droid-mcp-mlkit/io.droidmcp.mlkit

Package-level declarations

Types

class DetectFacesTool(context: Context) : McpTool

Detects faces in a local image with on-device ML Kit face detection (accurate mode, full classification). Returns bounding boxes plus expression/eye-open probabilities and head Euler angles. Does NOT identify or recognize individuals.

LabelImageTool

class LabelImageTool(context: Context) : McpTool

Classifies the contents of a local image with on-device ML Kit image labeling, returning labels above min_confidence (clamped 0.0–1.0, default 0.5).

MlKitTools

object MlKitTools

Provider for the ML Kit vision module: RecognizeTextTool, LabelImageTool, DetectFacesTool.

RecognizeTextTool

class RecognizeTextTool(context: Context) : McpTool

Extracts text from a local image with on-device ML Kit text recognition (Latin script). Returns the full recognized text plus per-line text and bounding boxes.