Skip to main content
Glama

Server Details

Compress, convert, resize, crop, upscale, OCR and remove backgrounds from images.

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A3.9/5.0

Scored across 18 tools

Disambiguation4/5

Most tools map to a distinct resource+action (compress, convert, inspect, upscale, remove_background, OCR, render, screenshot), and the website-scan family is cleanly layered as scans → pages → assets. The main soft spots are get_website_scan vs get_website_report (both describe a scan's state/result) and compress_image/convert_image overlapping with run_pipeline's compress/convert ops, though the descriptions do clarify the boundaries.

Naming Consistency4/5

The set is consistently snake_case and overwhelmingly verb-first (compress_image, convert_image, inspect_image, list_website_assets, get_website_scan, optimize_website, run_pipeline). Only html_to_image and screenshot_url break the verb_noun pattern, a minor deviation that stays readable.

Tool Count4/5

18 tools sits at the upper edge of comfortable, but they split into coherent clusters (7 image operations, 6 website-scan tools, 2 rendering, 1 pipeline, 1 account) with no obvious filler. A couple of scan-accessor tools could arguably be merged, but nothing feels gratuitous.

Completeness4/5

Core image lifecycle is well covered: read facts, compress, convert, upscale, cut out background, OCR, render, and batch via run_pipeline, plus full website-scan discovery, mapping, and application guidance. The gap is that common transforms (resize, crop, rotate, watermark) exist only inside run_pipeline, which is Pro-gated, and there is no tool to delete or manage stored scans.

Available Tools

18 tools
compress_imageCompress an imageAInspect

Make an image file smaller. Keeps the format unless format is given. Set target_bytes to hit an exact file size (e.g. 100000 for 100 KB). Otherwise mode decides: smart (default) finds the smallest file that still looks like the original, quality uses quality (1-100), lossless keeps every pixel (PNG, WebP, AVIF, TIFF only), keep does not compress: the image comes back as it was with only its metadata removed. Reads JPEG, PNG, WebP, AVIF, GIF, TIFF and SVG. Returns a download URL valid for one hour.

Inputs: mode, format, rotate, quality, +6 more.

convert_imageConvert an image to another formatBInspect

Convert an image to JPEG, PNG, WebP, AVIF, GIF or TIFF. Use webp or avif to modernise images for the web. Returns a download URL valid for one hour.

Inputs: format (required), quality, image_url, max_width, +2 more.

extract_textRead the text in an image (OCR)A
Read-onlyIdempotent
Inspect

Read printed text from a scan, a screenshot or a photo of a page. Languages: eng (English) and slv (Slovenian). Returns the text and the engine's confidence; below about 60 the text needs checking.

Inputs: image_url, languages, image_base64.

get_agent_promptInstructions for applying a scan's replacements to a codebaseA
Read-onlyIdempotent
Inspect

The step-by-step instructions for applying this scan's package: inspect the project, match each map entry to real files, change one reference at a time, validate, report what is unresolved. Never a blind search-and-replace. Still answered after the scan's files have been deleted. Reads only.

Inputs: scan_id (required), agent.

get_replacement_mappingThe replacement map of a website scanA
Read-onlyIdempotent
Inspect

What replaces what: one entry per original asset with original_url, original_path, replacement_path, package_file, sizes, replacement_status (ready, proposed, keep_original, rejected) and the pages that use it. Paged. Act only on entries that are ready; the files themselves are in the scan's ZIP (get_website_scan gives the address). To change a project's files, use the local server's tools (load_replacement_package, preview_replacements, apply_replacements), which ask the person first. Reads only.

Inputs: scan_id (required), limit, offset.

get_usageAPI usage this monthA
Read-onlyIdempotent
Inspect

How many requests this account has used this month, and its limits.

Inputs: no named parameters.

get_website_reportGet a website scan's resultA
Read-onlyIdempotent
Inspect

The result of an optimize_website call that was still working when it returned. Pass its job_id. Waits up to a minute for the scan to finish.

Inputs: job_id (required).

get_website_scanA website scan's status, totals and downloadsA
Read-onlyIdempotent
Inspect

Where a scan stands, what it found and saved, and the download addresses of its ZIP, replacement maps and reports. In totals.bytes, estimated_savings is a prediction; optimized_from and optimized_to are measured. Reads only.

