nvidia_cosmos3_edge_reason – 1 MCP server offers this tool
What it usually takes
enable_thinking– in 1 of 1image– in 1 of 1max_new_tokens– in 1 of 1prompt– in 1 of 1temperature– in 1 of 1top_p– in 1 of 1video– 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? |
|---|---|---|
Cosmos3-Edge Physical AI Reasoning co.huggingface.hugging-apps/nvidia-cosmos3-edge Reason about a physical scene with NVIDIA Cosmos3-Edge. Takes a text instruction plus an optional image or video and streams back a text answer. With thinking enabled, the model first emits a <think> chain of reasoning, then a final answer. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool | enable_thinking,image,max_new_tokens,prompt,temperature,top_p,video | Not stated |