Andre Cipriani Bandarra & François Beaufort
WebMCP - Making Agents a First-Class Citizen of the Web - Andre Cipriani Bandarra & François Beaufort
#1about 2 minutes
The challenge of AI agents on the human-centric web
Current AI agents must simulate human behavior to use websites, which is inefficient and gives bots too much power.
#2about 2 minutes
Introducing WebMCP for programmatic agent access
WebMCP is a protocol that allows websites to expose functions, or tools, for agents to use programmatically via declarative or imperative APIs.
#3about 3 minutes
A demonstration of the imperative API using JavaScript
A live demo shows how to enable WebMCP in Chrome and register a JavaScript function as a tool that an agent can discover and execute.
#4about 2 minutes
A demonstration of the declarative API with HTML attributes
A restaurant booking form is enhanced with `tool-name` and `tool-description` attributes to make it usable by agents without JavaScript.
#5about 2 minutes
Using the developer extension to debug and test tools
The Model Context Tool Inspector extension allows developers to see registered tools, call them manually, and test them with a simple LLM.
#6about 2 minutes
How WebMCP improves speed, reliability, and token usage
By providing a direct API, WebMCP makes agent interactions faster, more reliable, and more efficient by reducing token consumption from parsing HTML.
#7about 3 minutes
The early preview status and call for developer feedback
WebMCP is in an early preview in Chrome Canary, and the team is actively seeking developer feedback on use cases and API design.
#8about 5 minutes
Community engagement and the open-source developer extension
The developer extension is available on the Chrome Web Store and is open-source on GitHub for community contributions and feedback.
#9about 6 minutes
The future of the agentic web and semantic markup
Adopting standards like WebMCP encourages better semantic markup, making the web more efficient for both agents and crawlers, similar to SEO.
#10about 4 minutes
How to contribute to the W3C community group specification
The WebMCP specification is being developed as a draft report in a W3C community group, which is open for public participation and feedback on GitHub.
Related jobs
Jobs that call for the skills explored in this talk.
Patronus Group
Berlin, Germany
Intermediate
Product Management
REST
+2
Technoly GmbH
Berlin, Germany
Senior
JavaScript
Angular
+1
Wilken GmbH
Ulm, Germany
Senior
Amazon Web Services (AWS)
Kubernetes
+1
Matching moments
01:26 MIN
Using the Model Context Protocol for AI agent integration
How to scrape modern websites to feed AI agents
01:43 MIN
Exploring AI agents and the Model Context Protocol
Java Meets AI: Empowering Spring Developers to Build Intelligent Apps
04:04 MIN
How Model Context Protocol standardizes tool integration
From A2A to MCP: How AI’s “Brains” are Connecting to “Arms and Legs”
02:14 MIN
How MCP enables modern AI agent mashups
MCP Mashups: How AI Agents are Reviving the Programmable Web
02:31 MIN
Introducing the Model Context Protocol for tool integration
Beyond Prompting: Building Scalable AI with Multi-Agent Systems and MCP
01:42 MIN
Standardizing agent-tool communication with MCP
Build a Multi-Agent Role-Playing Game Master with Strands Agents
01:26 MIN
Introducing key protocols for agent communication
Building AI Applications with LangChain and Node.js
06:33 MIN
The security challenges of building AI browser agents
AI in the Open and in Browsers - Tarek Ziadé
Featured Partners
Related Videos
MCP Mashups: How AI Agents are Reviving the Programmable Web
Angie Jones
Exploring the Future of Web AI with Google
Thomas Steiner
WeAreDevelopers LIVE – AI vs the Web & AI in Browsers
Chris Heilmann, Daniel Cranney & Raymond Camden
From A2A to MCP: How AI’s “Brains” are Connecting to “Arms and Legs”
Brad Axen
How to scrape modern websites to feed AI agents
Jan Curn
AI in the Open and in Browsers - Tarek Ziadé
Tarek Ziadé
Generate AI in the Browser with Chrome AI - Raymond Camden
Raymond Camden
Beyond Prompting: Building Scalable AI with Multi-Agent Systems and MCP
Viktoria Semaan
Related Articles
View all articles



From learning to earning
Jobs that call for the skills explored in this talk.

&why GmbH
Berlin, Germany
€50-70K
Junior
Intermediate
Senior
React
Next.js
TypeScript

SMG Swiss Marketplace Group
Canton de Valbonne, France
Senior



autonomous-teaming
München, Germany
Remote
API
React
Python
TypeScript



Dr. Meyer & Meyer-Peteaux New Media Company GmbH & Co. KG
Rastede, Germany
API
CSS
GIT
SASS
Scrum
+7

dmrz
Düsseldorf, Germany
API
.NET
DevOps
Python
Microservices
+2