From ca8be6305720c42fc25725fc4dc47844e81f42fc Mon Sep 17 00:00:00 2001 From: "mark a. foltz" Date: Tue, 6 Oct 2026 21:31:55 -0700 Subject: [PATCH 1/2] Fix miscellaneous typos, cross-references, and biblio placement --- index.bs | 62 ++++++++++++++++++++++++++++---------------------------- 1 file changed, 31 insertions(+), 31 deletions(-) diff --git a/index.bs b/index.bs index da8b99a..54e62db 100644 --- a/index.bs +++ b/index.bs @@ -110,7 +110,7 @@ spec: ECMASCRIPT; urlPrefix: https://tc39.es/ecma262/

Introduction

-WebMCP API is a new JavaScript interface that allows web developers to expose their web application functionality as “tools” - JavaScript functions with natural language descriptions and structured schemas that can be invoked by [=agents=], [=browser's agents=], and [=assistive technologies=]. Web pages that use WebMCP can be thought of as Model Context Protocol [[MCP]] servers that implement tools in client-side script instead of on the backend. WebMCP enables collaborative workflows where users and agents work together within the same web interface, leveraging existing application logic while maintaining shared context and user control. +WebMCP API is a new JavaScript interface that allows web developers to expose their web application functionality as “tools” - JavaScript functions with natural language descriptions and structured schemas that can be invoked by [=agents=], [=browser's agents=], and assistive technologies. Web pages that use WebMCP can be thought of as Model Context Protocol [[MCP]] servers that implement tools in client-side script instead of on the backend. WebMCP enables collaborative workflows where users and agents work together within the same web interface, leveraging existing application logic while maintaining shared context and user control.

Terminology

@@ -120,7 +120,7 @@ TODO: Define any reusable high-level terms here that are not specific to algorit An agent is an autonomous assistant that can understand a user’s goals and take actions on the user’s behalf to achieve them. Today, these are typically implemented by large language model (LLM) based [=AI platforms=], interacting with users via text-based chat interfaces. -A browser’s agent is an [=agent=] provided by or through the browser that could be built directly into the browser or hosted by it, for example, via an extension or plug-in. +A browser agent is an [=agent=] provided by or through the browser that could be built directly into the browser or hosted by it, for example, via an extension or plug-in. An AI platform is a provider of agentic assistants such as OpenAI’s ChatGPT, Anthropic’s Claude, or Google’s Gemini. @@ -191,7 +191,7 @@ A tool definition is a [=struct=] with the following [=struct/items=] :: an [=annotations=]-or-null. : exposed origins - :: a [=list=] or [=origins=], initially [=list/empty=]. + :: a [=list=] of [=origins=], initially [=list/empty=]. A local pending tool execution is a [=struct=] with the following [=struct/items=]: @@ -802,7 +802,7 @@ The registerTool(tool, options @@ -1294,31 +1294,6 @@ The synthesize a declarative JSON Schema object algorithm, given a <{ -
-{
-  "mcp": {
-    "href": "https://modelcontextprotocol.io/specification/latest",
-    "title": "Model Context Protocol (MCP) Specification",
-    "publisher": "The Linux Foundation"
-  },
-  "json-schema": {
-    "href": "https://json-schema.org/draft/2020-12/json-schema-core.html",
-    "title": "JSON Schema: A Media Type for Describing JSON Documents",
-    "publisher": "JSON Schema"
-  },
-  "spotlighting": {
-    "href": "https://arxiv.org/abs/2403.14720",
-    "title": "Defending Against Indirect Prompt Injection Attacks With Spotlighting",
-    "publisher": "arXiv"
-  },
-  "sockpuppetting": {
-    "href": "https://arxiv.org/abs/2601.13359",
-    "title": "Sockpuppetting: Jailbreaking LLMs by Combining Prefilling with Optimization",
-    "publisher": "arXiv"
-  }
-}
-
-
The declarative execute steps are as follows: @@ -1500,7 +1475,7 @@ steps: expose the |observation|'s [=observation/tool map=] to the [=browser agent=] in whatever way it accepts. - Note: Despite the name of this API (i., Web*MCP*), this specification does not prescribe the + Note: Despite the name of this API (i.e., Web*MCP*), this specification does not prescribe the format in which tools are exposed to the [=browser agent=]. Browsers are free to distill and expose tools via Model Context Protocol, other proprietary "function calling" methods, or any other way it deems appropriate. @@ -1909,7 +1884,7 @@ page, protecting against malicious scripts or dependencies from using WebMCP API **What:** Shared evals for prompt injection attacks against WebMCP -**Threats addressed:** [[#prompt-injection]] (potentially [[#privacy-leakage-over-parameterization]] +**Threats addressed:** [[#prompt-injection]] (potentially [[#privacy-leakage-over-parameterization]]) **How:** Ensuring an interoperable basis for prompt injection defense, by requiring any implementer to protect against at least the attacks in that dataset. See [Issue #106](https://github.com/webmachinelearning/webmcp/issues/106). @@ -1952,3 +1927,28 @@ for the initial explainer, proposals, discussions, and other contributions that Also many thanks to Alex Nahas and Jason McGhee for sharing early implementation experience. Finally, thanks to the participants of the Web Machine Learning Community Group for feedback and suggestions. + +
+{
+  "mcp": {
+    "href": "https://modelcontextprotocol.io/specification/latest",
+    "title": "Model Context Protocol (MCP) Specification",
+    "publisher": "The Linux Foundation"
+  },
+  "json-schema": {
+    "href": "https://json-schema.org/draft/2020-12/json-schema-core.html",
+    "title": "JSON Schema: A Media Type for Describing JSON Documents",
+    "publisher": "JSON Schema"
+  },
+  "spotlighting": {
+    "href": "https://arxiv.org/abs/2403.14720",
+    "title": "Defending Against Indirect Prompt Injection Attacks With Spotlighting",
+    "publisher": "arXiv"
+  },
+  "sockpuppetting": {
+    "href": "https://arxiv.org/abs/2601.13359",
+    "title": "Sockpuppetting: Jailbreaking LLMs by Combining Prefilling with Optimization",
+    "publisher": "arXiv"
+  }
+}
+
From edbd1ed074a60a092d697beb0b25bad45ac4cb94 Mon Sep 17 00:00:00 2001 From: "mark a. foltz" Date: Thu, 8 Oct 2026 15:43:02 -0700 Subject: [PATCH 2/2] Move 
 to top preamble of index.bs

