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.
TypeScript MCP server for OpenAI Images/Videos and Google GenAI (Veo) media generation, editing, and asset downloads.
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
41/100 (Fair)
53/100 (Fair)
Install path
npx · high
npx · high
Engagement
3 0 0 9
2 0 0 52
Tools
Full support for OpenAI Images API parameters for generation and editingComprehensive OpenAI Videos (Sora) job lifecycle managementGoogle GenAI Veo video generation with operation polling and downloadsSmart media fetching with resource_link or inline resource outputsStrict MCP spec compliance with typed CallToolResult outputsDebug tool for verifying MCP output shapes across clients
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.)
