Image Processing

ai.pictomancer/image-processing

Gives Claude image processing capabilities through the Pictomancer API. You get resize, format conversion, compression, and the ability to chain operations into pipelines. Reach for this when you need an AI agent to normalize image sizes for uploads, convert between formats like PNG to WebP, compress files before storage, or run batch transformations. It's exposed over streamable HTTP, so you're making API calls to Pictomancer's service rather than running local binaries. Useful for automation workflows where images need consistent processing without manual intervention or building your own transformation logic.

tools: 11
transport: HTTP
last updated: Aug 17, 2026

Open website

Install

From registry metadata

$ npx add-mcp https://api.pictomancer.ai/mcp --name image-processing

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http image-processing https://api.pictomancer.ai/mcp

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 11 tools

Verified live against the running server on Nov 6, 2026.

get_format_infoGet supported formats and options Returns supported output formats and their configurable options. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json

Get supported formats and options Returns supported output formats and their configurable options. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json

No parameters. Call it with no arguments.

estimate_costEstimate the price of an operation Returns the exact USD price this API would charge for an operation on an input of the given size, without fetching or processing anything. Free. Use it before paying: send X-Max-Cost-USD on the real request to have the API refuse (412) instea...5 params

Estimate the price of an operation Returns the exact USD price this API would charge for an operation on an input of the given size, without fetching or processing anything. Free. Use it before paying: send X-Max-Cost-USD on the real request to have the API refuse (412) instea...

Parameters* required

formatstring

Requested output format; only avif changes the price.

input_bytes*integer

Size of the input image in bytes. Get it from analyze_image (free) if you do not know it.

operation*string

Operation to price. One of resize, compress, convert, crop, optimize_for_vision, optimize_generated, remove_background, pipeline. analyze is always free.

operationsarray

For pipeline only: the ordered operations, each {type, format?}. Volume discount applies at 3+ operations.

quality_targetboolean

Whether the request will use quality_target (SSIM search surcharge).default: false

analyze_imageAnalyze an image Fetch an image from a URL or base64 and return its metadata: size in bytes, pixel dimensions, source format, and what it costs every supported vision model in tokens. Always free. Dimensions are omitted if the image header cannot be read. Also reports whether...1 params

Analyze an image Fetch an image from a URL or base64 and return its metadata: size in bytes, pixel dimensions, source format, and what it costs every supported vision model in tokens. Always free. Dimensions are omitted if the image header cannot be read. Also reports whether...

Parameters* required

source*string

Image source: a public URL (https://...) or a base64-encoded string (optionally as a data URI like data:image/png;base64,...).

resize_imageResize an image Scale an image by a factor, or fill an exact box. Use 'scale' for uniform scaling, or 'scale_x'/'scale_y' for independent axes (float factors, e.g. 0.5 = half size). Alternatively set 'width'+'height' for fill mode: resize and smart-crop to those exact dimensio...13 params

Resize an image Scale an image by a factor, or fill an exact box. Use 'scale' for uniform scaling, or 'scale_x'/'scale_y' for independent axes (float factors, e.g. 0.5 = half size). Alternatively set 'width'+'height' for fill mode: resize and smart-crop to those exact dimensio...

Parameters* required

autorotboolean

Apply EXIF orientation before resizing. Opt-in; default false, which preserves current byte-for-byte behavior.

deliverystring

denoiseinteger

Median denoise before resizing: radius 1-3 (window 3x3 to 7x7). Opt-in; no surcharge.

equalizeboolean

Auto-contrast (histogram equalisation of the value channel; hue and saturation preserved) before resizing. Opt-in.

formatstring

Output format: jpeg, png, webp, tiff, gif, or avif. If omitted, the original format is preserved.

gravitystring

Fill-mode smart-crop strategy: one of ('attention', 'entropy', 'centre'). Only valid together with width and height; defaults to attention.

heightinteger

Target height in pixels for fill mode. Requires width.

scalenumber

Uniform scale factor applied to both axes (e.g. 0.5 = half size). Use this for simple scaling; use scale_x/scale_y for independent axes.

scale_xnumber

Horizontal scale factor (e.g. 0.5 = half width). If only scale_x is given, scale_y defaults to the same value.

scale_ynumber

Vertical scale factor (e.g. 0.75 = 75% height). Optional; defaults to scale_x if omitted.

sharpenboolean

Unsharp-mask sharpen after resizing (libvips defaults). Opt-in.

source*string

Image source: a public URL (https://...) or a base64-encoded string (optionally as a data URI like data:image/png;base64,...).

widthinteger

Target width in pixels for fill mode: resize and smart-crop to these exact dimensions in one call. Requires height. Mutually exclusive with scale/scale_x/scale_y. Upscaling is allowed.

compress_imageCompress an image Re-encode an image with quality/format options to reduce file size. Supports jpeg, png, webp, tiff, gif. Instead of a q number you can set quality_target (0-1]: the smallest file with SSIM at or above the target, searched on the worker (jpeg, webp, avif; flat...10 params

Compress an image Re-encode an image with quality/format options to reduce file size. Supports jpeg, png, webp, tiff, gif. Instead of a q number you can set quality_target (0-1]: the smallest file with SSIM at or above the target, searched on the worker (jpeg, webp, avif; flat...

