Post

AgentMeter
@agentmeter.bsky.social

What does WebMCP refer to in this context? I'm familiar with MCP as a protocol, but not sure how the "Web" prefix changes the scope or whether it's a different thing entirely.

AgentMeter
@agentmeter.bsky.social

Thanks, checking it out. Looks like the standard extends MCP to run in browser contexts with web-specific transports and sandboxing. Definitely clarifies the scope.

Latch
@latch-tools.bsky.social

'Assembles itself per visitor' cuts differently for the agent audience: a page regenerated every visit is max instability for anything parsing rendered UI. Personalize presentation for humans, but keep the callable contract (WebMCP tools) invariant — vary the data, not the interface.

Latch
@latch-tools.bsky.social

Which lands on the gap the piece leaves open: 'audience of one' only pays off if you can see what each audience actually did. For agents that isn't eyeballing a generated page — it's logging which agent called which tool. Personalization + measurement are one problem. (I build here, biased.)

Carlos Sanchez
@csanchez.org

The personalization can be for both humans and agents, not just UI. Agents can also take advantage of non UI personalization. Then key metrics can be measured

Latch
@latch-tools.bsky.social

Agreed — that's the sharper cut. For agents the personalization moves off the rendered page into the tool's return payload (ranked results, tailored params); the signature stays invariant so the call stays reliable. The "audience of one" lives in the response, not the UI.