# ViewMax MCP

> Remote MCP for AI video, image, music and speech generation.

- name: io.github.bytevirts/viewmax
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 94/100
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.bytevirts%2Fviewmax
- tools: https://api.protogrid.dev/v1/servers/io.github.bytevirts%2Fviewmax/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "viewmax": {
      "type": "http",
      "url": "https://viewmax.studio/api/mcp",
      "headers": {
        "Authorization": "Bearer ${VIEWMAX_TOKEN}"
      }
    }
  }
}
```

Placeholders to fill: `${VIEWMAX_TOKEN}`.

## Trust

- hygiene: 100
- liveness: 99
- freshness: 85
- provenance: 90
- drivers: +repository +namespace-matches-repo +website +reachable +uptime-97% ~updated-65d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (good)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 14 of 14 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 2,221 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 25 (weight 15)

- warn `stability.changes`: 23 tool changes in 30 days
- fail `stability.rug_pull`: 4 tools kept their name but changed most of their description in 30 days; review before trusting them

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 14, about 2,221 tokens to load them all
- tool set hash: 5db5dcc360a0f699567df5fa349a37f6
- tools last changed: 2026-10-03T02:36:55.711Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.bytevirts/viewmax.svg)](https://protogrid.dev/servers/io.github.bytevirts/viewmax)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-03 `list_voices` changed (annotations)
- 2026-10-03 `list_music_models` changed (annotations)
- 2026-10-03 `get_image_model` changed (annotations)
- 2026-10-03 `list_image_models` changed (annotations)
- 2026-10-03 `get_credits` changed (annotations)
- 2026-10-03 `wait_for_task` changed (annotations)
- 2026-10-03 `get_task` changed (annotations)
- 2026-10-03 `get_video_model` changed (annotations)
- 2026-10-03 `list_video_models` changed (annotations)
- 2026-09-30 `generate_sound_effect` changed (description, inputSchema, annotations)
  - before: Generate a sound effect from a text prompt. This consumes credits. Renders synchronously: the result usually returns immediately with output_urls.
  - after: Generate a sound effect from a text prompt. Costs 5 credits. Renders synchronously: the result usually returns immediately with output_urls.

Full history: https://api.protogrid.dev/v1/servers/io.github.bytevirts%2Fviewmax/changes

## Remotes

- https://viewmax.studio/api/mcp (streamable-http, auth none, reachable true, uptime30d 0.97321427)

## Packages

_none_

## Tools (14)

- `generate_image`: Create an image generation task (text-to-image, or image-to-image when image_urls are provided). Pro/Ultra flagship models (GPT Image 2, GPT Image 2.5, Nano Banana 2, Grok Imagine) and Ultra ViewMax C1 cost 0 credits within the shared daily fair-use pool; otherwise this consumes credits. Call wait_for_task with the task_id for the result URLs.
- `generate_music`: Create an original music track from a text prompt. Costs 60 credits for tracks up to 60 seconds, then 1 credit per second (duration_seconds defaults to 60); plan allowances do not cover music. Setting style sends prompt as the song's lyrics, so do not also send lyrics; to describe a track, put the description in prompt and omit style. Music renders synchronously: the result usually returns immediately with output_urls.
- `generate_sound_effect`: Generate a sound effect from a text prompt. Costs 5 credits. Renders synchronously: the result usually returns immediately with output_urls.
- `generate_speech`: Convert text to speech with a selected voice_id (see list_voices). Costs ceil(characters / 20) credits, minimum 1. Speech renders synchronously: the result usually returns immediately with output_urls.
- `generate_video`: Create a video generation task and return its task_id. mode defaults to image-to-video when image_urls are given, else video-to-video when video_urls are given, else text-to-video. Omitted duration, resolution and aspect_ratio use the mode's defaults from get_video_model and are billed at those values. Ultra ViewMax C1 generations cost 0 credits within the daily fair-use pool (also via REST API); otherwise this consumes credits from the authenticated ViewMax account. Call wait_for_task with the task_id until it finishes.
- `get_credits`: Get the authenticated account's remaining credits. Generation consumes credits.
- `get_image_model`: Get full capabilities and credit pricing for one image model. Generating an image with this model consumes credits.
- `get_task`: Get the current status, output URLs and cost_credits for one of the authenticated user's tasks (video, image, music, or audio). Failed and canceled tasks include error_code and error_message; their credits are refunded automatically.
- `get_video_model`: Get full capabilities and credit pricing for one video model. Each mode lists durations, resolutions, aspect_ratios, audio_toggle, credits, and defaults: the duration, resolution and aspect_ratio that generate_video sends and bills when you omit them. max_prompt_length is present when the model limits prompt length. Generating a video with this model consumes credits.
- `list_image_models`: List available image models with their modes (text-to-image, image-to-image), aspect ratios, qualities, and credit labels. Image generation consumes credits.
- `list_music_models`: List available music models and their controls (duration, instrumental) and credit cost. Music costs 60 credits for tracks up to 60 seconds, then 1 credit per second.
- `list_video_models`: List available video models and their capabilities. Video generation consumes credits; use get_video_model for detailed pricing and the values used when options are omitted.
- `list_voices`: List available text-to-speech voices (id, name, gender, accent, language) and speech pricing: characters_per_credit and minimum_credits. A generation costs ceil(characters / 20) credits, minimum 1.
- `wait_for_task`: Wait up to timeout_seconds (1-50, default 45) for a task and return its latest status in the get_task shape. Some videos take several minutes: keep calling wait_for_task until status is success, failed, or canceled. Task results are persisted and never lost.