If I build an agent on MuleRun, what API capabilities can I get?
Is it just LLMs, or do you also support images, video, etc.?
Official API Docs (Quickstart):
If you build an agent on MuleRun, you’re not limited to just LLM APIs.
MuleRun also supports image and video APIs, with clear input/output parameter definitions and ready-to-use cURL examples, so you can integrate multimodal capabilities directly into your agents.
I’ve also open-sourced a practical example for Nano Banana Pro Image Generation, which you can use as a reference or a starting point.
If you find it useful, feel free to leave a 
— it helps other creators discover these resources, and honestly, it keeps me motivated to open-source more examples.
Grab it here:
https://github.com/LinkAIBrain/mulerun-n8n-examples/…/NanoBananaPro-Image-Generation.json
More video API examples are coming soon as well …
1 Like