mcp-handler v2.2.0 Adds Experimental WebMCP Support for Browser-Based Agents
The mcp-handler library has been updated to version 2.2.0 to include experimental support for the WebMCP standard. This allows developers to expose existing MCP tools to in-browser agents via a single script tag.
Verified State Diff
Impact & Verification Analysis
Developers building AI agents or applications that integrate MCP tools directly into web browsers.
This update simplifies the integration of server-side MCP tools into browser environments by removing the requirement for complex client-side OAuth flows, significantly reducing development overhead for browser-based AI agents.
Full Fact Overview
The release of mcp-handler v2.2.0 introduces experimental support for WebMCP, a standard designed to bridge Model Context Protocol (MCP) tools with browser-based AI agents. Developers can now opt-in specific tools using the experimental_webMcp configuration object and load them into a webpage using a script tag with the ?webmcp-script parameter. This implementation proxies tool calls back to the MCP server as the authenticated user, effectively bypassing the need for client-side OAuth flows for authenticated tools.