Skip to main content
Glama
816,301 tools. Updated 2026-11-21 13:25

"Using OpenAI to Generate Images" matching MCP tools:

  • Remove a specific image from a product. Destructive, idempotent. Authenticated. OAuth (scope `products:write`) preferred; `api_key` fallback. Use when an image was uploaded by mistake or the merchant updated their listing. The product itself is preserved — only the image record and its file are removed. To remove the product entirely use `delete_product`. Args: product_id: ID of the product the image belongs to. image_id: ID of the image to delete. Visible in the `images` array of `get_product` responses. api_key: Optional API key (`pk_*`, generate at /account). Used when there is no OAuth token, and also when the OAuth token lacks the required scope — an explicitly passed key overrides an ambient token that is scoped too narrowly. An invalid or revoked token still fails regardless. Omit when using OAuth. Returns: ``{"deleted": True, "product_id": int, "image_id": int}`` on success, or ``{"error": ...}`` on auth/ownership failure.
    Connector
    Destructive
    No auth
  • Remove a specific image from a product. Destructive, idempotent. Authenticated. OAuth (scope `products:write`) preferred; `api_key` fallback. Use when an image was uploaded by mistake or the merchant updated their listing. The product itself is preserved — only the image record and its file are removed. To remove the product entirely use `delete_product`. Args: product_id: ID of the product the image belongs to. image_id: ID of the image to delete. Visible in the `images` array of `get_product` responses. api_key: Optional API key (`pk_*`, generate at /account). Used when there is no OAuth token, and also when the OAuth token lacks the required scope — an explicitly passed key overrides an ambient token that is scoped too narrowly. An invalid or revoked token still fails regardless. Omit when using OAuth. Returns: ``{"deleted": True, "product_id": int, "image_id": int}`` on success, or ``{"error": ...}`` on auth/ownership failure.
    Connector
    Destructive
    No auth
  • Upload a base64-encoded file to a site's container. Use this for binary files (images, archives, fonts, etc.). For text files, prefer write_file(). Requires: API key with write scope. Args: slug: Site identifier path: Relative path including filename (e.g. "images/logo.png") content_b64: Base64-encoded file content Returns: {"success": true, "path": "images/logo.png", "size": 45678} Errors: VALIDATION_ERROR: Invalid base64 encoding FORBIDDEN: Protected system path
    ConnectorNo auth
  • Check whether still images of a project show the SAME character as its character sheet — before paid clips are made from them. Each image is compared against the sheet's detail and fullbody views. It judges identity (species, build, colouring, head shape, large markings), NOT style, light, pose, place or props — and deliberately NOT micro details like an ear notch or the number of fingers, which no image model holds reliably. Free. Runs in the BACKGROUND: returns a `job_id` with HTTP 202 — poll it with lab_get_job until status is done|failed; the result lists per image passt, sicherheit, abweichungen, begruendung (or error). Up to 16 images and frames together per call. Images must be completed images of this project (imported images are refused). To check frames of a GENERATED CLIP (an orbit turnaround, a lab_animate clip) pass clip_frames: the clip's video_id and the seconds to cut out — the frames are taken from the clip itself and compared the same way; a second beyond the clip's end fails only that frame. The sheet needs a reference image (lab_generate_character_reference).
    ConnectorOAuth
  • Permanently delete a product listing and all its images. Destructive. Authenticated. OAuth (scope `products:write`) preferred; `api_key` fallback. Use only when the user explicitly asks to remove a listing they own. Cannot be undone — there is no soft-delete or trash bin. Idempotent: deleting a product that no longer exists returns an error, not duplicate side effects. Caller must own the product. Args: product_id: ID of the product to delete. Get from `get_my_products`. api_key: Optional API key (`pk_*`, generate at /account). Used when there is no OAuth token, and also when the OAuth token lacks the required scope — an explicitly passed key overrides an ambient token that is scoped too narrowly. An invalid or revoked token still fails regardless. Omit when using OAuth. Returns: ``{"deleted": True, "product_id": int}`` on success, or ``{"error": ...}`` on auth/ownership failure.
    Connector
    Destructive
    No auth
  • Permanently delete a product listing and all its images. Destructive. Authenticated. OAuth (scope `products:write`) preferred; `api_key` fallback. Use only when the user explicitly asks to remove a listing they own. Cannot be undone — there is no soft-delete or trash bin. Idempotent: deleting a product that no longer exists returns an error, not duplicate side effects. Caller must own the product. Args: product_id: ID of the product to delete. Get from `get_my_products`. api_key: Optional API key (`pk_*`, generate at /account). Used when there is no OAuth token, and also when the OAuth token lacks the required scope — an explicitly passed key overrides an ambient token that is scoped too narrowly. An invalid or revoked token still fails regardless. Omit when using OAuth. Returns: ``{"deleted": True, "product_id": int}`` on success, or ``{"error": ...}`` on auth/ownership failure.
    Connector
    Destructive
    No auth

