"영상 (videos/images)" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Create AI video, images, music and voice from your assistant, on your Galatic.ai plan.
Dreamina (CapCut) video and images: text, frames, references, draft to full quality, upscales
Fetch the transcript of any YouTube video (plain text or timestamped segments, in any available caption language), search YouTube for videos and channels, list a channel's uploads, Shorts, playlists and community posts, search inside one channel, and list every video in a playlist. Hosted Streamable HTTP server from getyoutubetranscript.com; sign in with OAuth or an API key. Credit-based: one credit per successful call.
One MCP server for top AI models and live data. Images (Nano Banana, GPT Image, FLUX, Seedream), video (Veo, Kling, Seedance, Runway), voice and music (ElevenLabs, Lyria), plus Google, Maps, YouTube, LinkedIn, Amazon, social and public data. Seven tools: search_tools and get_tool (free) find a tool and show its inputs and price, run_tool runs it, list_calls, get_call and get_balance show your call history, any one call and your balance, upload_file (free) sends input files up to 100 MB (photos, voice tracks, video) with no hosting needed. Each run has a fixed price, charged only when it returns a usable result. Calls finish inside their request (no cancelling needed); get_call recovers a dropped one. Pay per call with x402 (USDC on Base) or an account API key. Prefer one MCP tool per model? Use https://tollnode.com/mcp/full.
Your AI assistant writes a design as HTML and Tailwind CSS, and RenderPixels renders it in a real browser and returns images at the exact size each platform needs: social posts, banners, logos, favicon sets and Open Graph images. Each render reports clipped text and missing fonts or images so the assistant can fix and re-render. OAuth sign-in, saved brand kits, 50 free renders per month.
Make images, video, music and voiceovers with more than 1,000 generation models.
Search a curated library of organic TikTok and Instagram Reels videos made by real businesses (videos that spread without ads), filtered by industry, business type, funnel job (awareness, branding, sales), format and what the shoot takes. Read a video's breakdown: why it worked, its hook, its call to action and how many viewers asked where to buy. For marketing agencies, creators and businesses planning short-form content. Requires a SeedReel Grow or Harvest plan; sign in with SeedReel (OAuth).
MiniMax (Hailuo) video, images, music, speech and voice cloning, templates and the AI agent
PixVerse video, images, music and speech: effects, keyframes, lip-sync, extend, music videos
Generate AI images, video, speech, music and presentations from Claude, ChatGPT and Cursor.
Free polls for images and videos ranked head to head: create a poll, share a link, read results.
Remove image backgrounds free — no account, no watermark, up to 16 MP. Refine edges with a brush, swap in a colour, gradient, or photo, and batch 10 images at once. Developers get a remove.bg-compatible API (50 free images/day) and an MCP server for Claude, Cursor, and VS Code
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
Convert video, audio, images, PDFs and documents in 67 formats; results come back as links.
33 tools: LLM chat, summaries, translation, embeddings, speech, images. 25 free calls.
Render charts as PNG images from a URL — Google Image Charts / Image-Charts compatible API.
Multi-provider AI OCR and structured JSON/table extraction MCP server (https://smartocr.dev). Extract strict custom JSON schemas, Markdown tables, and CSV rows from PDFs, invoices, bank statements, receipts, timesheets, and scanned images using intelligent routing across Native PDF, Google Cloud Vision, and AWS Textract. Works out-of-the-box on the free tier (2 free documents/day) or with a Smart OCR API key (10 free credits on signup at smartocr.dev).
Create, edit, and schedule social media posts, carousels, videos, blogs, and emails.
Turn Twitch and Kick streams and long videos into captioned shorts; edit, draft posts, track views.
Generate images, video, speech, music and text with HiAPI's AI models. OAuth or API key.
Rhinobird is an AI creative assistant for new product development and e-commerce marketing. Explore new product opportunities through market insights, product concepts, and packaging design, then create e-commerce detail images, lifestyle visuals, ad posters, and marketing videos
Kling AI: 4.0, v3 and Omni video, Image 4.0 (8K) images, avatars, lip-sync, motion control, voices
Your tday brands and product screens in any MCP client, signed in with OAuth. To record narrated demo videos of your app, install the local server: npx -y @tday-com/mcp@latest install
Generate video, images, music, voiceovers, captions and dubbing with 40+ AI models.
