Image Understanding

Understand your videos with Reka AI — search, ask questions, and extract insights.

Local OCR and on-device screen reading for MCP clients (Claude, Cursor): read any window, locate elements to click, assert what's on screen. Apple Vision, no API keys, nothing uploaded.

Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to prevent token overhead and visual hallucination loops.

Vision analysis CLI + MCP server backed by Seed 2.0 via Volcano Ark or any OpenAI-compatible endpoint

MCP server that gives Claude Code the ability to watch and understand videos — extracts frames via ffmpeg and processes audio via multiple backends

Fast screenshot capture tool for web pages - optimized for Claude Vision API

MCP server exposing Mistral AI capabilities over MCP: chat, embeddings, FIM, vision, OCR, audio, agents, moderation, classification, files, batch, workflows, sampling, prompts, resources, and Streamable HTTP.

Media intelligence analysis for audio, video, and images via the Echosaw MCP server.

Multi-model vision MCP server (GLM-4.6V, Kimi, Qwen-VL, GPT-4o) that lets text-only coding models in Claude Code see and understand images.

Multi-model consensus: 2-6 frontier LLMs answer, an independent judge synthesises one answer.

MCP bridge: lets Claude Code (or any MCP client) build and run Ui.Vision RPA macros via the browser extension

Local MCP server to analyze video, audio & images — extract frames, transcribe speech, and OCR on-screen text. Lets Claude, Cursor & VS Code watch videos, read screen recordings, and transcribe audio. No API keys, no cloud.

智谱 GLM Coding Plan 视觉理解 MCP Server，对标官方 @z_ai/mcp-server

Turn a video (bug report, screen recording) into an agent-readable set of annotated keyframes. CLI + MCP server; the only native dependency is ffmpeg.

Multi-host plugin for delegating tasks and code reviews to Google Antigravity CLI (agy). Works inside Claude Code, Codex CLI, agy itself, and as a standalone CLI.

UI structure extractor for text-only LLMs - pure Go binary, offline, CGO_ENABLED=0, MCP-native

MCP server providing multimodal vision capabilities via OpenAI-compatible APIs

An MCP-compatible email sender server that sends emails using the nodemailer library.

MCP server for integrating Omnisearch with LLMs

Vision Bridge MCP Server — 让 DeepSeek（纯文本模型）通过 MCP 调用视觉模型来「看到」图片。支持 SiliconFlow / OpenAI 兼容 API，含图片压缩功能。