mcp-image-extractor and image-reader-mcp
About mcp-image-extractor
ifmelate/mcp-image-extractor
MCP server which allow LLM in agent mode to analyze image whenever it needs
This tool helps AI assistants, like those used by developers, analyze images by providing them in a format they can understand. It takes images from local files, URLs, or existing base64 data, converts them to an optimized base64 format, and then feeds them to an AI for analysis. This is primarily used by developers who are building or configuring AI agents.
About image-reader-mcp
moiri-gamboni/image-reader-mcp
An MCP (Model Context Protocol) server (using FastMCP) to provide tools for listing local image files and reading their content. Designed for LLM agent integration.
Exposes two core tools via FastMCP: `list_images` for directory scanning across seven image formats (.jpg, .png, .gif, .bmp, .webp, .svg, .jpeg) and `read_image` which returns base64-encoded content using FastMCP's `imageContent` helper for LLM vision processing. Designed for client-side MCP integration (e.g., Cursor, Claude) via stdio transport with JSON-RPC configuration, enabling vision-capable AI agents to access and analyze local image files.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work