Image Understanding

Local visual UI cache for AI agents using perceptual hashing, CLIP, and 3D spatial grounding.

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

MCP server for integrating Omnisearch with LLMs

MCP server for Dynamsoft SDKs - Capture Vision, Barcode Reader (Mobile/Python/Web), Dynamic Web TWAIN, and Document Viewer. Provides documentation, code snippets, and API guidance.

Minimal MCP server that exposes a single kimi_read_image tool for Moonshot and Kimi Coding.

MCP server for delegating executor-only coding, vision, and command tasks to a Mimo-compatible model route.

A TypeScript MCP server that gives text-only LLMs image understanding through StepFun vision models.

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

Multi-model vision understanding MCP server. Supports GLM-4.6V (Zhipu), DeepSeek-OCR (SiliconFlow - Free), Qwen3-VL-Flash (Aliyun), and Doubao-Seed-1.6 (Volcengine)

MCP Server providing vision capabilities for LLMs via GLM-4.6V, SiliconFlow, ModelScope, OpenAI, Claude, Gemini, and Coding Plan (Kimi K2.5)

MCP Server for Google AI Studio / Gemini API integration with file processing support

MCP stdio server for image recognition via an existing vision model

MCP server for Gemini 3.1 Flash with vision, chat, and image generation capabilities

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.

Chat with 300+ LLMs via OpenRouter. Analyze and generate images, audio, and video from MCP.

MCP server for AI vision analysis via OpenRouter

MapCooking by Kaax — the first conversational GIS. MCP server that turns Claude Desktop, Claude Code, Cursor, Codex (OpenAI Codex CLI / ChatGPT app), Windsurf and any MCP-compatible agent into an agronomic operator: plant counting, replanting plans, veget

Agent-native IDE extension for Pi Coding Agent with guarded editing, search, LSP, terminals, debugging, and observability

Mistral MCP server: extract invoices and documents from text, Markdown or OCR into typed JSON.

Reliable vision MCP server with ordered fallback across ModelScope, Zhipu, and OpenAI-compatible models