reground_qwen2_5_vl_7b_run_reground – 1 MCP server offers this tool
What it usually takes
image– in 1 of 1max_new_tokens– in 1 of 1question– in 1 of 1temperature– in 1 of 1top_p– 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? |
|---|---|---|
ReGround Qwen2.5-VL-7B co.huggingface.hugging-apps/reground-qwen2-5-vl-7b Run two-round ReGround visual reasoning on an image-question pair. Round 1: the model inspects the image, reasons, and may emit <reground>. If triggered, Round 2 re-injects the original image and asks for the final answer. Returns the full round-1 reasoning, whether reground triggered, the round-2 output (if any), and the extracted 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 | image,max_new_tokens,question,temperature,top_p | Not stated |