🤖 Make your website agent-ready with WebMCP, the new protocol for reliable, structured AI →
@ChromiumDev424K followers
11,443 views
8 Comments
Comments from the original post on X (Twitter)

@liormech
@andreban @WeAreDevs Love it! made our widget support it
2 likes

@ChromiumDev
@andreban @WeAreDevs Love this use case! 🩵
3 likes

@truechatdata
@andreban @WeAreDevs Structured AI access to the web is the right direction. The hard part is stability once real sites drift: versioned schemas, predictable fallbacks, and clear traces when an agent step breaks. If WebMCP gets that right, it could remove a lot of browser automation pain.
1 like

@ChromiumDev
@andreban @WeAreDevs Exactly. The goal with WebMCP is to move past brittle 'click-and-pray' automation by using that architectural foundation—specifically through versioned schemas and better error transparency—so you aren't stuck patching scripts every time a div changes.
1 like

@cyjkcodes
@firt @andreban @WeAreDevs Yeah I'm going to make websites for agents. humans don't seem to use the ones I make 😂I'm slightly joking
1 like

@iamsupersocks
@andreban @WeAreDevs @llmgram

@erdemserhaat
WebMCP is awesome for giving agents the tools layer. The piece I kept hitting was the agents guessing how the site actually works. Async timings, irreversible actions, and error states are all over the processes. Therefore I wanted to open-source operate.txt. One statis YAML at /operate.txt (robots.txt) style with the exact behavioral contract. Curious what Chrome-specific patterns (MFA flows, loading indicators, etc) you’d want document d? Happy to add them in v0.3. Ideas welcome

@Lovecatsandsun
@andreban @WeAreDevs 👍