Matching MCP Servers

Matching MCP Connectors

  • Generate images with the catalogue's image model, returned inline; image price plus $0.01 a call.

  • Hosted OpenAI Ads MCP server for Claude, ChatGPT and Cursor, with each action switched per account.

  • Generate an empty background plate for one short shot. Both reference inputs steer what the plate itself looks like — layout, prop identity, materials and lighting — and are unrelated to upload_shot_continuity_reference, which guides clip generation instead. Use reference_image_asset_ids for images already in this project (find them with get_asset_library) and reference_images_base64 to send bytes you produced locally, for example a frame lifted from an earlier scene so a prop matches what is already on screen. Uploaded bytes are used for this one generation and are not kept as project assets. The location's own reference images are always included on top of both. Spends credits. Returns a job id — poll it with get_job.
    ConnectorNo auth
  • Put a REAL photo or illustration on the site by describing it — no image bytes to send. Give a vivid `prompt` and a `public/` `path` (e.g. public/hero.jpg); Kleap generates it with Cloudflare FLUX.2 and stores it as a proper binary asset, exactly like write_files with encoding:"base64" but with NO base64 to transmit (a real image's base64 is too big for a model to emit reliably — this is the ONLY dependable way to add a generated picture). Use it for hero photos, section illustrations, onboarding images, OG images, or to replace a broken/ugly image. Square 768×768 by default; pass width/height (256–1440) for other ratios; hd:true uses the premium model (sharper, slower). ⚠️ To REPLACE an existing image, generate to a NEW filename (e.g. hero-2.jpg) and point the markup at it — overwriting the same path can be served stale from CDN/R2 cache. After it returns, call publish_app to deploy it live.
    Connector
    Destructive
    OAuth
  • Put a REAL photo or illustration on the site by describing it — no image bytes to send. Give a vivid `prompt` and a `public/` `path` (e.g. public/hero.jpg); Kleap generates it with Cloudflare FLUX.2 and stores it as a proper binary asset, exactly like write_files with encoding:"base64" but with NO base64 to transmit (a real image's base64 is too big for a model to emit reliably — this is the ONLY dependable way to add a generated picture). Use it for hero photos, section illustrations, onboarding images, OG images, or to replace a broken/ugly image. Square 768×768 by default; pass width/height (256–1440) for other ratios; hd:true uses the premium model (sharper, slower). ⚠️ To REPLACE an existing image, generate to a NEW filename (e.g. hero-2.jpg) and point the markup at it — overwriting the same path can be served stale from CDN/R2 cache. After it returns, call publish_app to deploy it live.
    Connector
    Destructive
    No auth
  • Attach one or more images to a ContentIn post that is not published yet. IMAGES ONLY — JPG, PNG or WEBP, at least 200×200px, at most 8 MB each, and at most 5 per post. Video, GIFs, PDFs and document carousels are NOT supported and will be refused, so do not try to attach one. Pass each image either as a public url (ContentIn downloads it) or as a base64 string with its mime_type. Two or more images publish as a LinkedIn multi-image post, in the order you list them. mode 'replace' (the default) makes the post's images exactly this set and deletes the ones it had; mode 'append' keeps the existing ones and adds to them, up to the same total of 5. Attaching does not publish anything — call publish_post or schedule_post afterwards, and call list_posts to check what is attached.
    Connector
    Destructive
    API key
  • The account's images, newest first: uploads, images found by page scans, and re-runs. Filter by status, by source (upload or scan) or by one scan's id, which is how a page scan's images are read once get_scan says they are done. An image with responsive sizes carries only their status here; get_image has their links. Pages of up to 50; ask for the next page while page is below last_page. For one image whose id you already have, call get_image instead.
    ConnectorAPI key
