations and 16-tile Wang tilesets on a fixed pixel grid with your SpriteForge account (sign-in with OAuth, paid credits), save them to your library and open them in the editor.
Design Tesla Paint Shop wraps from your AI assistant with 3D preview and export links.
Logo, colors, typefaces, tone of voice and CSS theme of any brand, read from its own website.