Parameters* required

autorotboolean

Apply EXIF orientation before compressing. Opt-in; default false, which preserves current byte-for-byte behavior.

deliverystring

denoiseinteger

Median denoise before compressing: radius 1-3 (window 3x3 to 7x7). Opt-in; no surcharge.

equalizeboolean

Auto-contrast (histogram equalisation of the value channel; hue and saturation preserved) before compressing. Opt-in.

formatstring

Output format: jpeg, png, webp, tiff, gif, or avif. If omitted, the original format is preserved.

qinteger

Quality (1-100). Lower = smaller file. Typical values: 60-80 for web, 85-95 for print. Maps to libvips Q parameter.

quality_targetnumber

Target SSIM (0-1]: the worker searches for the smallest file that still scores at least this. Alternative to q; mutually exclusive with it. Requires an explicit format among jpeg, webp, avif. Carri...

sharpenboolean

Unsharp-mask sharpen after compressing (libvips defaults). Opt-in.

source*string

Image source: a public URL (https://...) or a base64-encoded string (optionally as a data URI like data:image/png;base64,...).

stripboolean

Strip metadata (EXIF, ICC profile, etc.) from the output. Reduces file size slightly.

convert_imageConvert image format Convert an image to a different format (jpeg, png, webp, tiff, gif, avif). Optionally set quality, strip metadata, enable lossless mode (webp, avif), or tune encoder effort (avif). Instead of a q number you can set quality_target (0-1]: the smallest file w...12 params

Convert image format Convert an image to a different format (jpeg, png, webp, tiff, gif, avif). Optionally set quality, strip metadata, enable lossless mode (webp, avif), or tune encoder effort (avif). Instead of a q number you can set quality_target (0-1]: the smallest file w...

Parameters* required

autorotboolean

Apply EXIF orientation before converting. Opt-in; default false, which preserves current byte-for-byte behavior.

deliverystring

denoiseinteger

Median denoise before converting: radius 1-3 (window 3x3 to 7x7). Opt-in; no surcharge.

effortinteger

AV1 encoder CPU effort (0-9). Higher = smaller file, slower. Only applies to avif.

equalizeboolean

Auto-contrast (histogram equalisation of the value channel; hue and saturation preserved) before converting. Opt-in.

format*string

Target format: jpeg, png, webp, tiff, gif, or avif.

losslessboolean

Enable lossless encoding. Only applies to webp and avif.

qinteger

Quality (1-100). Maps to libvips Q parameter.

quality_targetnumber

Target SSIM (0-1]: the worker searches for the smallest file that still scores at least this. Alternative to q; mutually exclusive with it and with lossless. Only for jpeg, webp, avif. Carries a fl...

sharpenboolean

Unsharp-mask sharpen after converting (libvips defaults). Opt-in.

source*string

Image source: a public URL (https://...) or a base64-encoded string (optionally as a data URI like data:image/png;base64,...).

stripboolean

Strip metadata (EXIF, ICC profile, etc.) from the output.

crop_imageCrop an image Extract a rectangular region from an image, in one of three mutually exclusive modes. Manual: give the top-left corner (x, y) and dimensions (width, height) in pixels. Smart crop: give 'gravity' (attention, entropy, centre) plus width and height; the window is pi...14 params

Crop an image Extract a rectangular region from an image, in one of three mutually exclusive modes. Manual: give the top-left corner (x, y) and dimensions (width, height) in pixels. Smart crop: give 'gravity' (attention, entropy, centre) plus width and height; the window is pi...

Parameters* required

autorotboolean

Apply EXIF orientation before cropping. Opt-in; default false, which preserves current byte-for-byte behavior.

deliverystring

denoiseinteger

Median denoise before cropping: radius 1-3 (window 3x3 to 7x7). Opt-in; no surcharge.

equalizeboolean

Auto-contrast (histogram equalisation of the value channel; hue and saturation preserved) before cropping. Opt-in.

formatstring

Output format: jpeg, png, webp, tiff, gif, or avif. If omitted, the original format is preserved.

gravitystring

Smart-crop mode: picks the window automatically. One of ('attention', 'entropy', 'centre'). Requires width and height; mutually exclusive with x/y and trim. A target larger than the source clamps t...

heightinteger

Height of the crop rectangle in pixels. Required in manual and gravity modes.

sharpenboolean

Unsharp-mask sharpen after cropping (libvips defaults). Opt-in.

source*string

Image source: a public URL (https://...) or a base64-encoded string (optionally as a data URI like data:image/png;base64,...).

