Verified conversions across 205 color spaces: CSS strings, gamut checks, .cube LUTs
Nothing to run from here
Backdraw is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
94/100
trust score
10
downloads a day
local
runs on your machine
1k
downloads in 30d
What it does
Generate images with your own ChatGPT account in a background Chrome tab. Needs Windows + Chrome.
Quickstart
Install it the way its author documents:
1. npx backdraw@latest setup
2. Follow the setup steps to load the Chrome extension (one time)
3. Log in to chatgpt.com in that Chrome
4. Restart your MCP client (Claude Code, Claude Desktop, Cursor or VS Code)
5. If something doesn't work: npx backdraw@latest doctor
The full guide: https://github.com/devtalh/backdraw#readme
Publisher
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Backdraw as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Install it the way its author documents:
1. npx backdraw@latest setup
2. Follow the setup steps to load the Chrome extension (one time)
3. Log in to chatgpt.com in that Chrome
4. Restart your MCP client (Claude Code, Claude Desktop, Cursor or VS Code)
5. If something doesn't work: npx backdraw@latest doctor
The full guide: https://github.com/devtalh/backdraw#readme
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Generate or edit an image with ChatGPT through the user's own logged-in ChatGPT account in Google Chrome (no OpenAI API key, no extra cost).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| prompt | string | yes | Full image description or edit instructions, in any language. |
| aspect_ratio | string | no | Optional shape as W:H, e.g. 1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 4:5, 5:2 (Discord banner) or 3:1 (header). Any W:H with whole numbers between 1:4 and 4:1 works (not 1.5:1: use 3:2). ChatGPT draws 1:3 |
| transparent_background | boolean | no | Ask for a PNG with a transparent background (stickers, logos, icons, sprites). The result says whether the saved image really has transparent pixels. |
| reference_images | array | no | Optional local image files (png/jpg/webp/gif, up to …) attached to the message, e.g. the image to edit or a character sheet. Paths saved by earlier calls work directly. |
| conversation_url | string | no | Optional ChatGPT conversation link from an earlier result: the prompt is sent in that chat instead of a new one. Fine for quick follow-ups; for exact edits prefer reference_images in a fresh chat. |
| auto_reattach | boolean | no | If ChatGPT answers that it can't access the image and asks for it to be uploaded, attach the chat's latest image (or reference_images) automatically and ask once more. |
| output_dir | string | no | Optional folder to also copy the image(s) into, e.g. the current project's assets folder (absolute path preferred). The central images folder always keeps a copy. |
| filename_hint | string | no | Optional few words naming the subject (e.g. 'red fox mascot'), used for the saved file name instead of the start of the prompt. Pass it when the prompt opens with something else, such as instructions |
| wait_seconds | no | — | |
| include_preview | boolean | no | Attach a downscaled preview of the result so you can check it. |
| send_as_is | boolean | no | Send the prompt verbatim, without the short instruction the bridge adds (useful to answer a question ChatGPT asked). |
| reference_collection | string | no | Optional name of one of the user's Backdraw reference collections (see list_collections; matched loosely). Its images are attached after any reference_images, up to … references in total: over the lim |
| reference_files | array | no | Optional file names from list_collections to attach only those images of reference_collection, instead of the newest. |
Check a ChatGPT image job by job_id, waiting up to wait_seconds (default …) for it to finish; call it again while the result says STILL RUNNING or QUEUED.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job_id | string | no | Job id returned by generate_image (e.g. img_1a2b3c4d). |
| wait_seconds | no | — | |
| include_preview | boolean | no | Attach the image preview when the job succeeded. |
Cancel a queued or running ChatGPT image job. If ChatGPT is already generating, it presses Stop in the background tab and closes that tab.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job_id | string | yes | Job id to cancel. |
Download the generated images of the latest answer in an existing ChatGPT conversation (by its link) without sending anything.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| conversation_url | string | yes | ChatGPT conversation link (https://chatgpt.com/…/c/…). |
| aspect_ratio | string | no | Optional W:H (between 1:4 and 4:1, e.g. 16:9) to crop the downloaded images to, from the centre; the full images are kept too. For the result of a generate_image job, pass its aspect_ratio again. |
| output_dir | string | no | Optional folder to also copy the image(s) into (absolute path preferred). |
| wait_seconds | no | — | |
| include_preview | boolean | no | Attach a downscaled preview. |
List the Projects in the user's ChatGPT account (read from ChatGPT's sidebar in a background tab) and show which one is selected for images. Use it during setup.
No parameter schema on file.
Select and remember the ChatGPT Project where new image chats are created. Pass the project name as shown in ChatGPT (matched loosely) or its https://chatgpt.com/g/g-p-…/project link.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | no | Project name as shown in ChatGPT. |
| url | string | no | Project link (alternative to name). |
List the reference collections the user saved in Chrome (right-click an image, "Add to Backdraw"): each with its image count, folder and files (newest first, with the site they came from).
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Backdraw or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 94 / 100
Release 2.1.3 · scanned 28 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score94
Findings2 threat · 3 capability
Capabilityhigh
Coveragesource
Verificationsource
Surface digestbdefedf535d4acfaccc0b6f8696270931c5d7710ecfb4e40edb0680decde43f7
Score vectorthreat 100 → client 94
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (4 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| generate_image | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| list_projects | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| select_project | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| list_collections | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digestbdefedf535d4acfa
Scanned2026-10-28
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 2.1.3. Pin a release below and the command asks for exactly that one.
2.1.3
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Backdraw can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.