Directory / ARC (arcreport.ai): can an agent reach checkout?
ARC (arcreport.ai): can an agent reach checkout?
by arcreport.ai · https://www.arcreport.ai/api/ask
Free open check: can an AI agent reach checkout on this store? Advisory; ARC stops before payment.
11 of 11 checks · 19 Oct 2026
Is ARC (arcreport.ai): can an agent reach checkout? MCP server safe?
- No hidden instructions were found in its tool descriptions.
- Its error messages showed no secrets or internal details.
- 9 of its 16 tools are labeled read-only; the others may change or send things.
- Overall it scored 68/100 on 19 Oct 2026.
A test can only see what the server shows from outside, not what it does with your data behind the scenes. Connect servers from makers you trust.
What it can do
16 tools, in the server's own words.
precheckread-onlyCheck if an AI agent can reach checkout on a store before trying.
find_agent_ready_storesread-onlyFind stores where a saved check shows an AI agent can reach checkout, for running shoes, beauty, clothing, home goods, or another product need.
can_agent_checkoutCall when you need a saved checkout-link check for any public store URL, not only Index brands.
ask_arcRead whether an AI agent can reach checkout for a brand the ARC Index already lists.
agent_commerce_adoptionread-onlyRead ARC's agent commerce adoption counts, category and commerce platform rates from saved HTTP checks, including Checkout WebMCP among measured Shopify checko…
product_data_checkread-onlyFree latest saved product data and return/shipping policy check from the store's pages and structured data.
google_checkout_readinessRead saved public Google agentic checkout readiness checks for a store.
get_agent_factsRead free ARC agent facts for a store or product with no login.
list_category_agent_factsList free ARC agent facts by category (beauty, footwear, apparel, …) with no login.
dataset_inforead-onlyLatest open ARC dataset snapshot (start with store_answers: one plain answer per store on whether AI agents can find products and get a checkout link): immutab…
protocol_matrixread-onlyRead ARC's neutral Protocol Matrix: for UCP, ACP, PAP, WebMCP, MCP and agent payment protocols, how many checked stores declare, validate, answer and transact,…
agent_leaderboardread-onlyRead ARC's open agent leaderboard: cart success over the fixed ARC-100 v1 test set for each agent path ARC measures (ARC browser shoppers A-E, the UCP path, th…
submit_leaderboard_runSubmit your agent's run against ARC-100 v1 to ARC's open leaderboard.
submit_storeAdd stores to ARC's free, open agent-commerce directory (CC-BY dataset).
store_cardread-onlyRead a public store card and saved brand claim.
validate_ucp_profileread-onlyValidate a Universal Commerce Protocol (UCP) business profile against the published UCP JSON Schema (current release) and spec rules: authority binding, https …
Test results
Safe mode: only tools labeled read-only were run. How the test works
- ✕Tools work with good inputsfail
1 failed
- ✕agent_commerce_adoption: No answer within the time limit
- –can_agent_checkout: Not run: labeled as changing data
- –ask_arc: Not run: no safety label (if you own this server, test again in owner mode)
- –google_checkout_readiness: Not run: no safety label (if you own this server, test again in owner mode)
- –get_agent_facts: Not run: no safety label (if you own this server, test again in owner mode)
- –list_category_agent_facts: Not run: no safety label (if you own this server, test again in owner mode)
- –submit_leaderboard_run: Not run: labeled as changing data
- –submit_store: Not run: labeled as changing data
- and 8 more
- !Ready for the newest MCP versionnote
1 warning
- !Uses an older MCP version (2025-11-25). It works today, but it isn't on the July 2026 version (2026-07-28) yet.
- !Every tool is describednote
4 warnings
- !find_agent_ready_stores: Inputs with no description: limit
- !product_data_check: Inputs with no description: host, url
- !submit_leaderboard_run: Inputs with no description: spec, test_set, agent, run, results
- !submit_store: Inputs with no description: url, hosts, category
- !Tools are labeled safe or dangerousnote
1 warning
- !4 of 16 tools have no safety label (read-only or dangerous): ask_arc, google_checkout_readiness, get_agent_facts, list_category_agent_facts
- !Bad inputs give a clean errornote
2 warnings
- !protocol_matrix: Accepted wrong type for "protocol" without complaining
- !agent_leaderboard: Accepted wrong type for "include_stores" without complaining
- and 7 more
- !Fast enoughnote
2 warnings
- !Average tool answer: 2.2 s
- !find_agent_ready_stores: Slowest tool: find_agent_ready_stores (6.6 s): users will notice the wait
- and 2 more
- ✓ConnectsConnected in 283 mspass
- ✓Lists its toolsFound 16 toolspass
- ✓No hidden instructionsNo hidden instructions found in tool descriptionspass
- ✓Tools work togetherpass
3 chains working
- ✓find_agent_ready_stores → precheck: precheck found what find_agent_ready_stores returned (url = "https://www.arcreport.ai/agent-checkout/gymshark.com")
- ✓find_agent_ready_stores → product_data_check: product_data_check found what find_agent_ready_stores returned (url = "https://www.arcreport.ai/agent-checkout/gymshark.com")
- ✓find_agent_ready_stores → validate_ucp_profile: validate_ucp_profile found what find_agent_ready_stores returned (url = "https://www.arcreport.ai/agent-checkout/gymshark.com")
- ✓No secrets leakedChecked 15 error messages: no secrets or internal detailspass
Test it yourself
Free and open source. Same checks, same score.
npx qamcp-cli https://www.arcreport.ai/api/askScore over time
- 13 Oct 202681
- 17 Oct 202670
- 18 Oct 202668
- 19 Oct 202668
Reviews
Coming soon: reviews from people who use ARC (arcreport.ai): can an agent reach checkout?, signed in with GitHub, one per person. Reviews never change the score.
Soon you can claim this page: re-test it from here, reply to results, and show a "Tested by QAmcp" badge.
Have a concern, or want it removed? Ask us and we'll take it off the list. How the directory works