Generate images, videos and SVG with Nano Banana, GPT Image, Seedream, Recraft, Seedance, Kling
Maintained bygenframe.ai(verified)Also a maintainer?
Call this server's tools from your browser. Nothing to install.
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.
Generates one to four pictures with a genframe model and charges the account's credits (price per picture is in list_models; failed pictures are refunded). Returns the picture(s) and download links. Waits up to about 50 seconds; if a picture is still in progress, the result gives its job_id for get_job. Pictures with real people are allowed only as the person's own photos; the content policy of genframe.ai applies.
What to draw. Any language. 3–1500 characters.
Size option if the model has one, e.g. 1K, 2K, 4K (see list_models options.size).
How many pictures (each is charged). Default 1.
Model id from list_models. Default: a fast, cheap general model.
Quality option if the model has one (see list_models options.quality).
For example 1:1, 4:5, 9:16, 16:9, 3:2. The nearest ratio the model makes is used.
What must not be in the picture (only models with negative: true).
Optional reference pictures: public https URLs (JPG, PNG, WebP up to 8 MB) or links returned by this server. Only for models with refMax > 0.
Transparent background (only models with alpha: true).
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.
Run in a terminal
claude mcp add --transport http genframe https://app.genframe.ai/mcp
Generates one to four pictures with a genframe model and charges the account's credits (price per picture is in list_models; failed pictures are refunded). Returns the picture(s) and download links. Waits up to about 50 seconds; if a picture is still in progress, the result gives its job_id for get_job. Pictures with real people are allowed only as the person's own photos; the content policy of genframe.ai applies.
| Argument | Type | Description |
|---|---|---|
| size | string | Size option if the model has one, e.g. 1K, 2K, 4K (see list_models options.size). |
| count | integer | How many pictures (each is charged). Default 1. |
| model | string | Model id from list_models. Default: a fast, cheap general model. |
| prompt* | string | What to draw. Any language. 3–1500 characters. |
| quality | string | Quality option if the model has one (see list_models options.quality). |
| aspect_ratio | string | For example 1:1, 4:5, 9:16, 16:9, 3:2. The nearest ratio the model makes is used. |
| negative_prompt | string | What must not be in the picture (only models with negative: true). |
| reference_image_urls | array | Optional reference pictures: public https URLs (JPG, PNG, WebP up to 8 MB) or links returned by this server. Only for models with refMax > 0. |
| transparent_background | boolean | Transparent background (only models with alpha: true). |
{
"type": "object",
"required": [
"prompt"
],
"properties": {
"size": {
"type": "string",
"description": "Size option if the model has one, e.g. 1K, 2K, 4K (see list_models options.size)."
},
"count": {
"type": "integer",
"maximum": 4,
"minimum": 1,
"description": "How many pictures (each is charged). Default 1."
},
"model": {
"type": "string",
"description": "Model id from list_models. Default: a fast, cheap general model."
},
"prompt": {
"type": "string",
"description": "What to draw. Any language. 3–1500 characters."
},
"quality": {
"type": "string",
"description": "Quality option if the model has one (see list_models options.quality)."
},
"aspect_ratio": {
"type": "string",
"description": "For example 1:1, 4:5, 9:16, 16:9, 3:2. The nearest ratio the model makes is used."
},
"negative_prompt": {
"type": "string",
"description": "What must not be in the picture (only models with negative: true)."
},
"reference_image_urls": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 14,
"description": "Optional reference pictures: public https URLs (JPG, PNG, WebP up to 8 MB) or links returned by this server. Only for models with refMax > 0."
},
"transparent_background": {
"type": "boolean",
"description": "Transparent background (only models with alpha: true)."
}
},
"additionalProperties": false
}Makes an avatar from the user's own photo with a genframe preset and scene (see list_presets). Charged like one picture. Use only a photo of the user themself or of someone who agreed.
| Argument | Type | Description |
|---|---|---|
| style | string | Scene id from list_presets (default: the first). |
| preset* | string | Preset id from list_presets. |
| caption | string | Text on the poster for scenes with a caption; empty string = no text. |
| photo_url | string | The person's photo: public https URL or a link from this server. |
| aspect_ratio | string | Default 4:5. |
| photo_job_id | integer | Or one of the user's genframe pictures. |
{
"type": "object",
"required": [
"preset"
],
"properties": {
"style": {
"type": "string",
"description": "Scene id from list_presets (default: the first)."
},
"preset": {
"type": "string",
"description": "Preset id from list_presets."
},
"caption": {
"type": "string",
"description": "Text on the poster for scenes with a caption; empty string = no text."
},
"photo_url": {
"type": "string",
"description": "The person's photo: public https URL or a link from this server."
},
"aspect_ratio": {
"type": "string",
"description": "Default 4:5."
},
"photo_job_id": {
"type": "integer",
"description": "Or one of the user's genframe pictures."