---
 index.bs | 49 ++++++++++++++++++++++++-------------------------
 1 file changed, 24 insertions(+), 25 deletions(-)

diff --git a/index.bs b/index.bs
index 54e62db..ce1c715 100644
--- a/index.bs
+++ b/index.bs
@@ -107,6 +107,30 @@ spec: ECMASCRIPT; urlPrefix: https://tc39.es/ecma262/
   type: dfn
     text: is an object; url: sec-object-type
+
+{
+  "mcp": {
+    "href": "https://modelcontextprotocol.io/specification/latest",
+    "title": "Model Context Protocol (MCP) Specification",
+    "publisher": "The Linux Foundation"
+  },
+  "json-schema": {
+    "href": "https://json-schema.org/draft/2020-12/json-schema-core.html",
+    "title": "JSON Schema: A Media Type for Describing JSON Documents",
+    "publisher": "JSON Schema"
+  },
+  "spotlighting": {
+    "href": "https://arxiv.org/abs/2403.14720",
+    "title": "Defending Against Indirect Prompt Injection Attacks With Spotlighting",
+    "publisher": "arXiv"
+  },
+  "sockpuppetting": {
+    "href": "https://arxiv.org/abs/2601.13359",
+    "title": "Sockpuppetting: Jailbreaking LLMs by Combining Prefilling with Optimization",
+    "publisher": "arXiv"
+  }
+}
+

Introduction

@@ -1927,28 +1951,3 @@ for the initial explainer, proposals, discussions, and other contributions that Also many thanks to Alex Nahas and Jason McGhee for sharing early implementation experience. Finally, thanks to the participants of the Web Machine Learning Community Group for feedback and suggestions. - -
-{
-  "mcp": {
-    "href": "https://modelcontextprotocol.io/specification/latest",
-    "title": "Model Context Protocol (MCP) Specification",
-    "publisher": "The Linux Foundation"
-  },
-  "json-schema": {
-    "href": "https://json-schema.org/draft/2020-12/json-schema-core.html",
-    "title": "JSON Schema: A Media Type for Describing JSON Documents",
-    "publisher": "JSON Schema"
-  },
-  "spotlighting": {
-    "href": "https://arxiv.org/abs/2403.14720",
-    "title": "Defending Against Indirect Prompt Injection Attacks With Spotlighting",
-    "publisher": "arXiv"
-  },
-  "sockpuppetting": {
-    "href": "https://arxiv.org/abs/2601.13359",
-    "title": "Sockpuppetting: Jailbreaking LLMs by Combining Prefilling with Optimization",
-    "publisher": "arXiv"
-  }
-}
-