MCP App Store
by KeenEthics
OnVid Prompts icon

OnVid Prompts MCP Server for Claude

By Onka Solutions, Co.

Overview

OnVid Prompts writes prompts for AI video models. Describe your idea and where it will be used, and get ready-to-use prompts with the action, camera move, lighting, sound and clip length, plus a multi-shot version. Prompts are worded for the model you use: Veo and Sora get dialogue and sound lines, Kling and Wan get a separate negative prompt, Hailuo gets bracket camera commands, and Runway image-to-video prompts describe only the motion. Animating your own photo? The prompt keeps the person or product unchanged. Spoken lines stay word for word, in any language. Paste a prompt you already have to get an improved version and a list of what to fix, ask for video ideas for a topic, or browse 80 prompts across 16 categories, from cinematic scenes and product ads to dance, pets, anime, horror and holidays. The connector returns text only. It does not create videos, needs no account, and stores nothing you send.

How to connect

  1. Claude: Open the OnVid Prompts listing in the Claude connectors directory and choose Connect. Claude listing OnVid Prompts exposes 7 tools here.

Tools

build_video_prompt

Claude
Writes ready-to-use AI video prompts from a short idea: three shot variants (action, camera move, lighting, sound, length, aspect ratio) plus a multi-shot version, worded for a chosen video model (Veo, Sora, Kling, Seedance, Hailuo, Wan, Runway or others). Handles image-to-video from the user's own photo and spoken lines kept word for word. Use it when the user wants a prompt for a video idea. Returns text only; it does not create videos.

get_model_prompt_guide

Claude
Explains how to write prompts for one AI video model: prompt structure, how it handles sound and dialogue, negative prompts, clip length, tips, and an example prompt. Use it when the user asks how to prompt a specific model.

get_prompt

Claude
Returns the full text of one library prompt (prompt, negative prompt, aspect ratio, length, camera, lighting and sound), optionally filled in with the user's own subject or spoken line and worded for a specific video model or for image-to-video.

improve_prompt

Claude
Reviews the user's own video prompt and returns an improved version that keeps their words and adds what's missing (camera move, lighting, style, sound, length), worded for the chosen model, with a list of what changed and problems to fix (too many beats for the length, describing looks in image-to-video, long dialogue). Use it when the user shares a prompt and wants it better. Returns text only.

list_prompt_categories

Claude
Lists the prompt categories with counts, plus the uses, styles, models, lengths and aspect ratios the builder understands. Use it when the user wants to browse.

search_prompts

Claude
Searches a library of video prompts across cinematic, product ads, UGC, dance, pets, anime, music videos, food, fashion, travel, real estate, horror, holidays, fantasy, sports and satisfying clips. Returns short summaries with ids; call get_prompt for the full text.

suggest_prompt_ideas

Claude
Suggests video ideas for a topic, niche or product using formats that work on TikTok, Reels, YouTube and ads (POV, before and after, tiny world, talking pet, movie trailer and more), each with why it works, plus matching library prompts. Use it when the user doesn't know what to make yet.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/onvid-prompts"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/onvid-prompts)