  • Returns a private, short-lived upload URL for a file that has no public HTTPS link (a carousel PDF, an image, or an mp4). The file is sent with an HTTP PUT of its raw bytes to upload_url using the returned headers; the returned upload_id is then accepted by save_draft as media: [{ upload_id }] (an image item can add alt_text there), with id to attach it to an existing draft or scheduled post. The URL expires soon (expires_in gives the seconds left; it can be as little as 60), so upload right away. Limits: images 5MB, video 75KB–200MB mp4, PDF 100MB.
    ConnectorOAuth
  • Set the images an entry shows after its lead image: the whole ordered list of media ids (from media_catalog or get_entry), replacing the gallery; [] empties it. At most 5 (6 images in all with the lead), each once, never the lead itself (set_entry_image sets that). An image taken off loses its link; `links` sets or clears the link of an image in the list (needs Link images). A live edit, audited. Dry run by default. To ask a reviewer instead, use propose_entry_change.
    Connector
    Destructive
    OAuth
  • Generate images with any OceanToken image model (text-to-image, or image-to-image / editing when reference_image_urls are given). Returns download links (valid ~24h) and small previews. size takes '1024x1024'-style sizes or ratios like '16:9' (see get_model for what a model accepts); quality takes low/medium/high or 1K/2K/4K. Spends balance: estimate first for batches or expensive models, and pass max_cost_usd when the user set a budget. If the model takes longer than wait_seconds, returns a job_id to poll with get_job.
    ConnectorAPI key
  • Run Company Commenting Pipeline Generate LinkedIn comment drafts on recent posts by people who work at specific companies. USE THIS when the user names one or more companies: "comment on posts from people at Stripe" "I want to be visible to Anthropic and OpenAI engineers" "engage with anything Ramp employees posted this week" DO NOT USE for topic- or keyword-based commenting ("find me AI posts to comment on", "comment on posts about RAG"). Use run_commenting_pipeline instead, which searches the whole of LinkedIn by the user's saved comment_topics. How it differs: this tool searches by AUTHOR COMPANY and recency only, with no keyword filter, because ANDing a keyword against a single employer usually returns nothing. Topical relevance is then judged by the model over whatever those employees actually posted. As a result it may legitimately return zero drafts if nobody at those companies posted anything worth engaging with; that is a valid outcome, not an error, and you should say so plainly rather than retrying. Takes up to 5 companies per call. Companies with no matching LinkedIn page come back in unresolved_companies, so tell the user which ones failed. After calling this tool, ALWAYS display every draft to the user in full: **Post by [author_name] ([company]):** [post_text, the complete text, never truncated] **Drafted comment:** [comment_text, displayed in full] Do NOT call approve_comment_draft or schedule anything unless the user explicitly asks. Args: companies: Company names, e.g. ["Stripe", "Ramp"]. Max 5. n: How many drafts to generate (default 3, capped by the user's remaining daily cap). date_posted: "past_24h" | "past_week" | "past_month". Default "past_week". ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
    ConnectorOAuth
  • Store images in Image Hosting and get back permanent URLs on the image host — the same as the + Upload Image button on the page. Send each image as a public `url` to download, or as `base64` for a file that has no URL (a photo the seller pasted into the chat). Use the returned `url`s wherever a picture URL is taken: imageUrls of create-listing-draft, images of add-listing-images, or images: [{ src: url }] of node_listing_tool_replace_images. Why: a temporary link (presigned, chat attachment) passed straight to a draft is stored as it is and the picture disappears when the link expires. create-listing-draft copies external URLs here by itself; call this directly when you need the URLs first, or to file pictures under a SKU for node_listing_tool_set_library_images. Up to 12 images per call, 12 MB each, and 64 MB per request. Prefer `url` whenever the image has one. With `base64`, send 1 to 3 images per call and make several calls, one after another for the same `sku` (with `position` a call takes that position and the following ones, one per image, and none of them may already be used for the SKU or by another call): a chat client can stall for minutes while it assembles one large base64 request, and such a call may never reach this server; when it does not, nothing is stored and no error comes back. JPEG/PNG/GIF/WEBP/BMP/TIFF recognised by content; the call stores all or none. With `sku` and no `position` the images are appended after the SKU's existing ones. Authenticated via bearer token; requires product:write.
