Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Product Aura

REMOTE · PRODUCTAURA.CO · 3 COMPONENTS

Listing and ad images for Amazon, Etsy, Shopify, TikTok Shop and social ads, from one product photo.

+4 this week 73 Trust /100

Last scanned (22 hours ago)

Scores higher than 59% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Design and Media

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability76
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 6484 tokens (~162/item across 40 items; 39 tools + 1 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management47
  • Stability observed for 14 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage89
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 66% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 41 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
  • Supports UI / widget rendering.Pass
What we tested

Checks we ran (14)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol
  • Capabilities

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Nov 26 +1
    • Tool “create_product” rewrote its description, which is the text the model reads security
    • The server now declares the “resources” capability functional
    • First check of Capabilities: pass functional
    • New resource “image_set_gallery” functional
    • “create_product” added an optional parameter “kind” cosmetic
    • “create_product” reworded the description of “product_url” cosmetic
    • Tool “create_product” changed its title: Create a product from photos or a product page → Create a product (or a business) from photos, a product page or a website cosmetic
  • 20 Nov 26 0
    • “plan_image_set” added an optional parameter “sizes” cosmetic
    • “plan_image_set” reworded the description of “style” cosmetic

    2 cosmetic changes on this day. Switch on “Show cosmetic changes” to see them.

  • 19 Nov 26 +1
    • The server rewrote its instructions, which are the text every model session reads security
    • New tool “cancel_batch”, which the server declares destructive security
    • Schema quality: 5285 → 6247 ▼ functional
    • New tool “start_batch” functional
    • New tool “create_batch” functional
    • New tool “get_batch” functional
    • New tool “retry_batch” functional
  • 18 Nov 26 0
    • “plan_image_set” added an optional parameter “style” cosmetic
    • “plan_image_set” reworded the description of “pack” cosmetic
    • “redo_image” reworded the description of “note” cosmetic

    3 cosmetic changes on this day. Switch on “Show cosmetic changes” to see them.

  • 17 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

  • 10 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://productaura.co/api/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=productaura.co CN=YE2,O=Let's Encrypt,C=US 28 Oct 2026 26 Jan 2027 ECDSA 256 ECDSA-SHA384 543a19a5e293c8c94152f4f6b74f65c2411
SANs: *.productaura.co, productaura.co
CN=YE2,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 4df3b15dd6c0784c507cd37b58e6f115
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of productaura.co. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
co. DS published 7786 8 Verified
productaura.co. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=31536000; includeSubDomains
content-security-policy frame-ancestors 'none'; base-uri 'self'; object-src 'none'; form-action 'self'
x-content-type-options nosniff
x-frame-options DENY
referrer-policy strict-origin-when-cross-origin
permissions-policy camera=(), microphone=(), geolocation=(), payment=(), usb=()

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://productaura.co/api/mcp Verified 200
http (plaintext) http://productaura.co/api/mcp HTTPS enforced 301 https://productaura.co/api/mcp
MCP tools · 39 exposed · ~6,210 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
answer_facts ~180

Saves product facts the person knows, keyed by missingFacts[].key from create_product (e.g. dimensions, pack-count, key-ingredients), or corrects a fact read from the label. Values are printed word for word on the images and reused for every later set; an empty value removes a fact. Never make values up: ask the person, or skip (images are then made without those numbers). Free. Returns the product with updated facts and missingFacts. Example: {"product_id": "…", "facts": {"dimensions": "12 × 8 × 4 in (30.5 × 20.3 × 10.2 cm)"}}

NameTypeReqDescription
factsobjectyesFact key → value exactly as the person gave it (numbers and units unchanged), up to 20
product_idstringyes–

No output schema declared.

No examples provided.

auto_topup ~181

Shows or changes auto top-up (off by default): when the balance falls below `threshold` credits, the card saved for auto top-up buys `pack` automatically, at most `monthly_max` times a month. Call without arguments to see the status. Turning it on without that card (or with `new_card: true`) returns a Stripe link where the person saves one and sees the agreement (nothing is charged then). Ask the person before turning it on. Free; each top-up is a normal pack purchase. While `available` is false it is paused for everyone: turning it on returns `auto_topup_paused`.

NameTypeReqDescription
enabledboolean––
monthly_max–––
new_cardboolean–true: return a Stripe link to replace the saved card
packstring––
threshold–––

No output schema declared.

