Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Image Analyzer MCP Server analyze the image at ~/Downloads/photo.jpg"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP (Model Context Protocol) server that provides image analysis tools using Pillow (PIL) — no external APIs required. All processing is done locally.
analyze_image — Get dimensions, format, color mode, file size, aspect ratio, and DPI from an image file
analyze_image_base64 — Same analysis from a base64-encoded image string
get_dominant_colors — Extract dominant colors as hex values with RGB components and approximate coverage percentages
get_image_metadata — Read EXIF data including GPS coordinates, camera make/model, date taken, orientation, and more
convert_image — Convert between PNG, JPEG, WEBP, and GIF formats, returned as base64
Related MCP server: img-convert MCP Server
Python 3.10+
mcp>=1.0.0
Pillow>=10.0.0
cd image-analyzer-mcp
pip install -r requirements.txtpython server.pyThis starts the server over stdio, suitable for integration with MCP clients (e.g., Claude Desktop, Cursor, etc.).
python server.py --transport sse --host 0.0.0.0 --port 8080Requires uvicorn (pip install uvicorn).
Add to your MCP client config:
{
"mcpServers": {
"image-analyzer": {
"command": "python",
"args": ["/path/to/image-analyzer-mcp/server.py"],
"transport": "stdio"
}
}
}analyze_imageAnalyze an image file.
Parameter | Type | Required | Description |
| string | yes | Path to image file |
Returns: dimensions, format, mode, file size, aspect ratio, DPI.
analyze_image_base64Analyze an image from base64-encoded data.
Parameter | Type | Required | Description |
| string | yes | Base64-encoded image data |
Returns: Same as analyze_image, but without the file path.
get_dominant_colorsExtract dominant colors from an image.
Parameter | Type | Required | Default | Description |
| string | yes | — | Path to image file |
| integer | no | 5 | Number of dominant colors (max 128) |
Returns: List of dominant colors with hex values, RGB components, and approximate percentage coverage.
get_image_metadataExtract EXIF metadata from an image.
Parameter | Type | Required | Description |
| string | yes | Path to image file |
Returns: EXIF data including GPS coordinates, camera info, date taken, orientation, etc.
convert_imageConvert an image to a different format.
Parameter | Type | Required | Default | Description |
| string | yes | — | Path to image file |
| string | yes | — | PNG, JPEG, WEBP, or GIF |
| integer | no | 85 | Output quality (1-100, JPEG/WEBP only) |
Returns: Base64-encoded converted image data.
MIT
This server cannot be deployed
Image and PDF toolkit: convert to AVIF/WebP/JXL, resize, crop, remove backgrounds, optimize PDFs.
Image toolkit: resize, compress, crop, watermark, convert, rotate, EXIF read/strip.
Generate image thumbnails, resize, convert and compress photos from your AI chat. Local files.
Image & PDF tools for AI agents: compress, convert, resize, PDF, AI vision, pipeline.