awares_qwen2_5_vl_7b_crop_demo_answer_question – 1 MCP server offers this tool
What it usually takes
image– in 1 of 1question– 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? |
|---|---|---|
AwaRes Crop Retrieval co.huggingface.hugging-apps/awares-qwen2-5-vl-7b-crop-demo Answer a question about an image using AwaRes crop retrieval. The model first sees a low-resolution view of the image. If that is not enough to answer, it emits a GET_CROPS tool call naming the regions it wants; those regions are cropped from the original high-resolution image and given to the model in a second turn, which produces the 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. Returns: (final answer, high-res image with the retrieved regions outlined,, the low-resolution view the model saw on turn 1, pipeline trace) | image,question | Not stated |