ground-adapter
Calls the trained MI2 adapter and returns per-finding positive/possible/negative calls. Does not write a report — the agent produces the report using the write-report skill after grounding.
Budget
- Tool calls: 1 — exactly one
mcp_medimageinsig_adapter_classifycall per image. - Do not retry on success.
How to use
Resolve the image. If
image_pathis an http(s) URL, pass it through to the tool unchanged — do NOT download it,curlit, or turn it into a local file; the MCP server fetches URLs itself. Otherwise it is a local path: the MCP tool runs in a different working directory, so if it is not absolute, resolve it viarealpath; if it can't be resolved, ask the user.Call the adapter. Call
mcp_medimageinsig_adapter_classifywithfile_path= absolute path andhead= the caller's value if provided (otherwise omit; defaults tomlp). One call per image.Read the results. The adapter returns
{label: "positive" | "possible" | "negative"}, already bucketed using per-class operating points fit during training (Youden-J for rule-in, sens90 for rule-out). No further thresholding.Return the findings. Return the positive and possible labels. Omit negatives. Do not write a report. The agent decides what to do next.