No examples provided.

buy_credits ~116

Returns a payment link for a credit pack (pack_s 50, pack_m 150, pack_l 500 credits) or a plan (creator, pro, business; month or year). The person opens it, confirms on a Product Aura page and pays in Stripe; nothing is charged by this tool. Works without an account too: then it returns a link per pack, and the page after payment shows an API key.

NameTypeReqDescription
intervalstring––
packstring––
planstring––

No output schema declared.

No examples provided.

cancel_batch ~70

Skips the batch’s products that are not making images yet (free). Images already started finish, unless stop_images is true: then images no worker has started are cancelled and refunded. Example: {"batch_id": "…"}

NameTypeReqDescription
batch_idstringyes–
stop_imagesboolean––

No output schema declared.

No examples provided.

cancel_image_set ~59

Stops the images of an image set that are still waiting in the queue and refunds their credits in full. Images already being made finish as usual. Free. Returns how many were cancelled and the credits refunded.

NameTypeReqDescription
image_set_idstringyes–

No output schema declared.

No examples provided.

check_image_set ~68

Checks the finished images of a set against the platform’s published image rules (Amazon main image, sizes, formats, Etsy’s 1 MB warning, Shopify limits). Free. Returns pass, warn or info lines per image and for the whole set.

NameTypeReqDescription
image_set_idstringyes–

No output schema declared.

No examples provided.

check_marketplace_spec ~120

Checks one image (base64) against Amazon’s published main image rules: pure white background (RGB 255, 255, 255), product fills 85% or more, whole product in frame, no border, 500–10,000 px, zoom size, file type. Free; no account needed. Returns pass, warn or fail per check with the measured value.

NameTypeReqDescription
image_base64stringyesThe image file as base64 (JPEG, PNG, GIF, WebP or TIFF), up to 15 MB

No output schema declared.

No examples provided.

copy_image_to_set ~89

Copies a finished image into another image set of the same product, platform and language (for example to build variant B of an A/B test), as that set’s picked version of the image. Free: the same file. Example: {"generation_id": "…", "image_set_id": "…"}

NameTypeReqDescription
generation_idstringyes–
image_set_idstringyes–

No output schema declared.

No examples provided.

create_batch ~487

Bulk mode: starts image sets for many products in one call (up to 500; the account’s plan sets the limit). Each product is a product page url, public image_urls, upload_ids, or a product_id the account already has, with an optional name, description and facts. It runs in the background: each product is read, planned and, with mode "run", its images start as soon as its plan is written; with mode "review" each product stops at its plan until start_batch. One product failing never stops the others. Nothing starts beyond what is left (the plan’s products per batch and per day, and the credits for mode run): the dry run’s fits says how many products (from the first) can start now. Call with dry_run true first and tell the person the most it can cost and how many fit; if not all fit, offer the first fits products or buying credits (buy_credits); then call without dry_run. Credits are spent per product when its images start (1 credit per 2K image). Returns the batch id; follow it with get_batch. Example: {"mode": "run", "packs": ["amazon", "etsy"], "items": [{"url": "https://shop.example.com/products/mug"}, {"image_urls": ["https://cdn.example.com/apron.jpg"], "name": "Linen apron"}], "dry_run": true}

NameTypeReqDescription
brand_kit_id––A brand kit for every product; null = no brand; omitted = each product’s brand
dry_runboolean–Only check the products and return the most it can cost
itemsarrayyes–
localestring–Language of text on the images, e.g. "de"
modestring–"run" (default): make everything; "review": write every plan first, then start_batch
namestring–A name for the batch and the folder its products go in
packstring–One platform for every product (same as packs with one entry)
packsarray–The platforms every product gets, one image set each, e.g. ["amazon", "etsy"] (needed unless each item has its own)
stylestring–A social type’s style, e.g. "aesthetic"

No output schema declared.

No examples provided.

create_folder ~56

Creates a folder, optionally inside another one (parent_id from list_folders). Free. Returns the new folder with its id.

NameTypeReqDescription
namestringyes–
parent_idstring–Put the new folder inside this folder

No output schema declared.

