mcpbeat Sign in

Arumi MCP Server

by weidotbuild Your server? Claim it
answering

Arumi is answering right now. Last checked 8 min ago. It exposes 9 tools. Last commit 6 Nov 2026.

Generate AI images, video and audio with 55 models, priced in credits before you generate.

Uptime history 21 hours of history
21 hours agonow
100.0%
Uptime 24h
75 of 75 checks
9
Tools
read from the server
505 ms
Response time
average over 24h
0
Stars
last commit 6 Nov 2026

Nothing serious here today

Today is the operative word: we check Arumi every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 8 min ago.

run in your terminal
claude mcp add arumi --transport http https://api.arumi.ai/mcp
Settings → Connectors → Add custom connector, then paste this address
https://api.arumi.ai/mcp
~/.codex/config.toml
[mcp_servers.arumi]
url = "https://api.arumi.ai/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "arumi": {
      "url": "https://api.arumi.ai/mcp"
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "arumi": {
      "type": "http",
      "url": "https://api.arumi.ai/mcp"
    }
  }
}

Available tools 9

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

balance
get_balance
The user's Arumi credits: available, held by running generations, and owed. 1 credit = 0.01 USD.
complete
complete_upload
Finish an upload after the PUT; returns the asset_id to pass in a generation's references.
generate
generate
Start 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.
generation
get_generation
A generation's status; once it has succeeded, links to its results, and what it charged.
generations
list_generations
The user's latest generations, newest first, made on the site or through any of their keys.
model
get_model
One model's prompt limit, the reference files it takes, and its settings with their allowed values and defaults.
models
list_models
The models the user can generate with, by kind (image, video, audio, text). get_model gives one model's inputs and settings.
quote
quote
What a generation would cost, in credits, without making it. Tell the user before generating.
upload
create_upload
Start 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.

Endpoints

URLTransportStateLatencyChecked
https://api.arumi.ai/mcp streamable-http answering 468 ms 8 min ago

Alternatives to Arumi

same job, measured the same way
fal.ai
by fal-ai-community

Generate and edit images, video, audio and 3D with fal. Discover models and check prices.

answering
Yir
by yir

Generate images, videos and audio across many AI models via one API, with quotes before you pay.

answering
Mage
by mage

Generate AI images, video, and audio with many frontier models, private by default.

answering
EvoLink
by evolink

150+ image, video and audio models. Quote before you generate; pay as you go.

answering
Azurade AI
by azurade

Generate images and videos with frontier AI models. Pay per use; credits never expire.

answering
Vidaro Studio
by vidarostudio

Generate AI images and videos via OAuth; uses your Vidaro credits.

17 tools answering
Picsart GenAI
by picsart-api

The official Picsart MCP server: generate and edit images, video and audio with 150+ models.

34 tools answering
Muapi
by anil-matcha

Generate images, videos, and audio using 100+ AI models via muapi.ai.

48 installs/wk local only

Arumi — questions

Answers built from our own checks of this server.

What can Arumi do?
It exposes 9 tools, read directly from the server on our last check. Among them: complete_upload, create_upload, generate, get_balance, get_generation, get_model and 3 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is Arumi working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 75 of 75 checks got a reply (100.0%), average response time 505 ms. The bar chart above shows every period we have measured.
How do I connect Arumi?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Arumi need an API key?
No. Arumi completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 9 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Arumi?
It answers our handshake in 505 ms on average, which is faster than 23% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is Arumi open source?
The code is open source: it is published under the MIT licence and 0 stars on GitHub. The licence covers the code in the repository, not the hosted service at api.arumi.ai, which runs on its operator's own terms.