complete_upload
Finish an upload after the PUT; returns the asset_id to pass in a generation's references.
upload_idrequired
io.github.weidotbuildPublished by GitHub account weidotbuildv1.0.0Updated Nov 7, 2026
Generate AI images, video and audio with 55 models, priced in credits before you generate.
Remote MCP server that lets an assistant generate AI images, video, audio and music with Arumi's models, quoting the credit cost before each run.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.weidotbuild%2Farumi/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Add this to your client's mcpServers config.
{
"mcpServers": {
"arumi": {
"type": "http",
"url": "https://api.arumi.ai/mcp",
"headers": {
"Authorization": "Bearer <YOUR_TOKEN>"
}
}
}
}[Arumi — AI images, video, audio and music in one studio]
Arumi is an AI studio for images, video, audio and music. Write a prompt, pick the model that fits the job, see the price in credits before you generate, and keep every result in one history.
Background remover · Image upscaler · Object remover · Background changer · Old photo restoration · Video upscaler · Animate old photos
Hotel Lobby AI video · Photo to anime · Photo to collage poster · Photo to ugly doodle — see them all in Explore.
These run entirely in your browser: no sign-up, no credits, no watermark.
Split image · Join images · Add watermark · Audio trimmer · MP3 to video · Video trimmer · Add audio to video
Arumi is a remote MCP server over Streamable HTTP. Create an API key on the API keys page, set a monthly credit limit for it, and add it to your assistant.
Claude Code
Codex
Cursor and other clients
Then ask in plain words — "Make a 5-second video of a lighthouse at dusk." Your assistant checks the price first, then generates.
Your assistant only spends credits within the monthly limit you set on the key. Full guide: arumi.ai/mcp.
One-time credit packs from $9.99 for 1,000 credits. Paid credits stay valid for 120 days from your latest purchase, and an unused pack can be refunded within 14 days. Sign-up credits are free. See pricing.
Source: README.md at commit 3dcf146
Finish an upload after the PUT; returns the asset_id to pass in a generation's references.
upload_idrequiredStart uploading one of the user's files to use as a reference. PUT the file's bytes to upload_url with exactly the returned headers, then call complete_upload.
widthheightsha256requiredfile_namerequiredsize_bytesrequiredcontent_typerequiredStart a generation with the user's credits. It is refused, with nothing charged, when it would cost more than max_credits. Returns at once with a generation_id: call get_generation until it has succeeded or failed.
modelrequiredpromptparametersreferencesmax_creditsrequiredidempotency_keyThe user's Arumi credits: available, held by running generations, and owed. 1 credit = 0.01 USD.
Takes no parameters.
A generation's status; once it has succeeded, links to its results, and what it charged.
generation_idrequiredOne model's prompt limit, the reference files it takes, and its settings with their allowed values and defaults.
modelrequiredThe user's latest generations, newest first, made on the site or through any of their keys.
limitThe models the user can generate with, by kind (image, video, audio, text). get_model gives one model's inputs and settings.
modalityWhat a generation would cost, in credits, without making it. Tell the user before generating.
modelrequiredpromptparametersreferences100% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
claude mcp add --transport http arumi https://api.arumi.ai/mcp --header "Authorization: Bearer YOUR_API_KEY"export ARUMI_API_KEY="YOUR_API_KEY"codex mcp add arumi --url https://api.arumi.ai/mcp --bearer-token-env-var ARUMI_API_KEY{ "mcpServers": { "arumi": { "url": "https://api.arumi.ai/mcp", "headers": { "Authorization": "Bearer YOUR_API_KEY" } } }}