Image Understanding

DeepEye - 为纯文本大模型提供视觉能力的 MCP Server（图像描述 / OCR / 视觉问答）

基于 Claude API 的视觉识别 MCP server:为不支持视觉的主模型多一双眼睛。内部 http 直调视觉网关,图片放 user message 顶层 image content block,tool_result 仅返回文字描述,绕开 tool_result 内嵌 image 的网关兼容缺陷。

MCP server for AI-powered Cellpose cell segmentation via Model Context Protocol

Vision MCP Server for CatPawAI — 为纯文本模型添加视觉能力

MCP server that gives vision and image generation capabilities to text-only LLMs, running 100% locally

AlbumentationsX MCP for batch previews, compare preview runs, segmentation masks, and exports.

MCP-compliant image augmentation server using Albumentations

Give your AI agent eyes on the physical world — an MCP server for real-time DePIN edge-vision queries.

Physical camera perception, measurement, and verification tool for MCP AI agents

Universal vision tools for AI agents via Model Context Protocol

Smart hands for your AI agents - write-capable KVM+BMC+SSH MCP server: gated, verified, audited.

Plant phenotyping via PlantCV — returns traits plus the segmentation overlay they came from

DanceFlow ecosystem tools, workflows and skills. https://kieransimkin.co.uk/danceflow/

MCP server for GLM-4.6V-Flash multimodal understanding (image/video/file) via Zhipu API

MCP server for image analysis using OpenRouter

Windows 11 desktop automation and vision-LLM QA via MCP

VLM Image Understanding MCP Server - Support OpenAI protocol compatible VLMs

VL 视觉理解 MCP 服务 - 基于 tokendance 的 Qwen2.5-VL 模型

视觉理解 MCP Server - 为不支持视觉的编码模型提供图片理解能力

MCP server for vision capabilities with automatic model fallback via ModelScope API