Stay in the conversation
Brainstorm the idea, refine it and get the video in the same chat. No copying prompts between tabs.
Works in Claude and ChatGPT
Connect EveryGen to Claude or ChatGPT once. Then describe the video you want, and your assistant writes the prompt, picks the model and brings the finished clip back into the conversation.
https://everygenai.video/api/mcpDone. Seedance 2.0 Mini, 9:16, 720p, 5 seconds. Here is your video.
Brainstorm the idea, refine it and get the video in the same chat. No copying prompts between tabs.
Videos use the credits in your EveryGen account, the same ones you use on the website. No separate API plan.
Seedance, Kling, Veo, MiniMax and more. Ask your assistant to compare them or pick the right one for the shot.
You connect with your EveryGen login over OAuth and approve one permission: creating videos. Disconnect any time.
On claude.ai or in the Claude desktop app, open Customize, go to Connectors, click + Add and choose Add custom connector.
Name the connector EveryGen and paste this address:
https://everygenai.video/api/mcpClick Connect. Sign in to the EveryGen account whose credits you want to use, then choose Allow.
In any chat, describe the video you want. Claude may ask you to approve the tool call the first time; after that the finished clip appears in the conversation.
Using Claude Code?
Add the server from your terminal, then run /mcp inside Claude Code and sign in to EveryGen.
claude mcp add --transport http everygen https://everygenai.video/api/mcpReal results from the connector. Each clip came from the request on the left; the assistant turned it into the full prompt shown under the video.
Prompt sent to EveryGen
A golden retriever riding a small surfboard on a gentle wave at sunset, slow motion spray, warm golden light, joyful, cinematic, no text
Prompt sent to EveryGen
Luxury product shot: a glass perfume bottle standing on wet black stone, water droplets sliding down, slow orbiting camera, soft studio rim light, premium commercial look, no text or logos
Prompt sent to EveryGen
Cinematic drone shot gliding over a rainy neon-lit city street at night, reflections on wet asphalt, umbrellas moving below, moody blue and pink light, no text
Prompt sent to EveryGen
Stop-motion style: a small paper boat sails across a wooden desk past a coffee cup and pencils, warm desk-lamp light, playful and cozy, no text
Three tools cover the whole job. Your assistant decides when to call them; you only describe the video.
list_video_modelsLists every video model with its durations, resolutions, aspect ratios and credit cost per second.
generate_videoStarts a text-to-video or image-to-video job. Uses credits from the connected account; failed jobs are refunded.
get_video_taskChecks a job and returns the video link when it is ready.
It is a remote Model Context Protocol (MCP) server that lets AI assistants such as Claude and ChatGPT create videos with your EveryGen account. You add it once as a connector; after that the assistant can list models, start a video and fetch the result.
Claude on the web, desktop and mobile, Claude Code, ChatGPT plans and workspaces that allow custom MCP apps, and any other MCP client that supports remote servers.
No. Each video uses the same credits as on the website, based on the model, resolution and length. If a job fails, the credits are returned automatically.
Not for Claude or ChatGPT. You sign in with your EveryGen account and approve access. API keys are only for clients that cannot sign in with OAuth.
Not yet. The connector creates new videos from a prompt or a public image URL. Editing, clipping and trend templates stay on the website for now.
Remove EveryGen from the connectors or apps settings in Claude or ChatGPT. The assistant loses access immediately.
Create your EveryGen account, connect it to Claude or ChatGPT, then ask for your first clip.