Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Back to feed
Nymbo 
posted an update Aug 25
Post
970
I built a general use MCP space ~ Fetch webpages, DuckDuckGo search, Python code execution, Kokoro TTS, Image Gen, Video Gen.

# Tools

1. Fetch webpage
2. Web search via DuckDuckGo (very concise, low excess context)
3. Python code executor
4. Kokoro-82M speech generation
5. Image Generation (use any model from HF Inference Providers)
6. Video Generation (use any model from HF Inference Providers)

The first four tools can be used without any API keys whatsoever. DDG search is free and the code execution and speech gen is done on CPU. Having a HF_READ_TOKEN in the env variables will show all tools. If there isn't a key present, The Image/Video Gen tools are hidden.

Nymbo/Tools
karenny
•
edited 5 days ago

That’s a solid setup — having Fetch, DDG search, Python execution, and Kokoro TTS all in one general use MCP space makes it super versatile without relying on too many external keys. The option to extend with HF image/video gen is a nice touch too. Reminds me of how I set up my own workflow for quick tasks. By the way, if anyone’s looking for hardware support for projects like this, I once had to figure out how to contact brother https://brother.pissedconsumer.com/customer-service.html for printer integration, and their support actually made things a lot smoother.

In this post