    ConnectorOAuth
  • Generate a new MP4 video clip (a trailer shot, cutscene or animated background) from a prompt and 1-7 reference images, saved as a new video asset in the user's Voidless library. To continue an existing video use extend_video; to make a sprite move (a walk, an attack) as game frames use animate_sprite or generate_animation_set. 15 credits per second (60 for the default 4 s), charged on every call and refunded if it fails; a run usually takes minutes and returns a job for check_generation. Returns the asset ID, the MP4 link and a thumbnail; pass the asset ID to extend_video to make it longer.
    ConnectorAPI key
  • Generate one to four images from text without source images. Omit model unless the user explicitly requests one; call beatra.models.list before model or cost comparisons. This billable call consumes Beatra credits and creates an asynchronous task. Submit exactly once, then poll with beatra.tasks.get. Reuse the same client_request_id only for an identical retry.
    ConnectorOAuth
  • Manage the signed-in user's Coloring Magic Art coloring books (up to 100 pages per book). Ops: list (summaries only: id, title, page count, layout, age, model); get (one book with pages); create (new book, up to 50 coloring pages plus optional front/back cover); update (title, layout, age, model settings, or stored status); copy (duplicate a book and its page images); delete (remove a book permanently). On get, create, copy, and update, status is the stored book record (draft, generating, completed, failed) and activity is generating when any page status is generating, otherwise idle. list does not include status or activity. Poll jobs with generate status and jobIds; use generate status with bookId for per-page readiness. create stores pageLayout (layout is an alias). To create a book and start generation together, use create with startGeneration and confirmToken from generate quote mode plan. Prefer pages add for new pages in an existing book. Image generation spends the Coloring Magic Art website token balance. Purchases happen at /pricing; this tool never takes payment.
    Connector
    Destructive
    OAuth
  • Generate an image on Nano Banana Pro, Nano Banana 2, GPT Image 2.6 or Ideogram 4.5 from a text prompt, or a set of images from several, optionally guided by reference images. Use this when the user asks for an image, picture, illustration, character, logo, sticker or background, for the frames of a story or for the scenes of a video. Send `model` only when the user's own message names a model, never by your own choice, and never switch models silently; a finished image names the model that drew it. Never use it for a YouTube thumbnail: `vidiq_generate_thumbnail` designs those. Ask for several images in ONE call, an entry of `images` each, not one call per image: they are made at once and shown together. To keep a character or product the same across images, pass a picture of it in referenceImages (referenceImageFiles for a ChatGPT upload); if the user has none, make that picture first and pass its imageUrl in referenceImages. Runs asynchronously: returns an mcpJobId for each image. Poll `vidiq_job_poll` with each id until it is "completed" to get its imageUrl, and include the links in your reply so the user can open or save the files. Cost: 22 credit(s) per image, charged as each starts; an image that fails is refunded automatically. Before starting a set, tell the user the total.
    ConnectorAPI key
  • Design a new JamFrame template from a description with the design agent and save it in the workspace (15–30 AI credits): a reusable layout (a social post, banner, carousel or video) of text, shapes and the brand's or the user's own images. It doesn't draw or generate pictures (photos, illustrations, AI art): don't use it when the user only wants a picture made. It uses the workspace's brand kit, gives the changeable layers parameter keys and returns the template with its parameters and an editor link; render it with render_template. Carousels: pages; animated videos: video true. If it takes long, the result has a jobId: call again with only that jobId to get the template.
    ConnectorOAuth