qwen_drive_1_vqa_demo_plan_scene – 2 MCP servers offer this tool
What it usually takes
num_samples– in 2 of 2scene_label– in 2 of 2show_ground_truth– in 2 of 2
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? |
|---|---|---|
Qwen-Drive-1.0-4B co.huggingface.hugging-apps/qwen-drive-1-vqa-demo Plan future ego trajectories for a bundled driving scene. The VLM first writes a one-sentence rationale for the driving decision, then the reward-optimized Planning Expert samples 5 s of future waypoints (10 Hz) from the attention cache that generation produced. Returns: A path to the summary figure, the model's reasoning text, and the, displacement error of the first sample against the recorded human drive. | num_samples,scene_label,show_ground_truth | Not stated |
Qwen-Drive-1.0-4B co.huggingface.nkasmanoff/qwen-drive-1-vqa-demo Plan future ego trajectories for a bundled driving scene. The VLM first writes a one-sentence rationale for the driving decision, then the reward-optimized Planning Expert samples 5 s of future waypoints (10 Hz) from the attention cache that generation produced. Returns: A path to the summary figure, the model's reasoning text, and the, displacement error of the first sample against the recorded human drive. | num_samples,scene_label,show_ground_truth | Not stated |