RunhuaHuang/VisionPower

VisionPower: portable image understanding MCP server for Codex, Claude Desktop, Cursor, and other agents.

This repository also configures its own agents. See what VisionPower tells them →

68Stars 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

visionpower

01

RunhuaHuang/VisionPower

Skill Claude CodeCodex

Image-understanding tool for non-multimodal (text-only) models. Uses an external vision model to read screenshot text (OCR), interpret charts and diagrams, describe photos or UI mockups, and return the results as text. Models that can understand images directly must not call this skill; use their own vision capability…

not rated 68 +1 changed 1mo ago B SkillSpector: warn 94 tokens original MIT