From 5ea4652abbafe7088eb3e8a70b0ec75f1055590a Mon Sep 17 00:00:00 2001 From: Lazizbek Ravshanov Date: Sun, 30 Aug 2026 17:52:37 -0400 Subject: [PATCH 1/2] Drop the stale native-agents note from the security questionnaire --- security-privacy-questionnaire.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/security-privacy-questionnaire.md b/security-privacy-questionnaire.md index dc0e7df..670d9b7 100644 --- a/security-privacy-questionnaire.md +++ b/security-privacy-questionnaire.md @@ -72,7 +72,7 @@ None. The feature is gated by the [`"tools"`](https://webmachinelearning.github.io/webmcp/#permissiondef-tools) permission policy. It is allowed in top-level documents and same-origin descendants by default; The permission policy can be used to allow it in cross-origin iframes and/or to disallow it in same-origin frames. -Additionally, tools can specify [`exposedTo`](https://webmachinelearning.github.io/webmcp/#dom-modelcontextregistertooloptions-exposedto) to control which origins (or `native-agents`, name to be bikeshed per [#179](https://github.com/webmachinelearning/webmcp/pull/179)) can discover them. +Additionally, tools can specify [`exposedTo`](https://webmachinelearning.github.io/webmcp/#dom-modelcontextregistertooloptions-exposedto) to control which origins can discover them. > 15. How do the features in this specification work in the context of a browser's Private Browsing or Incognito mode? From cff431b24d43c255580c2825272cf97fd5330ea8 Mon Sep 17 00:00:00 2001 From: Lazizbek Ravshanov Date: Tue, 8 Sep 2026 10:55:30 -0400 Subject: [PATCH 2/2] Point the questionnaire at the open built-in agent exposure question --- security-privacy-questionnaire.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/security-privacy-questionnaire.md b/security-privacy-questionnaire.md index 670d9b7..564e385 100644 --- a/security-privacy-questionnaire.md +++ b/security-privacy-questionnaire.md @@ -72,7 +72,7 @@ None. The feature is gated by the [`"tools"`](https://webmachinelearning.github.io/webmcp/#permissiondef-tools) permission policy. It is allowed in top-level documents and same-origin descendants by default; The permission policy can be used to allow it in cross-origin iframes and/or to disallow it in same-origin frames. -Additionally, tools can specify [`exposedTo`](https://webmachinelearning.github.io/webmcp/#dom-modelcontextregistertooloptions-exposedto) to control which origins can discover them. +Additionally, tools can specify [`exposedTo`](https://webmachinelearning.github.io/webmcp/#dom-modelcontextregistertooloptions-exposedto) to control which origins can discover them. Whether tool authors in cross origin iframes can explicitly control exposure to the browser's built in agent, for example through a `native-agent` keyword, is an open design question tracked under [Built-in agent exposure by default](https://github.com/webmachinelearning/webmcp/blob/main/README.md#built-in-agent-default-exposure) in the README. > 15. How do the features in this specification work in the context of a browser's Private Browsing or Incognito mode?