GLM-Vision MCP ServerImage & Video ProcessingAI & Machine LearningVEN693Alicense-qualityBmaintenanceProvides a vision tool that converts images into structured text descriptions and OCR using the free GLM-4.6V-Flash model, enabling text-only LLMs like DeepSeek to understand images. Updated 6 hours ago (2026-08-14 16:45 UTC)1MIT