No examples provided.

create_product ~383

Creates a product from one or more photos (base64 JPG, PNG or WebP, up to 15 MB each; extra photos from other angles make the images more accurate) or from a product page link (Amazon, Etsy, Shopify or any shop: its photos and text are used), and analyses it: name, category, materials, colours, selling points, the closest category recipe, facts read from the label, and up to 5 missingFacts (each with a question and an example) to ask the person. A service business without a product (a gym, salon, studio, restaurant) works from its website as product_url: it is detected from the page (or set kind "business"), its photos and text are read, and it gets social media ads (pack social) of the place and its people; the product’s profile.kind says which. Free. Returns the product id for answer_facts and plan_image_set, and analysis: when ok is false, tell the person the problem (e.g. a blurry photo) and offer better photos before planning. Examples: {"product_url": "https://example.com/products/mug"}, {"product_url": "https://example-gym.com"}

NameTypeReqDescription
descriptionstring–What the person says about the product (guides the analysis)
extra_images_base64array–More photos of the same product from other angles
image_base64string–The main photo, base64-encoded (a data: URL prefix is fine)
kindstring–Usually leave out: detected from product_url. business: a service business’s website (social ads only)
namestring–Product name, if the person gave one
product_urlstring–A product page link instead of photos; with kind "business", the business’s website

No output schema declared.

No examples provided.

delete_brand_kit ~48

Deletes one brand kit (id from list_brand_kits). Image sets made with it keep their images. Free. Ask the person first.

NameTypeReqDescription
brand_kit_idstringyes–

No output schema declared.

No examples provided.

delete_product ~55

Deletes one product (id from list_products): it and its image sets leave the person’s account. Downloaded images are not affected. Free. Ask the person first. Returns the deleted id.

NameTypeReqDescription
product_idstringyes–

No output schema declared.

No examples provided.

edit_image ~137

Changes one finished image with a short instruction, e.g. "warmer light, add a marble counter" or "make the headline say Leak-proof". Keeps the product and everything else the same. The result is a new version; the old one stays. Costs the same credits as one image (usually 1); explicit, hateful or misleading changes are refused at no cost. Then call get_image_set.

NameTypeReqDescription
generation_idstringyesImage id from get_image_set
instructionstringyesWhat to change, in one or two sentences
versionsinteger–Variations to make at once (default 1)

No output schema declared.

No examples provided.

edit_product ~167

Changes a product’s name, kind, selling points (up to 5 short lines printed on images), facts (by key from list_products; an empty value removes one) or scene. Only the fields given change; later image sets use them. Free. Returns the product. Example: {"product_id": "…", "features": ["Set of 3", "Leak-proof lids"]}

NameTypeReqDescription
categorystring–What kind of product it is, e.g. "kitchen storage"
factsarray–Fact values by key; an empty value removes the fact
featuresarray–Selling points, replacing the current ones
namestring––
product_idstringyes–
settingstring–The scene for lifestyle images

No output schema declared.

No examples provided.

estimate_cost ~159

Returns what an image set would cost before anything is spent: its shots (default: the plan’s ticked ones), or with locales the cost of translating the finished set, or with colours the cost of its colour versions. Also returns the balance. Free. Tell the person the cost before generate_image_set, localize_image_set or recolour_image_set. Example: {"image_set_id": "…", "shots": ["main-white", "lifestyle"]}

NameTypeReqDescription
coloursarray–Instead: the cost of these colour versions
image_set_idstringyes–
localesarray–Instead: the cost of translating into these
shotsarray–Shot keys from the plan; default: the ticked ones

No output schema declared.

No examples provided.

generate_image_set ~392

Spends credits and starts making the images of an image set (all or nothing). shots: shot keys from the plan; leave empty for the default shots. Also adds images to a finished set: pass keys from get_image_set imageSet.moreShots (kinds of images the set does not have yet). Returns at once; images take about 1–3 minutes. Then call get_image_set.

NameTypeReqDescription
also_localesarray–More image languages, e.g. ["de", "fr"]: made automatically once these images are done, each as its own set (1 credit per image with text per language; others copied free). Check the cost with estima…
image_set_idstringyes–
invent_anglesboolean–Make other-angle shots (back, side) even when the product has only one photo; the model then guesses those sides (default true)
notestring–The person's own wish for every image of the set, e.g. "autumn mood, warm wood and dried leaves": it shapes the scenes, never the product, and adds no words. Free.
notesobject–The person's own wish per image, by shot key, e.g. {"social-in-use": "a beagle eating from a red bowl"}: it shapes the scene, props, angle or mood, never the product, and adds no words. Free.
roundsinteger–Versions of each image to make (default 1), to pick the best with pick_image_version; the main image on white is made once. Cost multiplies.
shotsarray–Shot keys to make; default: the plan’s default shots
translate_factsboolean–Translate the product facts printed on the images into the set’s language, numbers and units unchanged (default true; false prints them exactly as saved)

No output schema declared.

