WebKittens
Title of the proposal
WebMCP
URL to the spec
https://webmachinelearning.github.io/webmcp/
URL to the spec's repository
https://github.com/webmachinelearning/webmcp
Issue Tracker URL
https://github.com/webmachinelearning/webmcp/issues
Explainer URL
https://github.com/webmachinelearning/webmcp/blob/main/README.md
TAG Design Review URL
Mozilla standards-positions issue URL
mozilla/standards-positions#1412
WebKit Bugzilla URL
No response
Radar URL
No response
Description
Note that #649 exists, but it lacks context, and was not published by the authors/editors of this feature, so I'm publishing this request for a position in hopes of obsoleting that old one, and providing updated links and more details here. We did the same thing for the Mozilla position.
I just want to call out the fact that WebMCP is designed for two distinct use cases:
Built-in "native" browser agents actuating a site through WebMCP tools (things like Gemini in the sidebar in Chrome, ChatGPT Atlas, Co-pilot in Edge, you get it...)
In-page agents written in JavaScript—possibly in cross-origin iframes—actuating content in another origin via its explicitly-exposed tools.
WebMCP was conceived with only the first use case in mind, and we've been adapting to support (2), the agents-in-cross-origin-iframes case, due to developer demand. This demand came from wanting to democratize tools, so that they weren't only available to the "built-in" native agent running in your browser, but are available to in-page agent widgets that might want to use those same tools. This has led to things like webmachinelearning/webmcp#179, and webmachinelearning/webmcp#188, which are still under discussion. So we'd love your feedback!
Anyways, we'd love if you reviewed the proposal with both use cases in mind.
/cc @markafoltz, @bengreenstein, @khushalsagar, @bwalderman, @johannhof, @liady