Wjl1224734792/visual-primitives-mcp

基于视觉原语范式的多模态视觉理解 MCP 服务器。通过任务调度机制,将场景理解和坐标定位分离为独立工具,实现「先看清 → 再定位」的精确空间推理。

2Stars on the repository
2Mods indexed here, across every type
1mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

Wjl1224734792/visual-primitives-mcp

Instructions file CodexOpenCode

A local server that gives AI tools for understanding images and finding exact locations within them. It first describes what is visible, then uses that context to locate requested objects or points.

not rated 2 1mo ago A 4,512 tokens original MIT

Wjl1224734792/visual-primitives-mcp

Instructions file

A repository instruction file for a visual-primitives MCP server based on research about using visual elements as spatial anchors. MCP is a standard way for an AI agent to connect to external tools or services.

not rated 2 1mo ago A 228 tokens original MIT