reprise
Un-flatten any flat AI design into editable layers, reproduce it bit-perfect, from your agent.
我該用這個嗎
品質與安全性
發現項目（2）
- LOWTool 'reproduce' description lacks action verb在 reproduce 中
- LOWTool 'diagnose' description lacks action verb在 diagnose 中
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"reprise": {
"url": "https://tepesama-reprise-mcp.hf.space/gradio_api/mcp/http"
}
}
}遠端端點
https://tepesama-reprise-mcp.hf.space/gradio_api/mcp/httpstreamable-http它能做什麼
工具清單
工具（3）
⚪reproduce(image)
Un-flatten a flat design image into editable layers and reproduce it bit-perfect, returning the fidelity score. Returns: A JSON string with a bit_perfect flag and fidelity metrics (mae, psnr, exact-match %, stray px).
輸入結構描述
{
"type": "object",
"properties": {
"image": {
"type": "string",
"description": "The source design image as an http(s) URL or a base64 data URL."
}
}
}⚪autodetect(image)
Auto-detect the elements (subjects and text) in a design image as relative bounding boxes. Returns: A JSON string with the detected elements (relative bboxes) and their count.
輸入結構描述
{
"type": "object",
"properties": {
"image": {
"type": "string",
"description": "The design image as an http(s) URL or a base64 data URL."
}
}
}⚪diagnose(original, reproduction)
Score how faithfully a reproduction matches an original (MAE / PSNR / exact-match % / stray px). Returns: A JSON string with the fidelity metrics.
輸入結構描述
{
"type": "object",
"properties": {
"original": {
"type": "string",
"description": "The original image as an http(s) URL or a base64 data URL."
},
"reproduction": {
"type": "string",
"description": "The reproduced image to compare, as an http(s) URL or a base64 data URL."
}
}
}社群
證據