relateanything_
1 MCP server offers this tool
What it usually takes
det_threshold– in 1 of 1graph_mode– in 1 of 1image– in 1 of 1max_objects– in 1 of 1max_relations– in 1 of 1objects_text– in 1 of 1predicates_text– in 1 of 1rel_threshold– in 1 of 1show_labels– 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? |
|---|---|---|
RelateAnything co.huggingface.hugging-apps/relateanything-demo Predict open-vocabulary relations between detected regions in an image. 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: The annotated image, a markdown table of subject-predicate-object, triplets, and a one-line timing / status summary. | det_threshold,graph_mode,image,max_objects,max_relations,objects_text,predicates_text,rel_threshold,show_labels | Not stated |