Gives text-only LLMs vision capabilities via MCP, using vision models like Xiaomi MiMo-V2.5 to analyze images, describe content, and extract text through tools such as analyze_image, describe_image, and extract_text_from_image.
Vision MCP enables text-only agents to understand images through any OpenAI-compatible vision model. It supports local images, URLs, screenshots, documents, charts, and code errors with tools like analyze_image and understand_image.
Adds vision capabilities to text-only LLMs by integrating external vision models via MCP. It supports OCR, error screenshot reading, UI description, image comparison, and natural-language queries on images.