No examples provided.

get_batch ~111

Shows a batch made with create_batch: each product’s step (queued, product, plan, planned, starting, generating, done, failed, waiting_credits, skipped), its image_set id (get_image_set has the download links), images done of total, credits, and a plain error for a failed one. Without batch_id: the account’s latest batches. Free. Check every minute or so while products are moving. Example: {"batch_id": "…"}

NameTypeReqDescription
batch_idstring––

No output schema declared.

No examples provided.

get_credit_balance ~30

Returns the account e-mail and credit balance. 1 credit = one 2K image. Free.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_credit_history ~64

Lists the latest credit changes, newest first: images made, refunds for failed or cancelled images, credits bought or added, expiries. Free. Use it to answer "where did my credits go?".

NameTypeReqDescription
limitinteger–How many entries (default 50)

No output schema declared.

No examples provided.

get_image_set ~113

Returns each image’s status (queued, generating, done, failed), its text check (passed, retried, differs, not-checked; checking while it runs), small previews of finished images, and download links valid for 15 minutes. Free. Call again until done is true. A shot can get one extra version by itself: a free retry when the text on the first one did not match.

NameTypeReqDescription
image_set_idstringyes–
previewsboolean–Include image previews (default true)

No output schema declared.

No examples provided.

list_brand_kits ~85

Lists the person’s brand kits, default first: name, website, palette (hex colours, main first), headingFont and bodyFont (Google Fonts names), voice, whether the logo is used, and links to the logo and the typeface sample image. Free. The default kit is used by every new image set unless plan_image_set names another kit or "none".

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_folders ~47

Returns your folders in tree order, each with id, name, parentId and how many products it holds. Free. Use with move_product to organise products by store, platform or client.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_packs ~103

Lists the platform packs (Amazon, A+, Etsy, Shopify, social ads) with their shots, credit cost per shot, the recipes per pack (shot or module lists per product type), the supported languages for text on images, and the prices: plans monthly or yearly (20% off, a year of credits up front) with their credits, brand kits and credit-pack discount, and one-time credit packs (valid 24 months). Free; no account needed.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_products ~33

Lists the account’s products (newest first) with their image sets, category recipe, facts and missingFacts. Free.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

localize_image_set ~197

Makes a finished image set in other languages: the same images with only the text on them translated (numbers, units and names kept), for example an amazon.com set for amazon.de and amazon.fr. Each language becomes its own image set. Images with text cost 1 credit each per language (an edit); images without text are copied free. Call with dry_run true first and tell the person the cost; then call without it (spends credits). Returns the new image set ids; follow them with get_image_set. Example: {"image_set_id": "…", "locales": ["de", "fr"], "dry_run": true}

NameTypeReqDescription
dry_runboolean–Only return the cost; nothing is made or spent
image_set_idstringyes–
localesarrayyesImage languages to make, e.g. ["de", "fr"] (codes from list_packs imageLanguages)

No output schema declared.

No examples provided.

move_product ~78

Puts a product (id from list_products) in a folder (id from list_folders), or takes it out of every folder when folder_id is left out. Free. Image sets stay with the product.

NameTypeReqDescription
folder_idstring–Target folder; leave out for "not in a folder"
product_idstringyes–

No output schema declared.

No examples provided.

name_image_set ~67

Gives an image set a name, e.g. "Variant B: warm light", for A/B tests; an empty name removes it. The set code (PA-…) stays in file names. Free.

NameTypeReqDescription
image_set_idstringyes–
namestringyes–

No output schema declared.

No examples provided.

pick_image_version ~65

Makes this version (a generation id from get_image_set) the one its set uses for that image: the ZIP, downloads, checks and translations use it. Every version stays stored. Free. Example: {"generation_id": "…"}

NameTypeReqDescription
generation_idstringyes–

No output schema declared.

No examples provided.

plan_image_set ~696

Creates an image set for a product and platform pack and returns its shot plan, written for this product (takes up to a minute): each shot with what it will show, why it sells and its credit cost; shots that do not fit the product (unfit says why) are left out of the default shots. Also the current balance and the pack’s missingFacts. Every pack but social follows the product’s recipe for that pack (shopify also uses the store look, see store_look; amazon-aplus takes aplus_format and aplus_text); shots listing withoutFacts are made without numbers (answer_facts first to add them), and plan.note says so. Free; nothing is generated yet. locale sets the language of text on the images. The person’s default brand kit is used unless brand_kit_id names another or "none". Example: {"product_id": "…", "pack": "amazon-aplus", "aplus_text": "fields"}

