by dx_
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。
npm:reasonix-vision-mcp · local package118/wkpublished 4 mo ago
Describe, classify and OCR images.
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。
MCP server for browser and desktop automation: OCR, image recognition, real mouse and keyboard input
Human MCP: Bringing Human Capabilities to Coding Agents
Industrial cleanroom website recreation engine — headless multi-page crawl, vision-driven React synthesis, and 3-tier verification
49 pay-per-use APIs for AI agents via x402. AI, crypto, DeFi, blockchain, weather, search, security.
Watch video and live sessions, keep timestamped evidence, and verify an agent's own work.
Fast screenshot capture tool for web pages - optimized for Claude Vision API
MCP server for OpenRouter providing text chat and image analysis tools
Give text-only LLM coding agents (DeepSeek V4 Flash/Pro, Qwen, Kimi) vision via any multimodal model. One analyze_image tool — paste or drag in one or many images, analyzed in a single call, scoped to the current session. Works with Claude Code, opencode,
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.
VisionPower: a portable image understanding MCP server for Codex, Claude Desktop, Cursor, and other agents.
An MCP server that gives non-vision LLMs the ability to analyze images via any OpenAI-compatible vision API
Multi-model consensus: 2-6 frontier LLMs answer, an independent judge synthesises one answer.
MCP server for AI vision analysis via OpenRouter
Turn a screen recording into agent-readable annotated keyframes. MCP server + CLI on ffmpeg.
MCP server that uploads local media to EnriProxy and returns server-side analysis (resumable uploads).
MCP server for secure, bounded OpenAI-compatible vision analysis
MCP server for Ultralytics Platform projects, datasets, training, prediction, exports, and models.
Shrink images to a token budget for vision LLM agents and pipelines. Not for chat-pasted images.
MCP server and CLI tool for web design critique using GitHub Copilot vision