Photo AI Studio
AI photos from a selfie across 150+ themes, plus 19 image edits and AI video.
我该使用它吗
质量与安全性
发现（1）
- LOWTool 'browse_themes' suggests web access but openWorldHint=false在 browse_themes 中
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"photo-ai-studio": {
"url": "https://www.photoaistudio.com/api/mcp"
}
}
}远程端点
https://www.photoaistudio.com/api/mcpstreamable-http它能做什么
工具清单
工具（12）
🟢list_photo_themes
List Photo AI Studio photo theme categories (professional headshots, dating, wedding, graduation, and many more) with the URL of each category page.
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢get_pricing
Get Photo AI Studio credit-package and subscription pricing, plus the credit cost per generated photo.
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢get_service_overview
Get an overview of Photo AI Studio: what it does, when to use it, best-fit use cases, and the key links agents need (llms.txt content).
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢get_api_capabilities
Explain how an agent actually calls Photo AI Studio: connecting over MCP, the unauthenticated discovery endpoints, the REST fulfillment API, and how to buy credits.
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢get_account
Get the connected Photo AI Studio account: credit balance, total predictions, and membership date. Check this before generating, because every photo costs credits. Requires a connected Photo AI Studio account. Calling this tool starts the sign-in flow.
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢browse_themes(gender, tag)
Browse the photo themes available for generation, optionally filtered by gender category or a keyword. Returns the theme slugs that generate_photo expects. Requires a connected Photo AI Studio account. Calling this tool starts the sign-in flow.
输入模式
{
"type": "object",
"properties": {
"gender": {
"type": "string",
"enum": [
"male",
"female",
"groups",
"pets",
"product"
],
"description": "Filter themes by gender category"
},
"tag": {
"type": "string",
"description": "Search themes by name or keyword"
}
},
"additionalProperties": false
}🟡upload_image(image_url, image_base64)
Upload an image to the Photo AI Studio CDN and get back a URL. generate_photo, edit_image, and create_video all take CDN URLs, so start here. Accepts a public image URL or base64 data, up to 10 MB. Requires a connected Photo AI Studio account. Calling this tool starts the sign-in flow.
输入模式
{
"type": "object",
"properties": {
"image_url": {
"type": "string",
"description": "Public URL of the image to upload"
},
"image_base64": {
"type": "string",
"description": "Base64-encoded image data, raw or as a data URI. Use this when the image is not already on the web."
}
},
"additionalProperties": false
}🟡generate_photo(images, gender, category, type, prompt, ...)
Generate AI photos from face images, using a preset theme or a custom prompt. Costs 100 credits per photo. Upload the face photos with upload_image first, and find theme slugs with browse_themes. Requires a connected Photo AI Studio account. Calling this tool starts the sign-in flow.
输入模式
{
"type": "object",
"properties": {
"images": {
"type": "array",
"items": {
"type": "string"
},
"description": "CDN URLs of face photos (1-9), from upload_image"
},
"gender": {
"type": "string",
"enum": [
"male",
"female",
"groups",
"pets",
"product"
],
"description": "Gender category for theme selection"
},
"category": {
"type": "string",
"description": "Theme slug from browse_themes, required when type is themed"
},
"type": {
"type": "string",
"enum": [
"themed",
"custom"
],
"description": "themed uses a preset style, custom uses your prompt"
},
"prompt": {
"type": "string",
"description": "Custom prompt, required when type is custom"
},
"num_images": {
"type": "number",
"description": "Number of variations to generate (1-4)"
},
"style": {
"type": "string",
"description": "Style override, for example \"realistic\""
},
"aspect_ratio": {
"type": "string",
"enum": [
"1:1",
"2:3",
"3:2",
"16:9",
"9:16"
],
"description": "Output aspect ratio"
},
"wait_for_result": {
"type": "boolean",
"description": "Wait up to 55 seconds for the result before returning. Defaults to false: the tool returns a prediction_id immediately and you poll get_prediction, which is the reliable pattern for photos and videos."
}
},
"required": [
"images",
"gender"
],
"additionalProperties": false
}🔴edit_image(operation, image_url, prompt, hairstyle, hair_color, ...)
Edit a photo with one of 19 AI operations. Credit costs: remove_background 10, replace_background 3, everything else 100. Operations and their required arguments: - remove_background (image_url) - replace_background (image_url, prompt) - retouch (image_url, prompt) - skin (image_url) - hair (image_url, plus hairstyle or reference_image_url) - makeup (image_url) - age (image_url, target_age) - expression (image_url, target_expression) - body_type (image_url, target_body_type) - eye_color (image_url, target_eye_color) - color_correction (image_url) - custom (image_url, prompt) - clothes (image_url, clothes_image_url) - try_on (image_url, clothes_image_url) - product (image_url, product_image_url) - upscale (image_url) - restore (image_url) - face_swap (source_image_url, target_image_url) - extend (image_url) Every image argument must be a CDN URL from upload_image. Requires a connected Photo AI Studio account. Calling this tool starts the sign-in flow.
