MCP server for multimodal understanding and object grounding (bounding boxes) across images, videos, and documents, with support for multiple AI providers (Zhipu GLM-V, OpenAI GPT-4o, Anthropic Claude, or any OpenAI-compatible endpoint).
Local STDIO MCP server for object-detection annotation workflows. Manages datasets, categories, images, bounding boxes, and exports in JSONL format without modifying source images.
This MCP server enables human-in-the-loop semantic labeling by creating self-contained HTML forms for ambiguous data and securely retrieving labeled results.