We built a small LangGraph + MCP example showing how AI shopping agents can verify ecommerce merchants before making recommendations or transaction decisions.
The problem nobody is talking about:
There is currently no standard way for an AI agent to verify whether a merchant is safe to transact with.
Zero.
Legitimate AI transactions are already being blocked by fraud systems that cannot distinguish autonomous agents from bots.
The infrastructure layer that agentic commerce depends on does not really exist yet.
AI agents can:
-
discover products
-
browse stores
-
compare pricing
-
even complete purchases
But there is still no common machine-readable trust layer for commerce.
We built a small example using LangGraph + MCP where an agent calls a remote merchant verification server before proceeding with a commerce decision.
MCP endpoint:
https://mcp.gengeo.co/mcp
Would love feedback from others building commerce agents, MCP infrastructure, or trust systems for AI-driven transactions.