Media
Cubre parcialmente marcas de agua de texto de bajo contraste en posiciones perimetrales conocidas mediante parches Canvas locales.
Llama a esta herramienta desde tu código en tres lenguajes.
# 1) Request a presigned URL → returns { uploadUrl, storageKey }
curl -X POST 'http://127.0.0.1:3003/api/upload/presign/adaptive-12-point-watermark-cover-restorer' \
-H 'Content-Type: application/json' \
-d '{"filename":"imageFile.ext","contentType":"application/octet-stream","size":12345}'
curl -X POST 'http://127.0.0.1:3003/api/upload/presign/adaptive-12-point-watermark-cover-restorer' \
-H 'Content-Type: application/json' \
-d '{"filename":"zipFile.ext","contentType":"application/octet-stream","size":12345}'
# 2) PUT the file bytes directly to the presigned uploadUrl
curl -X PUT '<presigned uploadUrl>' \
--data-binary @/path/to/file.ext
# 3) Call the tool, passing the returned storageKey for each file field
curl -X POST 'http://127.0.0.1:3003/es/api/tools/adaptive-12-point-watermark-cover-restorer' \
-F 'imageFile=uploads/2026/01/01/your-tool-1700000000000-abc123.ext' \
-F 'zipFile=uploads/2026/01/01/your-tool-1700000000000-abc123.ext' \
-F 'originalWatermarkText=Buyer: cover-smoke
example.test/creator' \
-F 'placementMode=all' \
-F 'randomCount=4' \
-F 'randomSeed=' \
-F 'selectedPositions=' \
-F 'fontSizePercent=1.6' \
-F 'insetPercent=1.2' \
-F 'coverPaddingPercent=0.25'Envía una petición POST con tus entradas en JSON. Los parámetros de tipo archivo requieren una subida previa.
POST http://127.0.0.1:3003/es/api/tools/adaptive-12-point-watermark-cover-restorer| Nombre | Tipo | Obligatorio | Descripción |
|---|---|---|---|
| imageFile | filesubida requerida | No | — |
| zipFile | filesubida requerida | No | — |
| originalWatermarkText | textarea | Sí | — |
| placementMode | select | Sí | — |
| randomCount | number | Sí | — |
| randomSeed | text | No | — |
| selectedPositions | select | No | — |
| fontSizePercent | number | Sí | — |
| insetPercent | number | Sí | — |
| coverPaddingPercent | number | Sí | — |
Resultado de archivo
{
"filePath": "/public/processing/randomid.ext",
"fileName": "output.ext",
"contentType": "application/octet-stream",
"size": 1024,
"metadata": {
"key": "value"
},
"error": "Error message (optional)",
"message": "Notification message (optional)"
}Añade esta herramienta a tu servidor Model Context Protocol para que los agentes de IA puedan listarla y llamarla.
Añade este bloque a la configuración de tu cliente MCP:
{
"mcpServers": {
"elysiatools-adaptive-12-point-watermark-cover-restorer": {
"name": "adaptive-12-point-watermark-cover-restorer",
"description": "Cubre parcialmente marcas de agua de texto de bajo contraste en posiciones perimetrales conocidas mediante parches Canvas locales.",
"baseUrl": "http://127.0.0.1:3003/mcp/sse?toolId=adaptive-12-point-watermark-cover-restorer",
"command": "",
"args": [],
"env": {},
"isActive": true,
"type": "sse"
}
}
}Tras conectar al endpoint SSE, lista las herramientas expuestas:
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/list"
}Invoca la herramienta por su id; los argumentos se construyen a partir de sus parámetros:
{
"jsonrpc": "2.0",
"id": 2,
"method": "tools/call",
"params": {
"name": "adaptive-12-point-watermark-cover-restorer",
"arguments": {
"imageFile": "https://example.com/file.ext",
"zipFile": "https://example.com/file.ext",
"originalWatermarkText": "Buyer: cover-smoke\nexample.test/creator",
"placementMode": "all",
"randomCount": 4,
"randomSeed": "",
"selectedPositions": [],
"fontSizePercent": 1.6,
"insetPercent": 1.2,
"coverPaddingPercent": 0.25
}
}
}¿Dudas o problemas? Contacta con [email protected]