Enables analysis of local images through Kimi (Moonshot AI) vision models via the MCP protocol, supporting features like OCR and long context understanding.
Enables text-only LLMs to analyze images by bridging DeepSeek's web vision chat via MCP, supporting single/multiple image analysis, batch glob processing, and Windows screen capture for any MCP client.
Provides image understanding and OCR via GLM-4.6V-Flash, supporting URL, base64, and local file inputs. Enables AI assistants to analyze images and extract text from screenshots, documents, and more.
Enables intelligent image analysis using GLM-4.5V model, specializing in extracting and analyzing code from screenshots with support for file paths and clipboard input.