$ loading_
Enable vision-less LLMs to understand screenshots and images through a vision proxy.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "image-recognition-mcp" yet — see the docs or source repo.
Please analyze this clipboard screenshot, extract the error code and key messages, and summarize the likely cause in English.
Returns the error text, key fields, and a concise explanation of the likely issue.
Please extract the form contents from this image and organize them into JSON by field name and value.
Outputs structured field extraction results for archiving or downstream automation.
Please inspect this app UI screenshot and describe the main sections, buttons, and current state.
Returns a clear summary of the layout and key elements to quickly understand the screen.
Analyze images with AI for OCR, scene description, detection, and comparison.
Give text-only LLMs vision support for analyzing local or online images.
Enable any LLM to describe images from paths, URLs, or base64.
Add screenshot analysis and visual Q&A to OpenCode via OpenAI-compatible vision endpoints.
Enable non-vision agents to describe images, run OCR, and extract structured data.
Generate text descriptions from images with fast fallback vision model support.