there is a discovery layer (although, not sure if that will be the main draw), and i am vetting that discovery layer to ensure high quality of the mcp servers we have on that discovery layer.
the big value prop is only loading the mcp server or set of tools within the mcp server that is required for each prompt. this reduces wasteful context usage and clutter (and wasteful token usage).
happy to get vital-stack into the registry. when you're ready message me at support@mcp.hosting
Yaw Mode is an opinionated config overlay for Claude Code. You toggle it on and the next session inherits a curated bundle of rules, skills, and agents without touching your ~/.claude. Turn it off and you're back to vanilla Claude Code, same conversation history, nothing mutated.
The rules are mostly things I got tired of re-explaining to Claude: no speculative abstractions, validate only at system boundaries, never bypass branch protection, integration tests hit real DBs, etc. Skills and agents are bundled alongside.
Link has the full breakdown of what's inside and how the overlay keeps your conversation history safe.
Good question, the answer is simpler than the setup suggests, because for most servers mcp.hosting isn't actually in the data path.
When you install a server, your client (Claude Code, Cursor, etc.) ends up with the upstream's endpoint written into its own config and talks to it directly. No proxy, no status rewriting, x402 is whatever the upstream sends, unmodified, and your client-side payment handler runs natively.
So paid third-party MCP servers can absolutely negotiate through mcp.hosting-installed configs, and the hosted-proxy path doesn't break x402.
it's probably because they scan your codebase/directory for context reading files, searching for references, building understanding of your project. The UI versions skip that.
it does, but i’ve found it to be buggy, got hung up when that directory was not assigned (poor ux), and just crash often. i’ve found the cli much more performant.
Opens the ssh connection manager. And yes, it just uses the standard ssh, psql, mysql (etc) clients. The benefit is just clicking a button to connect. This could also be done with many different strategies. bash_aliases, ssh_config. But for a nice gui and button push UX this is what is provided. Also, if connecting through yaw there is a handy Remote Sessions gui (ctrl+shift+R) to interface with tmux or screen sessions easily.
Thanks for the reply. No github link because yes, it is closed source (although, free to use). It won't change in the future as I'm trying to model it on the Sublime Text model.
I can completely understand your concern, however, many tools these days we use are closed source (warp, cursor, sublime text, termius).
the big value prop is only loading the mcp server or set of tools within the mcp server that is required for each prompt. this reduces wasteful context usage and clutter (and wasteful token usage).
happy to get vital-stack into the registry. when you're ready message me at support@mcp.hosting
reply