MCP App Store
by KeenEthics
AutoHDR icon

AutoHDR MCP Server for ChatGPT

By AutoHDR

Overview

Raw to client-ready in one conversation. Brief ChatGPT like you would an editor: upload your shoot, choose AutoHDR’s flagship Iris model or another available style, and prepare your gallery. When it’s ready, ask ChatGPT to review the photos before delivery, replace grass on exterior shots, remove clutter, virtually stage a room, or create a twilight cover shot. Connect your AutoHDR account to check processing status, review edit history, and download finished photos. Supports camera JPEGs and common RAW formats. Processing times vary by shoot size and model. Processing, edits, presets, and first-time downloads may consume AutoHDR credits. Shoots are accessible through the integration for seven days after creation.

How to connect

  1. ChatGPT: Open the AutoHDR listing in the ChatGPT app directory and choose Connect. ChatGPT listing AutoHDR exposes 25 tools here.

Tools

commitPhotoshoot

ChatGPT
⚠️ Starts processing. Commit itself does not debit. House models = pay on download; creator models bill without download (fee when processing finishes). For raw this kicks off HDR and is not idempotent. Retry on error=files_not_landed; after 202 poll getPhotoshootStatus and ignore another commit 409. Call once every file has been PUT to its presigned URL (or, for from-urls, once you think the server fetch has landed). Pass the job_id from create in the body (it must belong to the photoshoot in the path — the two are cross-checked). Missing PUT files are 400. A from-urls job still landing is 409 error=files_not_landed — retry commit until 202. After 202, poll status; a later 409 error=conflict means already committed. Do not open another shoot.

createPhotoshoot

ChatGPT
Creates a new photoshoot bound to the token's identity and returns one presigned S3 PUT URL per file. PUT each file directly to its url with the content_type header given in the response (required — it's signed into the URL). URLs expire in 5 minutes. Then call the commit endpoint. Finished HDR photos and any enhancements (grass, declutter, a lit fireplace, replaced TV screens) are AI edits.

createPhotoshootFromFiles

ChatGPT
Create a photoshoot from attached or provided files. Use this when you have the files as attachments (or file references) rather than local paths to PUT. The AutoHDR server fetches each file. Next: retry commitPhotoshoot until 202, then poll getPhotoshootStatus. error=files_not_landed (409) means files have not landed yet — retry commit, do not create another shoot. After 202, ignore another commit 409 and poll status. awaiting_files=true means HDR has not started. Files run the full HDR pipeline. Does not charge; commit/download/transform costs are unchanged.

describePhoto

ChatGPT
AI eyes for an agent: returns a text description of a photo. Read-only and free (no credits). Omit prompt for an exhaustive dump of everything visible (sky, house, grass, fixtures, toilet seat up/down, wires, cars, roof cut off by the framing, etc.). Pass a prompt to ask a specific question. Defaults to the photo's current version; pass image_version_uuid (from GET .../history) to view a specific one. Owned by the token identity; a photo you don't own returns 404.

downloadPhotos

ChatGPT
⚠️ Spends credits. Download full-resolution photos from a photoshoot. Returns a presigned URL per photo, valid for 6 hours. Charges 1 credit per photo the first time it is downloaded; downloading it again is free. A display upload is already covered once a paid edit on it has made a new version. Returns 402 when the account is out of credits; nothing is charged or marked as downloaded. Disclosure watermark: while the account has it on (GET /v1/settings), photos it counts as altered come back as their disclosure copy, with the watermark drawn on; nothing changes on your side. Send variant: "clean" for copies without it, e.g. when you feed an MLS or add your own branding.

getCredits

ChatGPT
Returns the live credit balance for the account the token acts on. Use it to display a balance or check affordability before spending on transforms or downloads. Credits debit the client owner (M2M) or the consenting user.

getMe

ChatGPT
Returns the token's client id, resolved AutoHDR user, granted scopes, and current credit balance. The cheapest way to verify the OAuth chain end-to-end before making real requests.

getPhotoHistory

ChatGPT
Returns how a photo was made and every edit since, as a chain of steps (oldest first) — the same lineage the AutoHDR editor's history panel shows. Each step has a short label/description and points at its parent via parent_image_version_uuid (walk it to rebuild the chain; the is_head step is the current photo). Use step ids for branch edits on submit, or to deliver an earlier step (POST .../version to make it the head, then download); use the download endpoint for full-resolution files. Owned by the token identity; a photo you don't own returns 404.

