Design
Apply custom convolution kernel by defining your own matrix values for personalized image effects and processing
Call this tool from your code in three languages.
# 1) Upload each file first → returns { filePath }
curl -X POST 'https://api.elysiatools.com/upload/image-custom-kernel' \
-F 'file=@/path/to/imageFile.ext'
# 2) Call the tool with the returned filePath values
curl -X POST 'https://api.elysiatools.com/en/api/tools/image-custom-kernel' \
-F 'imageFile=/path/to/file.ext' \
-F 'kernelSize=3' \
-F 'kernelValues=Enter comma-separated values (e.g., 1, 2, 1, 2, 4, 2, 1, 2, 1 for 3x3)' \
-F 'intensity=1' \
-F 'normalize=true' \
-F 'outputMode=normal'Send a POST request with your inputs as JSON. File parameters require a separate upload first.
POST https://api.elysiatools.com/en/api/tools/image-custom-kernel| Name | Type | Required | Description |
|---|---|---|---|
| imageFile | fileupload required | Yes | Image to apply custom convolution kernel |
| kernelSize | select | No | Size of the convolution matrix |
| kernelValues | textarea | Yes | Matrix values (left to right, top to bottom). For 3x3: 9 values, for 5x5: 25 values, etc. |
| intensity | number | No | Strength of the convolution effect (0.1-10.0) |
| normalize | checkbox |
| No |
| Normalize kernel so that sum of all elements equals 1 (except for edge detection) |
| outputMode | select | No | Additional processing on the output |
File result
{
"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)"
}Add this tool to your Model Context Protocol server so AI agents can list and call it.
Add this block to your MCP client configuration:
{
"mcpServers": {
"elysiatools-image-custom-kernel": {
"name": "image-custom-kernel",
"description": "Apply custom convolution kernel by defining your own matrix values for personalized image effects and processing",
"baseUrl": "https://api.elysiatools.com/mcp/sse?toolId=image-custom-kernel",
"command": "",
"args": [],
"env": {},
"isActive": true,
"type": "sse"
}
}
}After connecting to the SSE endpoint, list the exposed tools:
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/list"
}Invoke the tool by its id, passing arguments built from its parameters:
{
"jsonrpc": "2.0",
"id": 2,
"method": "tools/call",
"params": {
"name": "image-custom-kernel",
"arguments": {
"imageFile": "https://example.com/file.ext",
"kernelSize": "3",
"kernelValues": "Enter comma-separated values (e.g., 1, 2, 1, 2, 4, 2, 1, 2, 1 for 3x3)",
"intensity": 1,
"normalize": true,
"outputMode": "normal"
}
}
}Questions or issues? Contact [email protected]