mocop
Browse · Docs · Guide · Analyze

ARC public API

API by ARC · rest

Import this document from /openapi.json or /.well-known/openapi.json. No API key. Use getStoreCard to look up one store's saved card, canAgentCheckout to read a stored checkout check (it does not fetch the store; 404 if none is stored), runAgentCheckout to fetch a fresh check, askArc to read the Index, datasetManifest for the open dataset files, and reportCheckout to record one checkout attempt. The same document is at /.well-known/openapi.json. Setup for Claude, ChatGPT, Gemini, Cursor and generic agents: /docs/connect. Any agent can ask whether a brand gets chosen and whether agents can reach checkout. The answer has two lanes: buy.agent_catalog is a live HTTP check of Shopify catalog tools and a valid UCP profile, and buy.browser is the browser cart. The catalog check is not a browser session and not any third-party agent product, and it does not change the score; browser cart results come from ARC browser shoppers A–E. agents_can_buy is true when either lane reached checkout or…

Endpoint: https://www.arcreport.ai/

Verification: observed. Source: crawl.

Capabilities (54)

  • Both MCP servers and every public tool with docs links
  • Read the stored checkout check without fetching the store
  • Run a new checkout check
  • Agent commerce adoption counts by category and platform
  • Latest saved product data from the page’s structured data
  • Find stores where an AI agent can reach checkout for running shoes or another…
  • Free agent facts for any store (Jev typed decisions)
  • Ask which stores agents can reach checkout on or read one brand
  • Read the Index or check checkout via MCP
  • MCP server card for the no-login /api/ask server
  • Agent Readiness Grades for up to 200 stores (bulk report for agencies)
  • What changed between the two most recent open-data snapshots and adoption…
  • Starter fixes for a store's failed Agent Readiness Grade audits
  • Data behind the /insights research pages as JSON or CSV
  • Open agent leaderboard on ARC-100
  • Audit state of a submission (rule arc-audit/v2)
  • Submission format schema URL and a full example body
  • Submit your agent's ARC-100 run
  • MCP server card for /api/mcp. check_store find_stores and product_data_check…
  • Method version and changelog
  • Public checkout outcomes for one store labelled by source
  • Report how far an agent got at checkout
  • Saved pre-checkout answer for a product or store URL
  • Saved pre-checkout answers for up to 100 stores
  • How many pre-checkout answers ARC has served
About · Contact · Privacy