viomba_creative_predictionLABSCO SUMMARY
Attention scored before the media spend, not after it.
The predictions come from neural models trained on Tobii infrared gaze-fixation data, which measures fixations rather than viewability proxies — so the numbers will not line up with tools that estimate attention from viewport time. Generation and prediction sit behind the same connection, which is what lets a creative be scored, refined and scored again.
What it is
An MCP server for Viomba, bringing human attention prediction, attention-optimised creative generation and video attention analysis into an MCP client, with a Meta Marketing API bridge.
What you get
- Attention KPIs predicted for a display ad — seen percentage and view time — plus a predicted gaze heatmap
- An ad creative sliced into timed PNG screenshots for frame-level inspection
- Creative generation as a job you start, poll, fetch with full HTML, iterate on, list and cancel
- An attention-weighted site map generated across a set of domains
- Video analysed for attention, audio and video events, and an AVS sync score, with visual attention heatmaps predicted for video ads
- A one-time browser upload URL for sharing a local video file, and a poll that returns a token usable as videoUrl
- Meta credentials connected in the dashboard, then ad accounts and ad creatives listed and predictions run against the real ad library
- Usage and per-tool breakdowns for your own account, and request history
Requirements
A Viomba account. Meta features need a Meta credential connected in the Viomba dashboard before the ad-library tools will return anything. Video work goes through the upload flow rather than a direct file path.
Setup effort
Paste a URL — add the endpoint to your client
USE CASES
01
Deciding which of two banner designs to run
Predict seen percentage and view time for each, read the gaze heatmaps to see what is being skipped, and slice an animated creative into timed screenshots to find the frame that loses people.
02
Producing a creative that is built for attention
Start a generation job, poll it, fetch the result with its HTML, then refine and re-score it.
03
Working out why a video ad loses people
Analyse the video for attention and audio/video events with an AVS sync score, and predict where the eye goes frame by frame.
04
Getting a local video file into the pipeline
Request a one-time upload URL, poll until it completes, and use the returned token as the video source.
05
Scoring the ads you are already running on Meta
List the connected credentials and ad accounts, pull the live ad creatives, and predict attention against the real library.
06
Planning placements across a set of sites
Generate an attention-weighted site map across the domains you buy on, rather than assuming above-the-fold is enough.
24 tools
Listed in project docs. Your client may show a different list.
viomba_heatmap_predictionviomba_ad_slicerviomba_generate_creativeviomba_refine_creativeviomba_check_generationviomba_get_creativeviomba_list_generationsviomba_cancel_generationviomba_generate_site_mapviomba_analyze_videoviomba_focus_predictionviomba_request_uploadviomba_check_uploadviomba_list_meta_credentialsviomba_set_meta_credentialviomba_list_meta_ad_accountsviomba_list_meta_ad_creativesviomba_get_meta_creative_predictionviomba_my_usageviomba_historyviomba_request_detailviomba_tool_breakdownviomba_fetch_imageBEFORE YOU INSTALL
What to know first
Tools you get
24 tools named in the project's documentation.
Requires
A client that can reach a remote MCP server over HTTP
INSTALLATION
Connect your client
Add the endpoint to your client.
Server setup
ENDPOINT URL
https://mcp.viomba.com/mcp