getPhotoshootStatus

ChatGPT
Returns status (in_progress | success | failure), pipeline (hdr | display), and the photo count. Poll every 3–5s while in_progress; stop at success (photos ready) or failure. pipeline=hdr is the photographer path (camera files) — the intended product, not 'HDR has started'. If awaiting_files is true, files have not been committed yet: call commit (retry on files_not_landed), do not treat this as a running HDR job. Display ingest is usually seconds. HDR typically takes a few minutes; plan on ~30 min, and large RAW sets can take up to an hour. image_count may climb while still in_progress — only success/failure are terminal. Do not submit transforms until success if you care which version is head. pipeline=display means the files were ingested as-is — no HDR. On failure you may optionally re-poll once after a few minutes — a very slow shoot can be flagged failed and then recover.

getPreset

ChatGPT
One preset by uuid, with its inputs (input_ports), output description, example media, and per-run credit_cost. makes_clip is true when the preset returns a video file. Otherwise it returns a photo. Both are AI edits. Use input_ports to map the shoot's assets onto the preset, then runPreset. A preset you can't reach 404s.

getSettings

ChatGPT
Account-wide defaults for the account the token acts on: the HDR models and enhancements a shoot uses when its create call leaves them out, realtor sign removal, perspective correction, walkthrough order, and the disclosure watermark (whether edits also write a disclosure copy, and which file downloadPhotos returns by default). The same settings as the Style tab in the AutoHDR app.

getSkill

ChatGPT
Get one published skill by name: its SKILL.md, its file list, and its declared runtimes, network hosts and credentials. Read-only and free.

getTransformJob

ChatGPT
Returns the job's current state. Poll every 3–5s until status is succeeded or failed (typically ~30s–2min). Three terminal shapes: succeeded + an output_image_version_uuid = a new version was minted (download that); succeeded + null output = the model ran and chose to change nothing (no-op skip — common for camera_removal when no photographer is in frame; the photo is unchanged; confirm with getPhotoHistory); failed = it broke. Only the job's owner can read it. A terminal job stays queryable — a succeeded/failed job keeps returning its final state (and failure_code/failure_message), so missing the poll that first flips it loses nothing.

listCapabilities

ChatGPT
The AI post-processing transforms partners may run, each with its live credit cost and whether it needs a mask. style.credit_cost is null: that edit is priced per model, on style_credit_cost from GET /v1/models. Do not treat a null or a missing number as 1. REST callers see the full catalog; MCP callers omit mask-required transforms (autoremove, autofill). Still requires a token like the rest of /v1. Fetch at runtime instead of hardcoding names or prices; new models appear here automatically.

listModels

ChatGPT
Models you can pass as indoor_model_id / outdoor_model_id at create: AutoHDR's own models, creator models like Aura, and your own or granted models. Interior photos use the indoor slot and exterior photos the outdoor slot; set both, since a slot you omit falls back to the account default. variant is indoor, outdoor, or indoor/outdoor (either). Indoor and outdoor versions of a look can share a name (Iris Blue Sky is 26 and 32), so pick by id and variant. All current creator models handle flash and flambient shoots; Aura, Fuse and Brut are built for it. type=predefined returns AutoHDR's own models (Iris, Ember, Classic); type=custom returns creator models like Aura plus your own and granted models, which depend on who the token acts for. style_credit_cost is what a style submit charges for that id; use it, not the style price on GET /v1/capabilities.

listPhotos

ChatGPT
Returns each processed photo's ids and filename. Use it to pick photos, then call the download endpoint for full-resolution files. Photos come back in gallery order, the same order as the photoshoot on the AutoHDR site (walkthrough order when it's on), continuing across pages, so list position works as a sequence number when naming downloads. Paginated with page/page_size (same shape as the transforms list).

listPhotoshoots

ChatGPT
Returns the acting account's photoshoots created in the last 7 days (most recently created first), each with its address, processing status, and photo count. Use it to discover photoshoot_ids to poll, list photos, or download. The 7-day window is fixed and cannot be widened — shoots created earlier are not listed here, and every photoshoot endpoint answers them with 410 photoshoot_expired. Paginated with page/page_size (same shape as the other list endpoints).

