About Orange Box
Orange Box is an MCP server published by MalcolmXavier7 in the Content category: mCP server for fal.ai's generative media API — 600+ image, video, audio & text models.
The repository has 1 stars and 0 forks, with the last commit 2 months ago. Recent commit activity is the strongest signal that reported issues will get attention.
Install
git clone https://github.com/MalcolmXavier7/orange-boxThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (20)
fal_budgetDaily/monthly spend caps, **checked before each generation** — stops the next expensive render instead of explaining it afterwards
Parameters not published.
fal_cancel_requestCancel a request that's still `IN_QUEUE`
Parameters not published.
fal_check_statusPoll a queued request's status (`IN_QUEUE` / `IN_PROGRESS` / `COMPLETED`)
Parameters not published.
fal_encode_file_as_data_uriLocally base64-encode a file so it can be passed as an `image_url`-style argument without a separate upload step
Parameters not published.
fal_generate_and_saveRun a model, download all media with versioned filenames, and log the run — one call
Parameters not published.
fal_generate_audioVoiceover, music, or sound effects by *kind* — the router picks the model, runs it, and saves the file
Parameters not published.
fal_get_model_schemaFetch a model's OpenAPI schema — exact input fields, types, defaults
Parameters not published.
fal_get_resultFetch the final output of a completed queued request
Parameters not published.
fal_get_run_logLocal spend dashboard: estimated spend, runs by model, failure rate, recent entries (today/week/month/all)
Parameters not published.
fal_list_modelsSearch/browse the fal.ai model catalog to find the right model id
Parameters not published.
Show all 20 tools
fal_match_referenceScan a reference image with a cheap vision model and get the best model + prompt to reproduce that look as a **still or a video shot**; optional cost-gated compare mode generates candidates on the top 2 models
Parameters not published.
fal_pick_winnerRecord which model won/failed a comparison — future recommendations reorder around your verdicts (learning loop)
Parameters not published.
fal_project_openOpen or create a shot project (a spot, a sequence, a board) and make it active
Parameters not published.
fal_run_modelRun a model synchronously and block for the result (best for fast models, <2 min)
Parameters not published.
fal_save_resultDownload result media URLs to a local directory with versioned filenames (`_v1`, `_v2`, … never overwrites)
Parameters not published.
fal_shot_listList every shot, and with `refresh=true` poll fal for whatever is **still rendering**
Parameters not published.
fal_shot_setCreate or update one shot — description, model, request id, status, notes, files
Parameters not published.
fal_submit_requestSubmit a job to the async queue and get a `request_id` back immediately (best for video/training)
Parameters not published.
fal_upload_fileUpload a local file to fal.ai CDN storage and get a hosted URL (preferred over data URIs for anything big)
Parameters not published.
fal_wait_for_resultSubmit a slow job, poll to completion with backoff, and download the media — **one call** instead of submit → status → status → result → save
Parameters not published.
Ask AI
Ask AI about Orange Box
Powered by Claude · Grounded in docs
Security checks
6 checks have not been run yet.