by johnexzy
Native macOS Computer Use MCP server with a live agent cursor, Apple Vision OCR, fail-closed targeting, and Accessibility actions.
npm:macos-computer-use-mcp · local package22/wkpublished 1 mo ago
Describe, classify and OCR images.
Native macOS Computer Use MCP server with a live agent cursor, Apple Vision OCR, fail-closed targeting, and Accessibility actions.
Local OCR & screen understanding for agents: read any window, find what to click. No uploads.
MCP server: 读取腾讯 CoDesign 产品原型（Axure），提取文字+流程图，生成结构化需求文档，供 AI Coding Agent 使用
Universal vision & file processor MCP server for LLMs: OCR screenshots, read code/text files, and dump zip archives as a clean sequential file-tree dump.
HERMES x402 — Solana-Native Agentic Harness. First private x402 AI agent with OODA loop, pay.sh confidential payments, Google A2A protocol, dark DeFi intelligence, and Nous Research model routing.
Claude Code MCP server for MiMo V2.5 multimodal analysis - image, video, audio
A local MCP server that gives unimodal LLMs multimodal vision — image/video recognition with multi-turn iterative analysis.
Official MCP server for Old Family Recipe — let Claude, ChatGPT, Cursor and any Model Context Protocol AI assistant save, search, and preserve family recipes (with provenance) in your cookbook. Includes OCR import of handwritten recipe cards, Sage AI chat
MiniMax MCP tools for pi - Web search and image understanding via MiniMax's Model Context Protocol
Production-grade MCP server with smart attachment auto-detection, ordered vision/OCR analysis, code context, and safe ZIP inspection.
MCP 服务器：将智谱 GLM-4V 视觉模型封装为工具（Streamable HTTP 传输），支持本地图片路径与 Data URL
An MCP-compatible email sender server that sends emails using the nodemailer library.
OpenAI gpt-image-1 MCP server with advanced image generation and editing capabilities
farsight-mcp: the MCP server exposing fetch_image, so an agent anywhere with outbound HTTPS can see an image sent via the farsight CLI.
MCP server analisis gambar (vision) via 9router — provider ag (Antigravity) + oc (OpenCode Free), fallback berantai, auto-discovery model.
Give text-only LLM agents eyes: an MCP server + CLI that describes images through a vision-language model (VLM) API.
Advanced n8n AI Agent node for Claude, OpenAI & Gemini — native PDF/image vision, Claude Max (Claude Code OAuth) support, Anthropic prompt caching, structured output with auto-fix, fallback models, and on-demand document fetch.
Peripheral Evaluation & Execution Proxy: The open-source token shield for AI coding harnesses that offloads mobile visual perception, coordinate grounding, micro-loops, and noisy log analysis to local models.
lucida-vision-mcp (eyes, not brain): a standard-MCP visual perception organ that states verifiable visual facts, never diagnoses. 通用视觉感知 MCP 服务器（眼睛不是大脑）
本地 stdio MCP 桥：动态透传远程 opencode-api 的 MCP 工具（describe_image 识图 / web_search 联网搜索），本地图片路径自动转 data URI