ViewMax MCP
Measured conclusion: Deep-tested. L2 outcome: tools_ok.
Generate AI video from any MCP client. Pick the model, see the per-second price before you spend.
| Author | net.viewmaxstudio |
|---|---|
| Access | remote |
| Publisher key required | No |
| Measured state | Deep-tested |
| L1 liveness | alive |
| L1 latency | 1969 ms |
| Last measured | 2026-10-24 |
Add to your agent
Copy this into your MCP client config:
{
"mcpServers": {
"ViewMax MCP": {
"url": "https://viewmaxstudio.net/api/mcp",
"transport": "streamable-http"
}
}
}
Measured tools (4)
generate_videoRender a video from a text prompt using ViewMax Studio. Returns immediately with a job id; the clip is not ready yet. Rendering takes roughly two to four minutes. Call `get_video` with the returned id to collect the result, waiting about 15 seconds between checks. Do not poll faster than that, and tell the user it is rendering rather than going silent while you wait. Credits are charged to the account the API key belongs to, and refunded automatically if the render fails. Available models: - seedance-2-mini: Native audio and multi-shot cuts in one clip. Longest takes we offer. (4–15s, 480p/720p/1080p, with audio) - h3-max: Native 768p with no upscale pass. Fastest turnaround, up to 15s takes. (5–15s, 480p/768p, with audio) - h3-max-turbo: Half the price of H3 Max at the same sizes, and the quickest render we carry. (5–15s, 480p/768p, with audio) - viewmax-agent-2.0: Writes, cuts and scores a whole video from one brief, at any length you ask for. (15s and up, 720p, with audio) Leave `model` unset to use the default. Call `list_video_models` if you need exact per-model limits or prices.
Parameters:
prompt(required) — string — What the clip should show. Describe subject, action, camera move and lighting; vague prompts render poorly.model— string — Which model renders it. Omit for the default model.duration— string — Clip length in seconds, as a string, e.g. "5". Which lengths are accepted depends on the model.resolution— string — Output resolution. Larger costs proportionally more.aspectRatio— string — Frame shape. Use "9:16" for phone-first platforms, "16:9" for landscape, "21:9" for cinematic.generateAudio— boolean — Whether a model that renders its own soundtrack should. Ignored by silent models.negativePrompt— string — What to keep out of the clip. Optional.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
get_videoLook up a render started by `generate_video`. While `status` is "pending" or "processing" the clip is still being made, so wait about 15 seconds and check again. When it is "completed" the result carries a public URL anyone can open, which you should hand the user directly. When it is "failed" the credits have already been refunded.
Parameters:
id(required) — string — The job id returned by `generate_video`.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
get_credit_balanceHow many ViewMax Studio credits the API key holder has left. Worth checking before booking an expensive render, since one that cannot be paid for is refused outright.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
list_video_modelsEvery video model on offer with its exact limits and credit prices: which lengths, resolutions and frame shapes it accepts, whether it renders audio, how long it takes, and what a second of output costs. Use it to choose a model on price or capability, or to quote a cost before rendering.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.