Custom die-cut stickers and emoji-style icons, one design or a set, on a plain background ready to cut out.
Scored across 5 tools
get_media_job and render_media_widget both return job status and both mutate job/credit records (marking stale jobs failed and refunding), so their boundaries overlap substantially. prepare_sticker's relationship to the project-based flow (generate_media/update_media_project) is also unclear, since 'prepared project' vs 'prepared sticker' is never reconciled.
All five names follow a clean verb_noun pattern (generate_media, get_media_job, prepare_sticker, render_media_widget, update_media_project). The object vocabulary is less consistent (media vs media_job vs media_project vs sticker vs widget), but the convention itself is predictable.
Five tools is a lean, mostly well-scoped set for a sticker/emoji generation service. However, render_media_widget depends on a prepare_media_project tool that is not in the set, so the count is effectively short of a coherent surface.
render_media_widget references a project_id 'returned by prepare_media_project', which does not exist, creating a hard dead end. There is also no clear generation step for a sticker produced by prepare_sticker, and no cancel/delete or project-listing operation.
Start the generation for a prepared project in the user's Abracadabrax account. Call this only after the user explicitly asked to generate, never on your own initiative: it spends the user's credits and sends the generation inputs to the configured model provider. Optional settings overwrite the saved project. Repeating with unchanged settings reuses a running or completed job, but a failed job can start a new paid attempt. Returns the job id and status; poll get_media_job for the output. It needs the user's Abracadabrax account: the client asks the user to sign in when it is missing. Use this only for text-to-image or text-to-video prompts. Do not use it for uploaded, attached or reference images, image editing, background removal, upscaling, virtual try-on, image-to-video or other media-to-media workflows.
Inputs: project_id (required), tab, ratio, prompt, +3 more. Returns: job, state, balance, message, +3 more
Return the status and saved output URLs of an existing image or video job owned by the linked account. A queued or running job older than ten minutes can be marked failed and its credits refunded once. This changes job and credit records; it never starts a generation.
Inputs: job_id (required). Returns: job, state, message, dashboard_url
Prepare custom stickers or emoji-style icons with Abracadabrax: one die-cut sticker or a set of 4, 6 or 9 in one image, from a subject, an optional short text and a style, on a plain background ready to cut out (the image has a solid background, not a transparent one). Returns the settings and the credits required; nothing is generated and no credits are spent. No sign-in is needed to prepare. Original designs only: do not use it for copyrighted characters, existing franchises, brand logos, trademarks or real celebrities; offer the user an original alternative instead. Text only: do not use it for uploaded, attached or reference images or videos (editing, background removal, upscaling, image-to-video); for those, point the user to the Abracadabrax workspace.
Inputs: subject (required), kind, count, style, +3 more. Returns: job, state, balance, message, +3 more
Show a saved Abracadabrax image or video project and its existing job. A queued or running job older than ten minutes can be marked failed and its credits refunded once. This changes job and credit records; it never starts a generation. Requires a project_id returned by prepare_media_project.
Inputs: project_id (required). Returns: job, state, balance, message, +3 more
Overwrite the saved widget settings (prompt, model, aspect ratio, duration) to a prepared project before generating. Changing generation settings detaches the prior job from this project without deleting that job or its media. Intended for the widget UI; no credits are spent. Use this only for text-to-image or text-to-video prompts. Do not use it for uploaded, attached or reference images, image editing, background removal, upscaling, virtual try-on, image-to-video or other media-to-media workflows.
Inputs: project_id (required), tab, ratio, prompt, +3 more. Returns: job, state, balance, message, +3 more
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Add one secure layer between your agents and this server.