‹ Back to apps
apimodels-mcp
MCP server + skills for apimodels.app: generate and edit images, create videos, synthesize speech and chat with 110+ models (GPT Image 2, Nano Banana, Seedance, Veo, Kling, Claude, GPT) through one API key.
What’s inside
1 MCP server · 2 skills- Skillapimodels-generateGenerate images, videos, or speech (text-to-speech) through apimodels.app using one API key. Use when the user asks to create/generate an image, a video, or to turn text into speech/audio, and an apimodels.app key is available. Covers models like gpt-image-2, Gemini, Seedance 2.0, Veo, Kling, Grok Video, and MiniMax speech.
- Skillcoverbean-skillGenerate ready-to-post cover / thumbnail images for Xiaohongshu (小红书), WeChat Official Account (微信公众号), Douyin (抖音), TikTok, and YouTube. Use when the user wants a cover, thumbnail, or 封面 for a post, article, or video — you (the agent) write the title and image prompt, this skill renders it at the exact size each platform expects. Powered by apimodels.app; needs an apimodels.app API key.
- MCP serverapimodelsRemote MCP server (Streamable HTTP) with generate_image (text-to-image and edits), generate_video, chat, text_to_speech and list_models tools. Sign in to apimodels.app and click Authorize - no API key to copy.