sam3_video_visual_inference – 1 MCP server offers this tool
What it usually takes
drop_masks– in 1 of 1every_x– in 1 of 1input_video– in 1 of 1masks– in 1 of 1ref_frame_idx– in 1 of 1sample_fps– in 1 of 1timeout_duration– in 1 of 1video_load_device– in 1 of 1
No server marks it as only reading: treat it as able to change data.
From each publisher's own tool list. We never call a tool.
Servers
| Server | Inputs | Read-only? |
|---|---|---|
SAM3 co.huggingface.gf-john/sam3 SAM3 video segmentation with visual prompts: track objects through a video given their segmentation masks on a reference frame; a drop-in match for SAM2's process_video. Seed the objects to track by supplying their masks on the reference frame (ref_frame_idx); SAM3 then propagates each object forward -- and, when ref_frame_idx is nonzero, also backward -- through every frame. Unlike video_inference (which finds objects from a text prompt), this tool tracks exactly the objects whose masks you provide, e.g. masks obtained from image_visual_inference or image_text_inference on the reference frame. The video can optionally be downsampled before tracking with sample_fps or every_x; all frame indices (the "frame" field of every detection AND the ref_frame_idx input) are 0-based positions in the SAMPLED frame sequence, NOT original video frame numbers, so with every_x=5 the detection "frame": 2 corresponds to original frame 10. Returns a JSON list of per-frame detections, one entry per tracke | drop_masks,every_x,input_video,masks,ref_frame_idx,sample_fps,timeout_duration,video_load_device | Not stated |