}
},
"additionalProperties": false
}Starts a video with a genframe model and charges the account's credits (refunded if it fails). Videos take about 1–6 minutes: the result gives a job_id; call get_job with wait_seconds to get the link when it is ready. Optional first/last frame pictures as public https URLs or links from this server.
| Argument | Type | Description |
|---|---|---|
| audio | boolean | Sound, for models that offer it (may change the price). |
| model | string | Video model id from list_models. Default: an inexpensive model. |
| prompt* | string | What happens in the video. Any language. 3–1500 characters. |
| duration | integer | Seconds, one of the model's options.duration (default 5 when offered). |
| resolution | string | One of the model's options.resolution, e.g. 480p, 720p, 1080p (1080p and above need the Про plan). |
| aspect_ratio | string | For example 16:9, 9:16, 1:1. With a first frame the frame's proportions win. |
| last_frame_url | string | Picture to end on (only models whose inputs.last is true; needs first_frame_url). |
| first_frame_url | string | Picture to start the video from (image-to-video). |
{
"type": "object",
"required": [
"prompt"
],
"properties": {
"audio": {
"type": "boolean",
"description": "Sound, for models that offer it (may change the price)."
},
"model": {
"type": "string",
"description": "Video model id from list_models. Default: an inexpensive model."
},
"prompt": {
"type": "string",
"description": "What happens in the video. Any language. 3–1500 characters."
},
"duration": {
"type": "integer",
"description": "Seconds, one of the model's options.duration (default 5 when offered)."
},
"resolution": {
"type": "string",
"description": "One of the model's options.resolution, e.g. 480p, 720p, 1080p (1080p and above need the Про plan)."
},
"aspect_ratio": {
"type": "string",
"description": "For example 16:9, 9:16, 1:1. With a first frame the frame's proportions win."
},
"last_frame_url": {
"type": "string",
"description": "Picture to end on (only models whose inputs.last is true; needs first_frame_url)."
},
"first_frame_url": {
"type": "string",
"description": "Picture to start the video from (image-to-video)."
}
},
"additionalProperties": false
}Shows the genframe account connected to this chat: credits balance, plan and how many generations can run at once. Free.
No arguments.
{
"type": "object",
"required": [],
"properties": {},
"additionalProperties": false
}Status of a generation by job_id: running, done (with the picture or video link) or failed (credits refunded). wait_seconds (0–50) waits for it to finish. Free.
| Argument | Type | Description |
|---|---|---|
| job_id* | integer | |
| wait_seconds | integer |
{
"type": "object",
"required": [
"job_id"
],
"properties": {
"job_id": {
"type": "integer"
},
"wait_seconds": {
"type": "integer",
"maximum": 50,
"minimum": 0
}
},
"additionalProperties": false
}The latest pictures and videos of this account (newest first) with job ids and download links. Free.
| Argument | Type | Description |
|---|---|---|
| kind | string | |
| limit | integer |
{
"type": "object",
"required": [],
"properties": {
"kind": {
"enum": [
"image",
"video",
"all"
],
"type": "string"
},
"limit": {
"type": "integer",
"maximum": 40,
"minimum": 1
}
},
"additionalProperties": false
}Lists the genframe models available to this account with their price in credits per option, aspect ratios, resolutions, durations and which inputs (reference pictures, first/last frame) they take. Call it before generating if you are unsure which model or option to use. Free.
| Argument | Type | Description |
|---|---|---|
| kind | string | Only picture models, only video models, or all (default). |
{
"type": "object",
"required": [],
"properties": {
"kind": {
"enum": [
"image",
"video",
"all"
],
"type": "string",
"description": "Only picture models, only video models, or all (default)."
}
},
"additionalProperties": false
}Lists genframe «Готовые промты» presets: turn a person's photo into a stylised avatar (e.g. crime-game poster, spy film poster). Each has several scenes (styles). Free.
No arguments.
{
"type": "object",
"required": [],
"properties": {},
"additionalProperties": false
}Removes the background of a picture (PNG with transparency; from the Дизайн plan, charged in credits). Give job_id of one of your genframe pictures or image_url.
| Argument | Type | Description |
|---|---|---|
| job_id | integer | |
| image_url | string |
{
"type": "object",
"required": [],
"properties": {
"job_id": {
"type": "integer"
},
"image_url": {
"type": "string"
}
},
"additionalProperties": false
}Doubles the size of a picture with Topaz (from the Дизайн plan, charged in credits). Give job_id of one of your genframe pictures or image_url.
| Argument | Type | Description |
|---|---|---|
| job_id | integer | |
| image_url | string |
{
"type": "object",
"required": [],
"properties": {
"job_id": {
"type": "integer"
},
"image_url": {
"type": "string"
}
},
"additionalProperties": false
}Turns a picture into a vector SVG with Recraft (charged in credits, see list_models tools). Give job_id of one of your genframe pictures, or image_url (public https, JPG/PNG/WebP, sides 256–4096 px).
| Argument | Type | Description |
|---|---|---|
| pro | boolean | Recraft Pro vectorizer (more detail, more credits). |
| job_id | integer | |
| image_url | string |
{
"type": "object",
"required": [],
"properties": {
"pro": {
"type": "boolean",
"description": "Recraft Pro vectorizer (more detail, more credits)."
},
"job_id": {
"type": "integer"
},
"image_url": {
"type": "string"
}
},
"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 20, 2026.