OpenVision
Enables AI assistants to analyze images using OpenRouter vision models within the Model Context Protocol ecosystem.
Acerca de
OpenVision is a Model Context Protocol (MCP) server providing image analysis capabilities powered by OpenRouter's diverse selection of vision models. It allows AI assistants within the MCP ecosystem to seamlessly analyze images from various sources, including URLs, local files, and base64-encoded data, using a simple and configurable interface. This enables a wide range of applications, from identifying objects in images to extracting data from charts and analyzing medical scans.
Características Principales
- Configurable with OpenRouter API key and default vision model
- Supports specifying temperature and max_tokens for controlling response generation
- Supports multiple image input types: URLs, local files, and base64-encoded strings
- 1 GitHub stars
- Allows custom system prompts to tailor analysis
- Integrates with Claude Desktop and Cursor
Casos de Uso
- Image analysis within AI assistants
- Object detection and identification
- Data extraction from charts and diagrams
Sponsored