Inputs: scan_id (required).

html_to_imageDraw HTML as an imageAInspect

Draw a page of HTML and CSS as a PNG, JPEG or WebP picture: social cards, badges, receipts, mockups, diagrams in SVG. The page is drawn by Chromium with no script and no network access, so inline CSS, SVG and data: pictures and fonts work and anything fetched from an address does not. width and height are the page's size in CSS pixels; scale 2 makes a sharper picture; full_page draws a long page to its end. Returns a download URL valid for one hour.

Inputs: html (required), scale, width, format, +4 more.

inspect_imageInspect an imageA
Read-onlyIdempotent
Inspect

Facts about an image without changing it: format, dimensions, file size, colour space, transparency, which hidden metadata it carries (EXIF, GPS position, colour profile), camera details, and fingerprints for finding duplicates.

Inputs: image_url, image_base64.

list_website_assetsThe assets of a website scanA
Read-onlyIdempotent
Inspect

Asset inventory of a scan: images, style sheets, scripts and fonts with their sizes, findings and state. estimated_bytes is a prediction, optimized_bytes is measured. Scripts and fonts are analysed only. Paged; filter by kind, status, finding or page. Reads only.

Inputs: scan_id (required), kind, page, limit, +4 more.

list_website_pagesThe pages of a website scanB
Read-onlyIdempotent
Inspect

Page inventory of a scan: address, status, images, sizes, estimated and measured savings. Paged; filter by status or search. Reads only.

Inputs: scan_id (required), limit, offset, search, +1 more.

list_website_scansList the account's website scansA
Read-onlyIdempotent
Inspect

The website projects of this account with their scans, newest first: id, site, status, pages analysed, bytes saved. Reads only.

Inputs: no named parameters.

optimize_websiteOptimize the images on a websiteAInspect

Start at one public web page, follow its links to the other pages on the same host, find every image they reference (img, srcset, picture, lazy-load attributes, inline CSS backgrounds, social images, icons), convert them to WebP and return a report: the pages scanned, each image's size before and after and the pages that use it, a download URL per image, zip_url for everything, and replacements mapping each original URL to its new file. To apply it to a codebase: download and unpack the ZIP, put the files from images/ next to the originals, then change each reference per replacements (or wrap it in a element with the WebP as and the original as the fallback). The free plan scans up to 5 pages and 100 images per call, Pro up to 50 pages and 500 images. A large site can take minutes: if the result is not ready the call returns a job_id to pass to get_website_report.

Inputs: url (required), quality, max_pages.

remove_backgroundRemove an image's backgroundAInspect

Cut the subject out of a photo. The background becomes transparent (PNG or WebP), a solid colour if background is a hex colour like #ffffff, or the original scene blurred if it is blur. Set refine for hair, fur and other fine edges, or graphic for a logo or text on a surface. Returns a download URL valid for one hour.

Inputs: format, refine, shadow, graphic, +3 more.

run_pipelineRun several steps on one imageAInspect

Run a multi-step workflow on an image in one call, for example remove the background, resize, convert and compress. Needs a Pro plan. Give "pipeline": { "steps": [{ "op", "params", "when"? }] } with ops remove_background, upscale, resize, crop, rotate, edit, watermark, convert, compress (params are the REST API's options, e.g. { "width": 1600 } or { "format": "webp", "mode": "smart" }; "when" makes a step conditional on format, min_width, max_width, min_bytes, max_bytes or has_alpha), or "preset": the name of a saved pipeline or a template (web-optimized, thumbnail, product-square, social-square, avatar, private-share). Set dry_run to see which steps would run and the resulting size without processing anything. Returns a download URL valid for one hour and a report of every step.

Inputs: name, preset, dry_run, version, +3 more.

screenshot_urlScreenshot of a web pageAInspect

Take a picture of the web page at a public http(s) address: PNG, JPEG or WebP, the first screen or the whole page. The page is drawn by Chromium without running its own script (what the server sends is what is drawn), and only public addresses can be reached. scale 2 makes a sharper picture. Returns a download URL valid for one hour.

Inputs: url (required), scale, width, format, +3 more.

upscale_imageUpscale an image 2x or 4xAInspect

Double an image's width and height with a super-resolution model, which reconstructs edges and texture instead of blurring. Takes images of up to about one megapixel (2.25 on Pro). scale 4 (Pro, up to one megapixel, slower) runs the model twice. Returns a download URL valid for one hour.

Inputs: scale, format, image_url, image_base64.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources