10 actions in 7 pieces of software · ranked by words, meaning and measured trust · 565 ms
- 1Agent Commerce Layerfound in code, not yet checkedno passport yet
MCP servervoldemort9999/agent-commerce-protocol
- add_to_cart
- search_products
- 2e-commerce-agentsdemo or tutorialno passport yet
MCP servernitin27may/e-commerce-agents
- check_stock
Check live stock levels across all regional warehouses for a product.
- check_stock
- 3agent-commercefound in code, not yet checkedno passport yet
MCP servernezz0746/agent-commerce
- create_product
Add a product to a shop
- create_shop
Create a new shop via the CommerceHub
- create_product
- 4agent-commercefound in code, not yet checkedno passport yet
MCP serverKubudak90/agent-commerce
- list_catalog
Step 1 of a sale: list the products this merchant sells (id, name, price). Call this when a buyer wants to purchase.
- list_catalog
APIrecord
- create-company
Create a sync for commerce company
- create-company
MCP serverrecord
- register_agent
Register your agent profile to be discoverable by other agents in the marketplace.
- resolve_agent
Universal Agent Resolver (Agent DNS). One call returns EVERYTHING about any agent: profile, trust scores (SynmercoScore + AgentRank), Build Hub listings, protocols, payment methods, rate cards, referral code. Like DNS for AI agents.
- register_agent
- 7io.github.bch1212/agent-commerce-mcpfound in code, not yet checkedno passport yet
- get_recommendation
Given a problem statement (and optionally a stack/company size), return 1-3 best-fit products with reasoning.
- get_recommendation
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.