listPresets

ChatGPT
A page of the public preset catalog, newest first. Private (own/team) presets are not listed here — author and run those in the AutoHDR app. Each card carries a name, creator_name, what it outputs (result_description), its inputs (input_ports — what to supply, photo or video), example media, credit_cost per run, and is_video/takes_clip/makes_clip. makes_clip is true when the preset returns a video file. Otherwise it returns a photo. Both are AI edits (takes_clip only means the input is a clip). Get one by uuid with getPreset, then runPreset.

listSkills

ChatGPT
List published AutoHDR skills: reviewed guides for real-estate tasks. Each has a name, a description, and what it declares it needs (script runtimes, network hosts, credentials). Read-only and free.

listTransformJobs

ChatGPT
Returns a page of your transform jobs for one photoshoot, newest first. photoshoot_id is required — the list is always scoped to a single shoot (and to your token identity: you only ever see your own jobs). Use it to recover a lost job_id or reconcile a shoot's jobs without polling each by id. Filter by lifecycle bucket with state (active = in-flight/recent, history = older/terminal, all = both). Each row carries a status_url you can poll directly. To sweep every shoot, call listPhotoshoots and page this per id.

readSkillFile

ChatGPT
Read one file of a published skill (a reference doc, example or script) by a path from getSkill's file list. Returns the text; reading a script does not run it. Read-only and free.

runPreset

ChatGPT
⚠️ Spends credits (not idempotent — a retry re-charges). Run a preset on explicit photos (items) or every visible photo in one shoot (photoshoot_id) — provide exactly one. Supply any inputs the preset's input_ports ask for beyond the subject via ports (each a photo version in your listing or an s3:// upload from asset-uploads). Charges the preset's credit_cost per photo. makes_clip is true when the preset returns a video file. Otherwise it returns a photo. Both are AI edits. Returns one workflow_uuid per target — poll it with getTransformJob, then download. Video presets run on one target at a time (use items, not the whole-shoot path). 402 when out of credits.

setPhotoVersion

ChatGPT
Point a photo at one of its history versions (an image_version_uuid from GET .../history) so that step becomes the current version — the one download returns and future transforms build on. Free (no credits). Use it to deliver an earlier edit, e.g. the step before a later change, and after a style regenerate or a redo: those land beside the old version and don't become current on their own. The id must belong to this photo's history, otherwise 404; if an id from an earlier call 404s, read GET .../history again for the current ids.

submitTransform

ChatGPT
⚠️ Spends credits (not idempotent — a retry re-charges). Submit one AI post-processing transform against a processed photo. The output image is an AI edit. Address the photo by photoshoot_id + image_uuid + image_version_uuid — get all three from GET /v1/photoshoots/{id}/photos (there is no resubmit-by-image-alone path). transform_name must be one advertised by /v1/capabilities; reedit requires a prompt; style requires model_id (optional prompt only when that id is 25 or higher) and re-renders the photo's look from its original photos rather than stacking on the current edit; mask transforms require a mask_url (autofill also needs a prompt or reference_image_urls). Returns a job — poll GET /v1/transforms/{job_id} until status is succeeded/failed (typically ~30s–2min). Then fetch the result via the photos/download endpoints. Charges the catalog price on submit (see /v1/capabilities). For style, read style_credit_cost on the model from GET /v1/models — that is the price charged for the model_id you pass. Skipped or failed steps are refunded. 402 when the account is out of credits. succeeded with a null output_image_version_uuid means the model ran and chose to change nothing (a no-op skip) — the photo is unchanged.

updateSettings

ChatGPT
Changes only the fields sent and returns the full settings. All or nothing: one invalid field (a model the account can't use, an unknown edit name) rejects the whole request with 422 invalid_setting and changes nothing. Account-wide, the AutoHDR app included. Nothing already made changes: models are fixed onto a shoot when it is created, and enhancements, sign removal, perspective and walkthrough are read when a shoot is processed, so a shoot created but not yet processed picks up the new value. Pass options on the create call when one shoot needs something different instead of changing these back and forth. Enhancements cost credits on every shoot they run on unless the plan includes them.

Capabilities

WritesInteractive

Example Prompts

Click any prompt to copy it.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/autohdr"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/autohdr)