# Arumi (remote · api.arumi.ai)

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

- Trust score: 75/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `api.arumi.ai`: 75/100 (this document), [markdown](https://verifymcp.io/servers/weidotbuild-arumi/api.md), [page](https://verifymcp.io/servers/weidotbuild-arumi/api)

## Channel facts

- Endpoint: `https://api.arumi.ai/mcp`
- Transports: `streamable-http`
- Auth: `required (not validated)`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 77/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 401, which proves neither a plaintext path nor enforcement.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 69/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 874 tokens (~97/item across 9 items; 9 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 50/100
  - Stability observed for 15 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 96/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 86% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 50/100
  - Injection-marker check failed: the server instructions contains an instruction to conceal the call from the user, the text "without telling the user", at byte 828 of that field.
  - We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Arumi MCP server?

Arumi is a hosted endpoint at https://api.arumi.ai/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http weidotbuild-arumi 'https://api.arumi.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "weidotbuild-arumi": {
      "url": "https://api.arumi.ai/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "weidotbuild-arumi": {
      "type": "http",
      "url": "https://api.arumi.ai/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.weidotbuild-arumi]
url = "https://api.arumi.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "weidotbuild-arumi": {
      "type": "remote",
      "url": "https://api.arumi.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add weidotbuild-arumi --url 'https://api.arumi.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  weidotbuild-arumi:
    url: "https://api.arumi.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "weidotbuild-arumi": {
      "Transport": "http",
      "Url": "https://api.arumi.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add weidotbuild-arumi -t streamable-http -u 'https://api.arumi.ai/mcp'
```

### Other

```json
{
  "mcpServers": {
    "weidotbuild-arumi": {
      "type": "http",
      "url": "https://api.arumi.ai/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-21 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-18 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-16 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-15 (score 72, 0)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-11-14 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-12 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-10 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-08 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (9)

### `complete_upload` (~35 tokens)

Finish an upload after the PUT; returns the asset_id to pass in a generation's references.

Input parameters:

- `upload_id` (string, required)

Output parameters:

- `asset_id` (string)
- `duration_seconds` (number)
- `kind` (string)
- `name` (string)

### `create_upload` (~144 tokens)

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.

Input parameters:

- `content_type` (string, required): for example image/png, image/jpeg, video/mp4, audio/mpeg
- `file_name` (string, required): the file's name, with its extension
- `height` (integer): required for images: height in pixels
- `sha256` (string, required): the file's SHA-256 as 64 lower-case hex characters (shasum -a 256)
- `size_bytes` (integer, required)
- `width` (integer): required for images: width in pixels

Output parameters:

- `expires_at` (string)
- `headers` (object)
- `next` (string)
- `upload_id` (string)
- `upload_url` (string)

### `generate` (~193 tokens)

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.

Input parameters:

- `idempotency_key` (string): optional, 16-128 characters [A-Za-z0-9._:-]: repeating a call with the same key returns the same generation instead of making another
- `max_credits` (integer, required): the most credits the user agreed to spend on this generation; it is refused when the quote is higher
- `model` (string, required): the model id from list_models
- `parameters` (object): the model's settings by key (get_model); any left out take the model's default
- `prompt` (string): what to make; for speech models the text to read
- `references` (null|object): uploaded files the model works from

Output parameters:

- `created_at` (string)
- `credits` (object)
- `error` (null|object)
- `generation_id` (string)
- `modality` (string)
- `model` (string)
- `outputs` (null|array)
- `progress` (integer)
- `prompt` (string)
- `status` (string): queued, processing, succeeded, failed or unknown
- `text` (string)
- `tip` (string)

### `get_balance` (~34 tokens)

The user's Arumi credits: available, held by running generations, and owed. 1 credit = 0.01 USD.

### `get_generation` (~36 tokens)

A generation's status; once it has succeeded, links to its results, and what it charged.

Input parameters:

- `generation_id` (string, required)

Output parameters:

- `created_at` (string)
- `credits` (object)
- `error` (null|object)
- `generation_id` (string)
- `modality` (string)
- `model` (string)
- `outputs` (null|array)
- `progress` (integer)
- `prompt` (string)
- `status` (string): queued, processing, succeeded, failed or unknown
- `text` (string)
- `tip` (string)

### `get_model` (~43 tokens)

One model's prompt limit, the reference files it takes, and its settings with their allowed values and defaults.

Input parameters:

- `model` (string, required): the model id from list_models

Output parameters:

- `id` (string)
- `maker` (string)
- `modality` (string)
- `name` (string)
- `prompt` (object)
- `reference_inputs` (null|array): in order: references of one kind fill these slots in turn
- `settings` (null|array)

### `list_generations` (~48 tokens)

The user's latest generations, newest first, made on the site or through any of their keys.

Input parameters:

- `limit` (integer): how many, newest first (1–20, default 10)

### `list_models` (~55 tokens)

The models the user can generate with, by kind (image, video, audio, text). get_model gives one model's inputs and settings.

Input parameters:

- `modality` (string): only this kind: image, video, audio or text

### `quote` (~97 tokens)

What a generation would cost, in credits, without making it. Tell the user before generating.

Input parameters:

- `model` (string, required): the model id from list_models
- `parameters` (object): the model's settings by key (get_model); any left out take the model's default
- `prompt` (string): what to make; for speech models the text to read
- `references` (null|object): uploaded files the model works from

Output parameters:

- `credits` (integer): what is reserved; for a fixed price also what is charged; for a speech model priced by length, the most it charges
- `estimated_credits` (integer)
- `exact` (boolean): true when the price is fixed; false when the model decides part of it, or a speech model charges by the length it actually speaks, and only up to credits is charged
- `model` (string)
- `usd` (string): credits in US dollars at 1 credit = 0.01 USD

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/weidotbuild-arumi/api#diagnostics

## Score history

- 2026-11-21: 75
- 2026-11-20: 74
- 2026-11-19: 74
- 2026-11-18: 74
- 2026-11-17: 73
- 2026-11-16: 73
- 2026-11-15: 72
- 2026-11-14: 72
- 2026-11-13: 71
- 2026-11-12: 71
- 2026-11-11: 70
- 2026-11-10: 70
- 2026-11-09: 69
- 2026-11-08: 69
- 2026-11-07: 68
- 2026-11-06: 68

## Common questions

### What is the Arumi MCP server?

Arumi is an MCP server listed in the public MCP registry as io.github.weidotbuild/arumi. Generate AI images, video and audio with 55 models, priced in credits before you generate. This page covers its hosted endpoint (https://api.arumi.ai/mcp).

### Is the Arumi MCP server safe to use?

Arumi scores 75 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Arumi MCP server expose?

Arumi exposes 9 tools: complete_upload, create_upload, generate, get_balance, get_generation, and 4 more. Their descriptions and schemas cost roughly 685 tokens of context every time the server is loaded.

### Does the Arumi MCP server require authentication?

Yes. Arumi asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the Arumi MCP server still maintained?

Arumi is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Arumi MCP server?

VerifyMCP ran 12 checks on Arumi, covering TLS certificate, Authorization, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about Arumi: HTTPS. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://api.arumi.ai/mcp
- Authorisation metadata: https://api.arumi.ai/.well-known/oauth-protected-resource/mcp
- Repository: https://github.com/weidotbuild/arumi
- Website: https://arumi.ai/mcp
- Changelog RSS feed: https://verifymcp.io/servers/weidotbuild-arumi/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/weidotbuild-arumi/api/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/weidotbuild-arumi/api.json
- HTML version of this page: https://verifymcp.io/servers/weidotbuild-arumi/api
