"An MCP that effectively manages other MCPs" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Make QR codes that keep working: free static codes, or changeable codes you can edit and track.
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
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.
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.
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.
Direction, award-tier motion blocks and a local check for coding agents that build websites.
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.
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.
Audience contract design audit, delivered per API call as an atom service on Conduit Atoms.
DXF and PDF/X-4 for AI agents: structured facts, PNG renders, an interactive in-chat viewer.
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.
Read and build visual moodboards, shot lists and lookbooks from an AI assistant.
SVGProof converts logos into clean, editable SVG files that print shops, sign makers and design tools accept. It's built for flat art: AI-generated logos from ChatGPT, Gemini or Midjourney, plus icons, wordmarks and badges. The output is accurate shapes with few nodes, not a picture wrapped in an SVG.
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.
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.
Spritulus’s MCP lets AI assistants create and update 2D games, assemble sprites and animations, and configure scenes, dialogue, and gameplay through natural-language requests. Use it alongside the visual editor to turn ideas into playable games that you can publish as they are or export for further customization.
Remote MCP that generates original launch assets over Streamable HTTP. Usage is metered in credits.
Turn a prompt and a link into a branded, print-ready QR code that always scans.
Design custom silicone wristbands in 3D, get exact prices and an order link for bandfactory.eu.
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.
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).
Free pixel art and tileset editor, no account needed. Opens a sprite, an animation or a 16-tile Wang autotile set in an editor inside the chat, lets you edit it by hand (layers, frames with onion skin, tiling preview), and returns the edited PNG.
Verified component catalog over remote MCP: agents pick component ids and get a stamped project repo that builds. Connect at https://www.botkelp.com/mcp. Auth: MCP OAuth 2.1, or a Bearer bk_live_ API key; initialize and tools/list are open.
The PostNitro MCP server lets AI assistants and agents — Claude (Desktop, Code, and Cowork), Cursor, ChatGPT, and any other Model Context Protocol client — create carousels, image posts, and videos, manage brand kits, audio tracks, and connected social accounts, and schedule posts directly. Instead of writing REST API calls, you connect the server once and your AI assistant gets ready-made tools covering carousel, image, and video generation, brands, audio, social accounts, and scheduling.
Cloud Blender for AI agents: build, inspect, render and animate 3D scenes over remote MCP. Keep editable .blend projects and export GLB or STL. Make your first 3D asset free—30 compute minutes per UTC month, no credit card. First 100 eligible Free account owners to use all 30 minutes in one UTC month by December 31, 2026 UTC receive one calendar month of beta free: 4 compute hours per UTC month, 2 concurrent workers per deployment, 2 deployments, 2048×2048 renders at up to 256 samples, and 10 GiB storage. Existing usage counts toward the 4-hour allowance. Limited to 100 rewards; expires January 1, 2027 00:00 UTC. Free resumes afterward without an automatic charge. Examples, eligibility and terms: https://sceneplane.online/launch?utm_source=glama&utm_medium=directory&utm_campaign=first100
Generate your app's mascot, then props, poses and animations that stay on-model.
OODS Foundry is an object-oriented design system that extends the one you already have.
Landing page CRO for paid ads and any page that must convert: audit, fix copy, build new pages.
Classic Paint inside your conversation. Draw, edit images, and sketch ideas with an MCP App.
Plan and score the website of an architecture or interior design studio.
Book covers from a title and an author: 39 styles, 28 palettes, mockups, SVG and PNG.
Custom websites with an AI concierge, booking and an AI door built in. Score any site out of 10.
A shared Excalidraw board that people and agents draw on together
Cost of an ADU, shed, barndominium and more from LEVA priced 3D configurators
Build and edit launch-ready websites for tech founders from a brief or an authorised reference.
creative-constraints — an original deck of 162 domain-neutral creative constraints, drawn by…
Make a transparent PNG shirt design from a prompt or an image URL, with the background removed.
Generate images and PDFs from your Bannerify templates, or compose an image from shapes.
500+ typed UI atoms an agent composes into real rendered interfaces. Free, no API key.
A tactile React component library, and the design system that keeps your AI agent on-brand.
House plans and AI-drafted CAD floor plans (DXF, DWG, PDF) from AI Architectures: search ~500 free house plans, see CAD drawings by the AI drafter, and with an account have a new layered, dimensioned CAD floor plan drawn, changed in plain words and downloaded.
Make a classroom seating chart or a wedding seating chart that follows your rules, then print it.
Design custom t-shirts, hoodies, caps, mugs and totes, price an order, and link to order it.
Read about Ariel Adler (Israeli brand designer) and book an intro meeting with him.
Read visual design reviews captured on live web pages with the Website Feedback Tool Chrome extension: comments, CSS selectors, computed styles, console and network errors, and screenshots, so a coding agent can apply the fixes. Tool calls require the agent key from the extension (Connect AI agent) as an Authorization: Bearer header.
Opens, inspects, and renders DXF/CAD drawings for AI agents: describe_dxf returns structured facts (layers with actual drawn colors, units, bounds, text content) and render_dxf returns PNG images. On MCP Apps hosts like ChatGPT and Claude, view_dxf opens an interactive in-chat viewer with pan, zoom, and layer toggles.
Cherishly is a reverent memorial keepsake generator that creates high-resolution, shareable tribute cards honoring loved ones. Backing the Cherishly mobile apps on iOS, Android, and www.cherishlyapp.com , this MCP server empowers AI assistants to design beautiful keepsakes with gold foil typography, custom photo medallions, and interfaith honorifics in seconds.
Search over 1.85 million captioned images using text, a reference image, or both. Upload a JPEG, PNG, or WebP image as base64, or provide a public HTTPS image URL. Find similar images from a Lightdrift asset ID and retrieve hosted file URLs, source licenses, and attribution. Connect with OAuth or an API key. Searches cost $0.005 ($5 per 1,000); image details are free. Setup: https://docs.lightdrift.ai/guides/images-mcp
Critique a company’s brand from its public website and an optional public document. Sigil returns positioning, visual identity, voice, a brand score, prioritized changes, and a link to the full Read; it does not design logos, generate brand books, or access private company systems.
Parametric 3D CAD for AI agents. Claude Code, Cursor or any MCP client can build and edit real OwlCAD projects: primitives, booleans, and generators for gears, threads and Gridfinity. Check a part for printability and interference, then export STL, 3MF, OBJ or STEP. Output is an editable model with named millimetre dimensions, not a mesh, so you can open it in the browser and change any value afterwards. Sign in with OAuth or an access token. Requires OwlCAD Pro.
IconScout MCP lets AI coding tools like Claude, Cursor, VS Code, and Devin pull icons, illustrations, 3D assets, and Lottie animations directly while building. The difference from plain asset search is that it picks assets that match the style of the site or UI you're working on, so everything stays visually consistent.
Run a custom-merchandise store end to end from an AI agent: generate designs, build products with mockups and margin-safe pricing, list them on Shopify, WooCommerce, Wix and TikTok Shop, and route orders to Printful, Printify or Gelato for fulfillment. Sign in with OAuth, no API key to handle.
Run a custom-merch store from an agent: design, build products, list on every channel, fulfill.
Create Thumbnails That Make People Click