AI marketing team for founders, callable from any agent: plan what to say, edit video, generate images and clips, write and design posts, publish to LinkedIn, X, Instagram, TikTok, YouTube, Facebook, Threads, Bluesky, Discord and Mastodon and read what performed. OAuth sign-in, no API key; every draft waits for approval unless you say publish now. Free Forever plan: 10 posts a day, no card.
Make faceless AI short videos from a story idea: script, voiceover, captions, scenes.
Create and edit images and video, generate music, and retrieve existing audio projects.
Publish to self-hosted WordPress from AI agents: markdown, images, SEO, and Notion sync.
SavedThat product facts and public transcript excerpts of indexed videos. No sign-in.
AI video agent: edit timelines, captions, voice, music, images and ads, then render MP4s.
Create AI influencers and make their photos and talking videos, with the same face every time.
Create and edit museum audioguide apps: stations, tours, texts, images, audio and app design.
One key and one prepaid balance for 3,051 pay-per-call tools from 99 providers for AI agents: search, maps, shopping, market data, web pages, images and more. Agents find tools by job, see the price before running, and pay per call. Failed calls are free. Sign in with OAuth, no API key to copy. Sign-up is open to everyone.
Create AI images, video and music with your Lexu credits, with a spending limit per call.
Schedule and publish posts to TikTok, Instagram, YouTube, LinkedIn and more from any AI agent. Connect your social accounts once, then let Claude, ChatGPT or any MCP client create, schedule, edit and review posts across every platform. Upload images and videos to your media library and attach them to posts. Signs in with OAuth; HubPost never sees your passwords. Also available in the [Claude directory](https://claude.ai/directory/hubpost) and as a [ChatGPT app](https://chatgpt.com/plugins/plugin_asdk_app_6ab141477a708191a7c5f68714ee7c39). Setup guide: [hubpost.co/mcp](https://hubpost.co/mcp?utm_source=glama&utm_medium=mcp-directory).
Make narrated tutorial videos of any website or web app by asking your AI assistant.
Scrape TikTok profiles and videos — followers, views, likes and music, by Magnova
Images, video, music, speech, and public social data for AI agents.
SEO and market data: SERP, keyword volume, backlinks, site audit, Maps, reviews, traffic, ChatGPT visibility, Amazon, jobs, DNS, bulk HTTP/API requests.
Score video as an agent: cue sheet from the cut, 100+ AI instruments play your MIDI, mix to picture
Turn images into pixel art, extract and remap palettes, and upscale sprites without blur.
Connect Trainn to AI assistants like Claude and ChatGPT to create product videos, help articles and courses through chat—and update articles and courses in the same conversation. What you can do - Turn recordings into product videos. Upload screen captures or webinar recordings, then tell AI how to turn them into product videos with AI narration and visual effects. - Write and update help articles. Turn notes, transcripts and product briefs into structured articles, with relevant videos embedded. - Build courses. Create chapters, lessons, quizzes and optional certificates. - Create personalized collections. Organize relevant videos and articles into structured resources for customer onboarding or training. - Find answers in your content. Ask questions about your Trainn library and reuse existing knowledge in new training. - Find what needs updating. Compare release notes with relevant training, flag potentially outdated information and help revise affected articles and courses. Who is it for? Customer success, education, support and product marketing teams that need to create and maintain training as their product grows. Trainn MCP reduces the manual work between planning content with AI and turning it into training customers can use. New content starts as a draft for you to review and edit. Nothing is published without your explicit request. How to connect: Sign up to Trainn, then add https://mcp.trainn.co/mcp to your AI assistant’s MCP settings and authorize access. Get started with these sample prompts, or follow our setup guide. Important links 1. Page: https://trainn.co/mcp/?utm_source=glama&utm_medium=directory 2. Documentation: https://help.trainn.co/categories/eCGRIB5MdtE-new-releases/Szlojlmuhl8-trainn-mcp/4VtkBh2fLkA-connect-trainn-mcp 3. LinkedIn: https://www.linkedin.com/company/trainn
Narrated videos made in Claude: motion graphics or illustrated stories, for YouTube, TikTok, Reels.
