When it comes to agents, businesses today have two options: allow them or block them. We think this is too binary, and there is much room for middle ground. That's why we started a new experiment: WebMCP Commerce. https://webmcp.com/commerce For agents: a way to know where and how they can shop. For businesses: a way to set the terms of interaction for agents. Our motivation: Many businesses are happy to let agents shop, but want to keep control of checkout, or the opportunity to upsell. Others deeply care about keeping the customer relationship or want the human involved at certain points. It's pretty obvious that agents are becoming the next customers, but it's unclear how businesses should communicate their terms to agents, and vice versa? - When is a human in the loop required? - When is co-browsing allowed but headless browsing isn't? - Can a business require an agent to go through its upsell flow? Our API for agents currently exposes three things: 1) Commerce capabilities: What WebMCP tools are available, and can an agent complete a transaction? 2) Agent access: Can an agent get into the site from a local browser or a remote browser? 3) Agent policy: What are the business's actual terms for agent interaction? Please try it out and share your feedback with us! dm open. We’re also looking for more businesses that want to implement WebMCP end-to-end on their site, including checkout, and signal that they’re open for business with agents!