Vision Relay

Bridges Google Gemini and Alibaba Qwen vision models through CLI tools to provide image analysis capabilities from local files, URLs, or base64 data with automatic validation and configurable execution parameters.

An MCP server that provides a relay bridge to Google Gemini and Alibaba Qwen vision models through their respective CLI tools, enabling image analysis capabilities without direct API integration. Built by ah-wq using TypeScript and the MCP SDK, it accepts images from local files, URLs, or base64 data, handles automatic image preparation and validation, and executes CLI commands with configurable timeouts and parameters. The implementation features a modular provider architecture that isolates CLI-specific logic, comprehensive error handling with detailed command output, and support for various image formats with size limits and extension validation, making it useful for AI assistants that need vision capabilities through existing CLI toolchains rather than direct API access.