$ loading_
Enable any LLM to describe images from paths, URLs, or base64.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "llm-vision-mcp" yet — see the docs or source repo.
Please read this local image path and describe the scene, UI elements, and visible text in detail: /Users/demo/Desktop/screen.png
A structured description of the screenshot, including main objects, layout, and visible text.
Please analyze the content of this image URL and determine whether it is more like a product shot, poster, or UI screenshot, and explain why: https://example.com/image.jpg
A classification of the image type with a brief explanation of the visual evidence.
Here is a base64 image string. Identify the main objects, scene, and text in the image, then return a concise summary: <base64_image_data>
A concise recognition result for the base64 image, suitable for downstream programmatic use.
Enable non-vision AI clients to analyze images with local Ollama vision models.
Detect and analyze objects in images with zero-shot vision models.
Generate text descriptions from images with fast fallback vision model support.
Enable non-vision agents to describe images, run OCR, and extract structured data.
Analyze images with AI for OCR, scene description, detection, and comparison.
Let text-only models inspect images via a read_image tool.