输入模式
{
"type": "object",
"properties": {
"operation": {
"type": "string",
"enum": [
"remove_background",
"replace_background",
"retouch",
"skin",
"hair",
"makeup",
"age",
"expression",
"body_type",
"eye_color",
"color_correction",
"custom",
"clothes",
"try_on",
"product",
"upscale",
"restore",
"face_swap",
"extend"
],
"description": "The edit operation to perform"
},
"image_url": {
"type": "string",
"description": "CDN URL of the image to edit, required for every operation except face_swap"
},
"prompt": {
"type": "string",
"description": "Text prompt for replace_background, retouch, and custom"
},
"hairstyle": {
"type": "string",
"description": "Target hairstyle for the hair operation"
},
"hair_color": {
"type": "string",
"description": "Target hair color for the hair operation"
},
"reference_image_url": {
"type": "string",
"description": "Reference image for hair or custom"
},
"target_age": {
"type": "number",
"description": "Target age for the age operation"
},
"target_expression": {
"type": "string",
"description": "Target expression, for example \"happy\""
},
"target_body_type": {
"type": "string",
"description": "Target body type"
},
"target_eye_color": {
"type": "string",
"description": "Target eye color"
},
"clothes_image_url": {
"type": "string",
"description": "Clothes image for clothes and try_on"
},
"product_image_url": {
"type": "string",
"description": "Product image for the product operation"
},
"source_image_url": {
"type": "string",
"description": "Source face image for face_swap"
},
"target_image_url": {
"type": "string",
"description": "Target image for face_swap"
},
"num_images": {
"type": "number",
"description": "Number of variations for try_on (1-4)"
},
"wait_for_result": {
"type": "boolean",
"description": "Wait up to 55 seconds for the result before returning. Defaults to false: the tool returns a prediction_id immediately and you poll get_prediction, which is the reliable pattern for photos and videos."
}
},
"required": [
"operation"
],
"additionalProperties": false
}🟡create_video(type, image_url, prompt, resolution, duration, ...)
Create an AI video. Costs 500 credits for a video, or 100 credits for a product_holder image. Types: - image_to_video: animate an image (image_url, prompt) - ugc: a spokesperson video from a script (script, voice_id) - product_holder: a person presenting a product (product_image_url) Requires a connected Photo AI Studio account. Calling this tool starts the sign-in flow.
输入模式
{
"type": "object",
"properties": {
"type": {
"type": "string",
"enum": [
"image_to_video",
"ugc",
"product_holder"
],
"description": "Type of video to create"
},
"image_url": {
"type": "string",
"description": "CDN URL of the image to animate"
},
"prompt": {
"type": "string",
"description": "Animation prompt, required for image_to_video"
},
"resolution": {
"type": "string",
"description": "Video resolution, default 720p"
},
"duration": {
"type": "number",
"description": "Duration in seconds, default 4"
},
"aspect_ratio": {
"type": "string",
"description": "Output aspect ratio"
},
"script": {
"type": "string",
"description": "UGC script, up to 150 characters"
},
"voice_id": {
"type": "string",
"description": "Voice ID for UGC"
},
"emotion": {
"type": "string",
"description": "UGC emotion, default neutral"
},
"language": {
"type": "string",
"description": "UGC language, default English"
},
"gender": {
"type": "string",
"description": "UGC model gender"
},
"person_image_url": {
"type": "string",
"description": "Person image for product_holder"
},
"product_image_url": {
"type": "string",
"description": "Product image, required for product_holder"
},
"output_type": {
"type": "string",
"enum": [
"image",
"video"
],
"description": "product_holder output: image costs 100 credits, video costs 500"
},
"person_prompt": {
"type": "string",
"description": "Person description for product_holder"
},
"wait_for_result": {
"type": "boolean",
"description": "Wait up to 55 seconds for the result before returning. Defaults to false: the tool returns a prediction_id immediately and you poll get_prediction, which is the reliable pattern for photos and videos."
}
},
"required": [
"type"
],
"additionalProperties": false
}🟢get_prediction(prediction_id)
Check an operation started by generate_photo, edit_image, or create_video. Returns the state and, once finished, the result URL. Requires a connected Photo AI Studio account. Calling this tool starts the sign-in flow.
输入模式
{
"type": "object",
"properties": {
"prediction_id": {
"type": "string",
"description": "The prediction_id returned when the operation started"
}
},
"required": [
"prediction_id"
],
"additionalProperties": false
}🟢list_predictions(page, limit, state)
List past generations, edits, and videos, with paging and an optional state filter. Requires a connected Photo AI Studio account. Calling this tool starts the sign-in flow.
输入模式
{
"type": "object",
"properties": {
"page": {
"type": "number",
"description": "Page number, default 1"
},
"limit": {
"type": "number",
"description": "Items per page, default 20, maximum 100"
},
"state": {
"type": "string",
"enum": [
"pending",
"succeeded",
"failed"
],
"description": "Filter by state"
}
},
"additionalProperties": false
}社区
证据