Design

Median Pass Filter

Apply median pass filter to remove noise while preserving edges with multiple algorithms

file· File resultOpen tool

Quick start

Call this tool from your code in three languages.

cURL

# 1) Upload each file first → returns { filePath }
curl -X POST 'https://api.elysiatools.com/upload/image-median-pass' \
  -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-median-pass' \
  -F 'imageFile=/path/to/file.ext' \
  -F 'algorithm=standard' \
  -F 'kernelSize=3' \
  -F 'iterations=1' \
  -F 'threshold=30' \
  -F 'preserveEdges=true' \
  -F 'channels=all' \
  -F 'format=original' \
  -F 'quality=95'

API reference

Send a POST request with your inputs as JSON. File parameters require a separate upload first.

Endpoint

HTTP

POST https://api.elysiatools.com/en/api/tools/image-median-pass

Parameters

Name	Type	Required	Description
imageFile	fileupload required	Yes	Upload any image file (JPEG, PNG, WebP, GIF, BMP, TIFF) to remove noise while preserving edges
algorithm	select	No	Choose median filter algorithm. Standard works well for most noise types
kernelSize	range	No	Size of the median filter kernel (must be odd). Larger kernels remove more noise but may blur details
iterations	number	No	Number of median filter passes. More iterations = stronger noise reduction

MCP integration

Add this tool to your Model Context Protocol server so AI agents can list and call it.

Server configuration

Add this block to your MCP client configuration:

mcp.json

{
  "mcpServers": {
    "elysiatools-image-median-pass": {
      "name": "image-median-pass",
      "description": "Apply median pass filter to remove noise while preserving edges with multiple algorithms",
      "baseUrl": "https://api.elysiatools.com/mcp/sse?toolId=image-median-pass",
      "command": "",
      "args": [],
      "env": {},
      "isActive": true,
      "type": "sse"
    }
  }
}

List available tools

After connecting to the SSE endpoint, list the exposed tools:

tools/list

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/list"
}

Call this tool

Invoke the tool by its id, passing arguments built from its parameters:

tools/call

{
  "jsonrpc": "2.0",
  "id": 2,
  "method": "tools/call",
  "params": {
    "name": "image-median-pass",
    "arguments": {
  "imageFile": "https://example.com/file.ext",
  "algorithm": "standard",
  "kernelSize": 3,
  "iterations": 1,
  "threshold": 30,
  "preserveEdges": true,
  "channels": "all",
  "format": "original",
  "quality": 95
}
  }
}

Chain multiple tools in one session with a comma-separated toolId list, e.g. /mcp/sse?toolId=png-to-webp,jpg-to-webp,gif-to-webp (max 20).