NameTypeReqDescription
aplus_formatstring–amazon-aplus only: basic (970 × 600 and 970 × 300, open to every brand; default) or premium (1464 × 600 modules, only for brands Amazon approved for Premium A+)
aplus_textstring–amazon-aplus only: image (text on the images, default) or fields (calm empty copy zones; the text comes back per image as copy, to paste into Amazon’s A+ text fields)
brand_kit_id––A brand kit from list_brand_kits, or "none"; default: the person’s default kit
localestring–Language of text on the images, e.g. en, de, fr, ja (default: the brand’s, else the account’s, else en)
model_agestring–Clothing: the model’s age (default any)
model_bodystring–Clothing: the model’s build (default any)
model_skinstring–Clothing: the model’s skin tone (default any)
packstringyesPlatform pack: amazon, amazon-aplus, etsy, shopify, tiktok-shop (square images for every TikTok Shop region); social ads: social (static ad images) or social-carousel (square carousel ad cards, one s…
product_idstringyes–
sizesarray–social only: make every ad in each size: 4:5 feed, 1:1 square, 9:16 story, 1.91:1 landscape. Each size is its own image and costs its credits. Leave out for each ad in its own shape.
stylestring–A social type’s style. instagram-grid: aesthetic (default: a different scene in every post, no text), standard-mix (photos and witty designed posts in one palette) or calm-clean (one calm look). soci…

No output schema declared.

No examples provided.

rate_image ~76

Thumbs up (1) or down (-1) on one generated image, with optional reasons: product-changed, wrong-text, not-realistic, bad-composition, wrong-style, low-quality. Helps improve the images. Free.

NameTypeReqDescription
generation_idstringyes–
rating–yes–
reasonsarray––

No output schema declared.

No examples provided.

recolour_image_set ~250

Makes a finished image set’s main image in other colours of the product, for colour variations and swatches (stores show one image per colour; all_images true makes every image, shot for shot): only the product’s colour changes, the scene and text stay. Each colour becomes its own image set. Images with the product cost 1 credit each per colour (an edit); images without it are copied free. A hex code or a photo of the product in that colour (photo_base64) makes the colour more exact. Call with dry_run true first and tell the person the cost; then call without it (spends credits). Returns the new image set ids; follow them with get_image_set. Example: {"image_set_id": "…", "colours": [{"name": "Navy", "hex": "#1F3A5F"}], "dry_run": true}

NameTypeReqDescription
all_imagesboolean–Every image of the set in each colour, not only the main image (default false)
coloursarrayyes–
dry_runboolean–Only return the cost; nothing is made or spent
image_set_idstringyes–

No output schema declared.

No examples provided.

redo_image ~176

Makes a free new version of an image whose product came out different (shape, label, colour, logo) or whose text is wrong. Limits: 3 per image and a monthly allowance per account; outside them use regenerate_image or edit_image (1 credit). Free. Returns the new image id. Ask the person what is wrong and pass it as note. Example: {"image_id": "…", "reason": "product-changed", "note": "the label says 250 ml, it should be 500 ml"}

NameTypeReqDescription
image_idstringyes–
notestringyesWhat exactly is wrong, in the person’s words, e.g. "the cap is silver, it should be gold"; it is turned into a correction for the new version
reasonstringyesWhat is wrong

No output schema declared.

No examples provided.

regenerate_image ~119

Makes one image of a set again with the same prompt, as 1–5 new versions next to the old ones, to pick the best (pick_image_version). Each version costs the original image’s credits (usually 1). Not for the main image on white (a cut-out of the photo); use edit_image for that. Returns the new generation ids; then call get_image_set.

NameTypeReqDescription
generation_idstringyesImage id from get_image_set
versionsinteger–New versions to make at once (default 1)

No output schema declared.

No examples provided.

retry_batch ~95

Tries a batch’s failed products again from where each stopped (free; all, or item_ids). With resume true instead: starts the products that waited for credits (step waiting_credits) after a top-up, spending their credits. Example: {"batch_id": "…"}

NameTypeReqDescription
batch_idstringyes–
item_idsarray––
resumeboolean–Start the products waiting for credits instead

No output schema declared.

