mcp-openvision

mcp-openvision

3.4

If you are the rightful owner of mcp-openvision and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

MCP OpenVision is a Model Context Protocol server for image analysis using OpenRouter vision models.

MCP OpenVision is a Model Context Protocol (MCP) server that provides image analysis capabilities powered by OpenRouter vision models. It enables AI assistants to analyze images via a simple interface within the MCP ecosystem. The server supports various image input types, including base64-encoded strings, image URLs, and file paths. It can be configured with an OpenRouter API key and allows users to specify different vision models for analysis. The tool is designed to work seamlessly with platforms like Claude Desktop and Cursor, and it offers a straightforward installation process via Smithery, pip, or UV. MCP OpenVision is particularly useful for applications requiring detailed image analysis, such as identifying objects, extracting text, or analyzing visual data for specific insights.

Features

  • image_analysis: Analyze images with vision models, supporting various parameters like image input, query, system prompt, model, temperature, and max_tokens.
  • Crafting Effective Queries: Guidance on creating queries that provide context and focus for image analysis, enhancing the quality of results.
  • Image Input Types: Supports base64-encoded strings, image URLs, and file paths for image input, with options for relative paths and project_root specification.