thresholdnumber

Trim sensitivity (must be positive; default 10.0). Only valid together with trim: true.

trimboolean

Trim mode: removes a uniform background border via content detection. Mutually exclusive with x/y/width/height/gravity.

widthinteger

Width of the crop rectangle in pixels. Required in manual and gravity modes.

xinteger

Left edge of the crop rectangle in pixels. Manual mode only.

yinteger

Top edge of the crop rectangle in pixels. Manual mode only.

optimize_for_visionResize an image for a vision model Resize an image to the largest size a given vision model still benefits from, and report what it costs that model in tokens before and after. Every provider downscales oversized input before counting tokens, so this alone saves bytes and uplo...6 params

Resize an image for a vision model Resize an image to the largest size a given vision model still benefits from, and report what it costs that model in tokens before and after. Every provider downscales oversized input before counting tokens, so this alone saves bytes and uplo...

Parameters* required

deliverystring

formatstring

Output format: jpeg, png, webp, tiff, gif, or avif. If omitted, the original format is preserved.

max_tokensinteger

Optional cap on what the image may cost the target model. Without it the image is resized to the model's own ceiling, which saves bytes and upload latency but no tokens, because every provider alre...

qinteger

Quality (1-100). Maps to libvips Q parameter.

source*string

Image source: a public URL (https://...) or a base64-encoded string (optionally as a data URI like data:image/png;base64,...).

target_model*string

Vision model the image is being prepared for, e.g. claude-opus-5, gpt-4o, gemini-2.5-pro. Unknown ids are rejected rather than guessed: the wrong limits would silently resize to the wrong size.

optimize_generated_imageOptimize an AI-generated image for the web The step after image generation. gpt-image, DALL-E, Flux, Midjourney and Stable Diffusion hand back 2-8 MB PNGs; this returns the same picture as a web-ready webp (default), avif, jpeg or png, metadata stripped, transparency kept on w...7 params

Optimize an AI-generated image for the web The step after image generation. gpt-image, DALL-E, Flux, Midjourney and Stable Diffusion hand back 2-8 MB PNGs; this returns the same picture as a web-ready webp (default), avif, jpeg or png, metadata stripped, transparency kept on w...

Parameters* required

deliverystring

formatstring

Output format: webp (default), avif, jpeg or png. webp, avif and png keep transparency; jpeg flattens it.default: webp

max_dimensioninteger

Cap on the longest side in pixels. Larger images are scaled down to fit, aspect ratio preserved; smaller images are never upscaled.

qinteger

Quality (1-100). Maps to libvips Q parameter. Omit to use the encoder default; or set quality_target instead.

quality_targetnumber

Target SSIM (0-1]: the worker searches for the smallest file that still scores at least this. Alternative to q; mutually exclusive with it. Carries a flat surcharge for the extra encodes.

source*string

Image source: a public URL (https://...) or a base64-encoded string (optionally as a data URI like data:image/png;base64,...).

stripboolean

Strip metadata. Defaults to true: generated images carry no EXIF worth keeping. Metadata includes any C2PA manifest, which would be invalid after re-encoding anyway.default: true

remove_image_backgroundRemove the background from an image Cut the subject (person, product, animal, object) out of a photo and return it on a transparent background as png (default), webp or avif. Optional q (1-100) for webp/avif. Runs a segmentation model (U2Net) on CPU: expect a few seconds per i...4 params

Remove the background from an image Cut the subject (person, product, animal, object) out of a photo and return it on a transparent background as png (default), webp or avif. Optional q (1-100) for webp/avif. Runs a segmentation model (U2Net) on CPU: expect a few seconds per i...

Parameters* required

deliverystring

formatstring

Output format: png (default), webp or avif. All three keep the transparency; jpeg is not offered because it has none.default: png

qinteger

Quality (1-100) for webp and avif. Ignored for png, which is lossless. Omit to use the encoder default.

source*string

Image source: a public URL (https://...) or a base64-encoded string (optionally as a data URI like data:image/png;base64,...).

image_pipelineRun a multi-step image pipeline Chain multiple operations (resize, compress, convert, crop) in sequence. The image is fetched once, then each operation is applied to the output of the previous one. Max 10 operations per pipeline. ### Responses: **200**: Processed image binary...3 params

Run a multi-step image pipeline Chain multiple operations (resize, compress, convert, crop) in sequence. The image is fetched once, then each operation is applied to the output of the previous one. Max 10 operations per pipeline. ### Responses: **200**: Processed image binary...

Parameters* required

deliverystring

operations*array

Ordered list of operations to apply sequentially. Each operation receives the output of the previous one. Max 10.

source*string

Image source: a public URL (https://...) or a base64-encoded string (optionally as a data URI like data:image/png;base64,...).

Details

Transport: HTTP
Registry: MCP registry, active
Tools verified: Nov 6, 2026