No examples provided.

save_brand_kit ~425

Creates a brand kit, or changes one when brand_kit_id is given (only the fields sent change). With website and no brand_kit_id, the brand’s name, colours, fonts and logo are read from the site first; show the person what was found, including the font sample (fontSampleUrl), and save fonts_confirmed true once they say it matches. Brand kits put text in the brand’s fonts (shown to the image model as a typeface sample image) and designed elements in its colours. Free; the number of kits depends on the plan (1 without a plan, Creator 3, Pro 10, Business 50). Returns the saved kit (and, after an import, what was found). Example: {"website": "https://example.com"}

NameTypeReqDescription
body_font––Google Fonts family for small text, e.g. "Inter"
brand_kit_idstring–The kit to change; leave out to create a new one
font_sample_base64string–A picture of a paragraph set in the brand’s font, for fonts not on Google Fonts
fonts_confirmedboolean–The person checked the fonts and their sample: they match
heading_font––Google Fonts family, e.g. "Playfair Display"
is_defaultboolean–Use this kit for new image sets by default
logo_base64string–The logo (PNG with transparency, JPG, WebP or SVG)
namestring––
palettearray–Hex colours, main colour first, e.g. ["#1A1A1A", "#E8DCC8"]; [] removes them
use_logoboolean–Put the logo, small, on images with a spot for it (poster, grid)
voicestring–How the brand sounds, e.g. "warm, playful, no jargon"
websitestring–The brand’s website; on a new kit its brand is read from it

No output schema declared.

No examples provided.

send_feedback ~36

Sends feedback to the Product Aura team (what worked, what did not, what is missing). Free.

NameTypeReqDescription
messagestringyes–

No output schema declared.

No examples provided.

start_batch ~170

For a batch made with mode "review": starts the images of the products whose plan is ready (all, or item_ids from get_batch). Without item_ids, products still being planned start by themselves once planned. Spends the credits of their ticked images; refused when the balance does not cover them, then only_what_fits true starts the first ones the credits cover. Call with dry_run true first and tell the person the cost and how many fit. Example: {"batch_id": "…", "dry_run": true}

NameTypeReqDescription
batch_idstringyes–
dry_runboolean–Only return products, credits and fits
item_idsarray–Only these products
only_what_fitsboolean–Start only the first products the credits cover

No output schema declared.

No examples provided.

store_look ~407

Shows or changes the store look shopify-pack images are made in, so a whole catalogue matches: backdrop colour and type, accent colour, light, image shape, model notes and an optional reference photo from the person’s store. Each brand kit can have its own look (brand_kit_id); a brand without one, and a set without a brand, use the account’s look (own: false says a brand uses it). Call without fields to see it; send only the fields to change. Free. Returns the saved look. Example: {"brand_kit_id": "…", "backdrop_color": "#E8E2DA", "ratio": "4:5"}

NameTypeReqDescription
accent_color––Hex for small props and type; null for none
backdrop_colorstring–Hex, e.g. #EDEDED (default)
backdrop_typestring–seamless (default), textured or scene
brand_kit_idstring–A brand kit from list_brand_kits; leave out for the account’s own look
facesstring–show (default) or crop (never show faces)
lightstring–soft-studio (default), hard-flash or natural-daylight
model_lookstring–How models look, e.g. "women in their 20s, athletic"
ratiostring–auto (default: the product type’s shape: square; 4:5 clothing, home, pet, gifts; 3:4 shoes), or 1:1, 4:5, 3:4 or 5:6 for every image
reference_image_base64string–A photo from the person’s store (JPG, PNG or WebP) to match: backdrop, light, crop
remove_referenceboolean––
skin_tonesstring–e.g. "light, medium and deep"

No output schema declared.

No examples provided.

Install

How do I install the Product Aura MCP server?

Product Aura is a hosted endpoint at https://productaura.co/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · productaura.co

# add to Claude Code
claude mcp add --transport http co-productaura-productaura 'https://productaura.co/api/mcp'
Common questions

What is the Product Aura MCP server?

Product Aura is an MCP server listed in the public MCP registry as co.productaura/productaura. Listing and ad images for Amazon, Etsy, Shopify, TikTok Shop and social ads, from one product photo. This page covers its hosted endpoint (https://productaura.co/api/mcp).

Is the Product Aura MCP server safe to use?

Product Aura scores 73 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Product Aura MCP server expose?

Product Aura exposes 39 tools: list_packs, get_credit_balance, create_product, answer_facts, list_products, and 34 more. Their descriptions and schemas cost roughly 6,210 tokens of context every time the server is loaded.

Does the Product Aura MCP server require authentication?

No. We connected to Product Aura without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Product Aura MCP server still maintained?

Product Aura is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the Product Aura MCP server?

VerifyMCP ran 14 checks on Product Aura, covering TLS certificate, Authorization, HTTPS, HSTS header and 10 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.