CCAPI

Image, video, music and text generation across 100+ models through one endpoint, so an assistant that can only write text can also produce assets. Eleven tools spanning five jobs, reachable with one API key and no local process to run: - **Image** — `generate_image`, `edit_image`, `upscale_image` - **Video** — `generate_video`, optionally with a synchronised soundtrack - **Music** — `generate_music`, `generate_lyrics`, `extend_music` - **Text** — `chat_completion` across Claude, GPT, Gemini, DeepSeek, GLM, MiniMax, Kimi and Qwen - **Shared** — `list_models`, `get_balance`, `get_task` Video and music are asynchronous: those tools return a task id and the assistant polls `get_task` until the job finishes. Alongside the full endpoint there are four scoped endpoints — `/mcp/image`, `/mcp/video`, `/mcp/music`, `/mcp/text` — each carrying one capability plus the shared discovery and polling tools. Tool selection degrades as the list grows, so an assistant that only ever generates images