Generate short videos from a text prompt. Pay per clip by card, no account needed.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Optional Bearer API key. generate_video can pay per clip without one. Reading a video requires it.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Generate a short video from a text prompt. Costs $1.00 per 5-second 540x960 clip, payable by card over the Machine Payments Protocol -- no account needed. Returns immediately with a video id; rendering takes 30-90 seconds, so poll get_video_status until it is READY or ERROR.
Text prompt describing the video you want to generate
Random seed for reproducibility
Optional https URL or base64 photo. When set, the clip is that photo animated for one purchase: duration and resolution are locked to the clip offer.
Duration of the video in seconds (5-60)
Quality tier key (540x960 or 720x1280). These are tier identifiers, not the output size. On the Wan backend 540x960 renders at 480x832 and is stored upscaled to 540x960, and 720x1280 produces 720x1280 portrait. Read output_width/output_height on the video for the actual dimensions. Omitting the field selects 540x960. The 180x320 and 360x640 tiers are retired: they produced the same 480x832 file as 540x960 and are no longer accepted.
Negative prompt to avoid certain content
Machine Payments Protocol credential answering the challenge from an earlier payment_required result. Omit it when calling with an API key that has credits.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
claude mcp add --transport http video https://sisif.ai/mcp
Headers
Authorization (optional, not in the config above): Optional Bearer API key. generate_video can pay per clip without one. Reading a video requires it.Generate a short video from a text prompt. Costs $1.00 per 5-second 540x960 clip, payable by card over the Machine Payments Protocol -- no account needed. Returns immediately with a video id; rendering takes 30-90 seconds, so poll get_video_status until it is READY or ERROR.
| Argument | Type | Description |
|---|---|---|
| seed | integer | Random seed for reproducibility |
| image | string | Optional https URL or base64 photo. When set, the clip is that photo animated for one purchase: duration and resolution are locked to the clip offer. |
| prompt* | string | Text prompt describing the video you want to generate |
| duration | integer | Duration of the video in seconds (5-60) |
| resolution | string | Quality tier key (540x960 or 720x1280). These are tier identifiers, not the output size. On the Wan backend 540x960 renders at 480x832 and is stored upscaled to 540x960, and 720x1280 produces 720x1280 portrait. Read output_width/output_height on the video for the actual dimensions. Omitting the field selects 540x960. The 180x320 and 360x640 tiers are retired: they produced the same 480x832 file as 540x960 and are no longer accepted. |
| negative_prompt | string | Negative prompt to avoid certain content |
| payment_credential | string | Machine Payments Protocol credential answering the challenge from an earlier payment_required result. Omit it when calling with an API key that has credits. |
{
"type": "object",
"required": [
"prompt"
],
"properties": {
"seed": {
"type": "integer",
"description": "Random seed for reproducibility"
},
"image": {
"type": "string",
"description": "Optional https URL or base64 photo. When set, the clip is that photo animated for one purchase: duration and resolution are locked to the clip offer."
},
"prompt": {
"type": "string",
"maxLength": 1000,
"description": "Text prompt describing the video you want to generate"
},
"duration": {
"type": "integer",
"default": 5,
"maximum": 60,
"minimum": 5,
"description": "Duration of the video in seconds (5-60)"
},
"resolution": {
"enum": [
"540x960",
"720x1280"
],
"type": "string",
"default": "540x960",
"description": "Quality tier key (540x960 or 720x1280). These are tier identifiers, not the output size. On the Wan backend 540x960 renders at 480x832 and is stored upscaled to 540x960, and 720x1280 produces 720x1280 portrait. Read output_width/output_height on the video for the actual dimensions. Omitting the field selects 540x960. The 180x320 and 360x640 tiers are retired: they produced the same 480x832 file as 540x960 and are no longer accepted."
},
"negative_prompt": {
"type": "string",
"maxLength": 500,
"description": "Negative prompt to avoid certain content"
},
"payment_credential": {
"type": "string",
"description": "Machine Payments Protocol credential answering the challenge from an earlier payment_required result. Omit it when calling with an API key that has credits."
}
},
"additionalProperties": false
}Read the state of one video you started. Returns PENDING, PROCESSING, READY or ERROR, and the file URL once it is READY. Requires the API key that owns it.
| Argument | Type | Description |
|---|---|---|
| video_id* | integer | The id generate_video returned. |
{
"type": "object",
"required": [
"video_id"
],
"properties": {
"video_id": {
"type": "integer",
"description": "The id generate_video returned."
}
},
"additionalProperties": false
}List the videos belonging to the calling API key, newest first. Requires an API key.
| Argument | Type | Description |
|---|---|---|
| limit | integer | How many videos to return. |
| status | string | Keep only videos in this state. |
{
"type": "object",
"required": [],
"properties": {
"limit": {
"type": "integer",
"default": 20,
"maximum": 100,
"minimum": 1,
"description": "How many videos to return."
},
"status": {
"enum": [
"PENDING",
"QUEUED",
"RETRYING",
"PROCESSING",
"READY",
"ERROR",
"REFUNDED"
],
"type": "string",
"description": "Keep only videos in this state."
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 3, 2026.