diff --git a/Makefile b/Makefile
new file mode 100644
index 0000000..6289c55
--- /dev/null
+++ b/Makefile
@@ -0,0 +1,23 @@
+# make Generate index.html from index.bs
+# make lint Check index.bs for warnings and errors
+# make watch Regenerate index.html after any change to index.bs
+
+LOCAL_BIKESHED := $(shell command -v bikeshed 2> /dev/null)
+
+index.html: index.bs
+ifndef LOCAL_BIKESHED
+ curl https://api.csswg.org/bikeshed/ -f -F file=@$< >$@;
+else
+ bikeshed spec
+endif
+
+ifdef LOCAL_BIKESHED
+.PHONY: lint watch
+
+lint: index.bs
+ bikeshed --print=plain --dry-run --die-when=late --line-numbers spec $<
+
+watch: index.bs
+ @echo 'Browse to file://${PWD}/index.html'
+ bikeshed --print=plain watch $<
+endif # LOCAL_BIKESHED
diff --git a/index.bs b/index.bs
index b475325..7867007 100644
--- a/index.bs
+++ b/index.bs
@@ -19,6 +19,66 @@ Indent: 2
Die On: warning
+
+
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.
@@ -70,4 +130,20 @@ interface ModelContextContainer {
"publisher": "The Linux Foundation"
}
}
-
\ No newline at end of file
+
+
+Acknowledgements
+
+Thanks to
+Brandon Walderman,
+Leo Lee,
+Andrew Nolan,
+David Bokan,
+Khushal Sagar,
+Hannah Van Opstal,
+Sushanth Rajasankar
+for the initial explainer, proposals and discussions that established the foundation for this specification.
+
+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.