WebMCP

### WebKittens @mwyrzykowski @marcoscaceres ### 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 _No response_ ### Mozilla standards-positions issue URL https://github.com/mozilla/standards-positions/issues/1412 ### WebKit Bugzilla URL _No response_ ### Radar URL _No response_ ### Description Note that https://github.com/WebKit/standards-positions/issues/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](https://github.com/mozilla/standards-positions/issues/1391#issuecomment-4373989857). ---- 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](https://webmachinelearning.github.io/webmcp/#dom-modelcontextregistertooloptions-exposedto) 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 https://github.com/webmachinelearning/webmcp/pull/179, and https://github.com/webmachinelearning/webmcp/issues/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