Library
86,219 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
RemixMeme
MCP serversGenerate watermark-free vertical AI meme videos from 1–2 photos for TikTok and Reels.
-
Wuai
MCP serversFacts about Wuai, which captions and translates videos in real time, clips and shares them
-
ConvertAudioToText
MCP serversTranscribe audio and video links, read transcripts and summarize them, signed in with your account.
-
Eikino
MCP serversGeolocate photos or video frames and check media for AI generation signs via API key.
-
TrendTemplate
MCP serversRead-only catalog of AI trend video templates: viral TikTok memes, photos needed, lengths, prices.
-
Vividemo
MCP serversMake videos with Vividemo's AI production agent: start projects, follow progress, get the files.
-
MakersMCP
MCP serversFree kits for makers: brand kits, fonts, screenshots, films, music, captions and video formats.
makersmcp@0.2.1 -
Motion Fab Library
MCP serversMotion-graphics video prompts and 200+ motion-design techniques with working GSAP code.
-
Bannx
MCP serversRender on-brand images, PDFs and videos from templates; create and edit templates and brands.
-
SayScreen
MCP serversMake narrated tutorial videos of any website or web app by asking your AI assistant.
-
SeedReel
MCP serversSearch organic TikTok and Instagram Reels videos made for businesses, and read their breakdowns.
-
yt-dlp MCP
MCP serversDownload video and audio with yt-dlp via AI agents: inspect, batch, subtitles, convert.
@fanyzp/ytdlp-mcp@1.0.0 -
Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.
google/gemini-3.8-flash:batch -
Qwen: Qwen3.7 Flash
ModelsQwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...
qwen/qwen3.7-flash -
Auto Router (Beta)
ModelsThe experimental version of our Auto Router where we test new improvements. Use it to get the latest and greatest version of our general purpose auto router, but expect beta...
openrouter/auto-beta -
MoonshotAI: Kimi K3 (batch)
ModelsKimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...
moonshotai/kimi-k3:batch -
Google: Gemma 4 31B
ModelsGemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
google/gemma-4-31b-it -
humanjs
MCP serversHumanize browser automation for AI agents, QA tests, and demos. Playwright-first — record sessions to video or runnable tests, and drive it over MCP from your favorite AI.
git clone https://github.com/totigm/humanjs.git -
Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual...
inclusionai/ling-3.0-flash-vl -
Qwen: Qwen3.8 27B
ModelsQwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...
qwen/qwen3.8-27b -
Google: Gemma 4 31B (free)
ModelsGemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
google/gemma-4-31b-it:free -
Qwen: Qwen3.5-Flash
ModelsThe Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...
qwen/qwen3.5-flash-02-23 -
MiniMax: MiniMax M3.1 Flash
ModelsMiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex,...
minimax/minimax-m3.1-flash -
Meta: Muse Ember
ModelsMuse Ember is the smallest and most efficient model from Meta that’s designed for complex reasoning execution and the work agents repeat all day: tool calls, coding agent subtasks, routing,...
meta/muse-ember
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.