You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I have verified that this discussion would not be more appropriate as an issue in a specific repository
I have searched existing discussions to avoid duplicates
Discussion Topic
Assume that we have a website that has lots of structured data, and all data is interlinked using extensive JSON-LD schemas on their pages. Some AI crawlers are using this information to build their knowledge graph.
Now, in JSON-LD you can add ConsumeActions to link to external data sources too, for example your API: you could have a page with all the articles you are selling in your shop, and then point to your API using this method:
My question is: is there a standard to connect these with a MCP server so agents know what they can do?
Is an equivalent to https://schema.org/WebAPI needed? MCPServer for example.
It would be nice if AI companies can come up with some standard for allowing this connection.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
-
Pre-submission Checklist
Discussion Topic
Assume that we have a website that has lots of structured data, and all data is interlinked using extensive JSON-LD schemas on their pages. Some AI crawlers are using this information to build their knowledge graph.
Now, in JSON-LD you can add
ConsumeActions to link to external data sources too, for example your API: you could have a page with all the articles you are selling in your shop, and then point to your API using this method:{ "@context": "https://schema.org", "@type": "CollectionPage", "name": "Leather Goods Collection", "description": "Our finest selection of leather jackets and boots.", "mainEntity": { "@type": "ItemList", "itemListElement": [ { "@type": "ListItem", "position": 1, "url": "https://www.myshop.com/products/leather-jacket", "name": "Vintage Leather Jacket" }, { "@type": "ListItem", "position": 2, "url": "https://www.myshop.com/products/leather-boots", "name": "Classic Leather Boots" } ] }, "potentialAction": [ { "@type": "ConsumeAction", "target": { "@type": "EntryPoint", "urlTemplate": "https://www.myshop.com/api/v1/collections/leather-goods/products", "contentType": "application/json" } }, { "@type": "SearchAction", "target": { "@type": "EntryPoint", "urlTemplate": "https://www.myshop.com/collections/leather-goods/search?q={search_term_string}" }, "query-input": "required name=search_term_string" } ] }My question is: is there a standard to connect these with a MCP server so agents know what they can do?
Is an equivalent to
https://schema.org/WebAPIneeded?MCPServerfor example.It would be nice if AI companies can come up with some standard for allowing this connection.
Beta Was this translation helpful? Give feedback.
All reactions