luigipederzani

afaik Claude already has a "discovery" tool for official Claude connectors, that's why a lot of companies are rushing to get on the marketplaces. I know that bc I'm the founder of https://manufact.com and we helped a ton of companies with that.

which is far from the best MCP inspector out there we hosted an online version of the mcp-use inspector which is pretty convenient: https://inspector.manufact.com/inspector

Building MCP Apps (MCP servers with Apps SDK support) is pretty painful right now.

You need to:

1. Spin up a server that returns UI components.

2. Hand-write a bunch of JSON schemas + tool wiring

So we open-sourced a high-level MCP Server SDK that basically lets you have both the MCP server and React components in the same place:

- Every React component you put in your resources/ folder is automatically built and exposed as an MCP resource + tools. No extra registration boilerplate.

- We added a useWidget hook that takes the tool args and maps them directly into your component props, so the agent effectively “knows” what data the widget needs to render. You focus on UI + logic, the SDK handles the plumbing

Docs for that flow here: https://docs.mcp-use.com/typescript/server/creating-apps-sdk...

We also shipped an MCP Inspector to make the dev loop much less painful: you can connect your MCP server, test UI components from tools (with auto-refresh), and debug how it behaves with ChatGPT/agents as you iterate. https://docs.mcp-use.com/inspector/debugging-chatgpt-apps

Both the SDK and the Inspector are open-source, and any contributions are very welcome :)

Those are the repos:

- SDK: https://github.com/mcp-use/mcp-use

- Inspector: https://github.com/mcp-use/mcp-use/tree/main/libraries/types...

One thing I’ve been thinking about: Should Code Mode live purely in the MCP client, or could there be real value in having MCP servers also expose a “code mode” execution surface themselves?

For some mcp servers, having domain-specific batch operations or embedded execution could unlock more efficient workflows.

Love the concept—TubePen is super cool! A couple of quick thoughts:

1. Make it so we can just paste the video URL instead of editing it ourselves. Way easier. 2. Let people try it without logging in first. Login walls are hurt conversions!

Seriously, though, this has so much potential. Can’t wait to see where it goes!

I totally agree with you. At orango.ai, we have implemented the auto-click feature, but before it clicks, we position the cursor on the button and display a brief loading animation, allowing the user to interrupt the process.

That’s really cool! Can I try the ai writer without signing up?