Side-by-side comparison of two Model Context Protocol servers — install paths, tools, quality signals, and directory engagement so you can pick the right one for Claude, Cursor, and other MCP clients.
ComputerVision-based 🪄 sorcery of image recognition and editing tools for AI assistants.
Unified AI model API for 130+ models across 18 providers. Browse models, check pricing, create image/video/music/audio tasks, poll results, check balance, and call LLM endpoints. Free catalog tools work without an API key. npx @runapi.ai/mcp
Quality signal
39/100 (Emerging)
53/100 (Fair)
Install path
uvx · high
npx · high
Engagement
2 0 0 328
2 0 0 52
Tools
Local image processing with OpenCV and imutilsObject detection using pre-trained Ultralytics modelsOptical Character Recognition with EasyOCRDrawing tools for arrows, circles, lines, rectangles, and textImage overlay and color palette transformationsConfigurable detection confidence and processing parameters
Unified API for 130+ models across 18 providersSupports image, video, music, audio, and text-to-speech modalitiesEmbedded catalog and prompt search tools without API keyAuthenticated tools for task creation, status polling, and balance checksHosted MCP endpoint and local stdio MCP client optionsIntegration with multiple MCP-compatible hosts (Claude Code, VS Code, Cursor, etc.)