Live prices for 111 Chinese models; batch cost calculators for video and images.
Remote MCP server to generate fictional character portraits (8 styles) and lip-synced talking MP4 videos (8 English voices) from text. No subscription.
Generate videos and images, animate stills, extend clips, upscale, remove watermarks and subtitles.
Document conversion and OCR for AI agents: PDF, Office docs, images to text.
Give your AI agent a “publish” button. Droply turns HTML pages, Markdown, PDFs, CSVs, images or a whole multi-file site into a live link like name.droply.page, in one tool call. Update a project later and the link stays the same, so anything already shared shows the new version. Agents can also list projects with view counts, set a password, or limit access to specific emails. OAuth sign-in, free plan that never expires; works in Claude, Cursor, Claude Code and any client that supports remote MCP.
ChartAnt is a remote MCP server that gives your AI assistant 51 tools to draw charts, diagrams and maps as real PNG images with their own link, ready for email, Slack, slides or a README. - 40+ chart and diagram types: line, bar, column, pie, area, scatter, funnel, sankey, treemap, waterfall, gantt, heatmap, KPI cards, dashboards, flowcharts, mind maps, org charts and more. - Maps of every country: world maps, the states, provinces or regions of any country, and pin maps from coordinates. Region names in 20+ languages, with "did you mean" hints for names that don't match. - Charts that stay updated: sign in once and your assistant can save a chart at a fixed link. Later, say "add 10% to this month's sales" and the image at the same link updates. Copies can go to Slack, Teams, Discord or email on every change or on a schedule. - Nothing to install and no API key: paste the URL into Claude, ChatGPT, Cursor, VS Code, Windsurf or n8n. - EU-hosted. Chart data is used only to draw the image and is never logged.
Anime image generation for AI agents at $0.003 per image, one of the cheapest anime image APIs. Tools: generate_anime_image (anime $0.003, ultra $0.01, ultra-max $0.02 per image), generate_anime_video ($0.016/s at 480p, $0.04/s at 768p) and get_anime_video. Sign in with OAuth or send an API key as a Bearer header. Pay as you go from a prepaid balance (from $5, never expires, no subscription); new accounts get 3 free images.
Search your saved Reels, TikToks and YouTube videos and creator libraries by what was said.
Review generated images, video and audio against a brief before deciding whether to retry a render.
Create app-store screenshots, social graphics, AI and device-only videos.
Turn YouTube videos and audio or video files into searchable, exportable transcripts.
Medium MCP server for ChatGPT, Claude and any AI agent: create post, edit post, cross-post article and get post stats in your own Medium account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Medium yourself; Cotlet does not store your password and you need no Medium API key. About the official Medium API: Medium has an old REST API, but it is no longer supported and Medium does not allow new integrations (checked 11 Oct 2026). Accounts that still hold a token can only create posts, list publications and upload images, with no editing, stats or responses. Setup and FAQ: https://cotlet.dev/integrations/medium-api-mcp-server
Generate and upscale AI images, video and audio with leading models, right from your AI chat.
Start a video generation job and poll it until the clip is ready; video price plus $0.01 a call.
Create AI images, short videos and voice-overs on Deepnia, with the price shown first.
AI shorts, script-to-video, music videos, AI images, music and voiceover; paid tools quote first.
Fathom MCP server for ChatGPT, Claude and any AI agent: list calls, complete action item, add action item, share call, set link access, regenerate summary, update settings and delete call in your own Fathom account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Fathom yourself; Cotlet does not store your password and you need no Fathom API key. About the official Fathom API: Fathom has a REST API and an official MCP server, but both only read your calls (checked 22 Oct 2026). The API lists meetings and returns summaries, transcripts and action items, requests recording downloads and manages webhooks. Setup and FAQ: https://cotlet.dev/integrations/fathom-video-api-mcp-server