$ loading_
Add private local image and video frame understanding to AI assistants.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "MiniCPM Vision MCP" yet — see the docs or source repo.
Use MiniCPM Vision MCP to analyze this local image, describe the main subjects, extract visible text, note key details, and provide a concise summary suitable for a report.
Returns an image description, OCR text extraction, key findings, and a directly usable summary.
Use MiniCPM Vision MCP to analyze this video by key frames, identify when the UI issue appears, and summarize what happens in each abnormal frame.
Outputs frame-level issue localization with timestamps, observed symptoms, and a troubleshooting summary.
I have a batch of product screenshots that cannot be uploaded to the cloud. Use MiniCPM Vision MCP to check for layout shifts, missing elements, or copy errors, and classify them by severity.
Generates locally processed visual QA results listing issue types, affected screenshots, and severity groups.
Analyze videos with frame extraction, scene detection, and metadata retrieval.
Analyze images with AI for OCR, scene description, detection, and comparison.
Detect and analyze objects in images with zero-shot vision models.
Convert images into text descriptions so text-only LLMs can answer visual queries.
Give text-only LLMs vision support for analyzing local or online images.
Enable any LLM to describe images from paths, URLs, or base64.