agenticplug.ai - Agentic Commerce Optimization company
Live index · Updated October 5, 2026

Agentic Web Readiness Index

Which companies in AI search and agentic commerce are actually agent-ready? Every one scored against the same 32 checks by Agent Ready Report, our agent-readiness scanner, refreshed weekly.

Organizations benchmarked
53
Median readiness score
4 / 16
Median AI search foundations
10 / 11
Pass any commerce protocol
0 / 53

Scan your own site

Free · No email

Agent Ready Report checks 35 things AI agents and AI search look for, and explains each one in plain English.

No email, no account. Checks are site-wide, so a domain is enough, and a scan takes up to a minute.

Rankings

Not one of the 53 organizations benchmarked here passes a single agentic commerce protocol. ACP, UCP, AP2, x402 and MPP are all at zero, including among the companies building them.

Ranked by
The number of scored checks passing: the 16 readiness checks and the 11 AI search foundations, 27 in all. No grade or level: the tally is the result.
Who’s listed
Any organization whose own site positions it in agentic search and agentic commerce, whether they build the protocols, run the platforms, sell readiness as a service, or measure it. Companies can also ask to be considered. Nobody is dropped for scoring badly, and listing can never be bought.
Three scores
16 readiness checks, 11 AI search foundations and 5 agentic commerce protocols, side by side. Commerce is scored for every row and kept out of the rank. The 27-check ranked total is on every row.
Index operator · not ranked

agenticplug.ai

agenticplug.ai · scanned 2026-10-05

16 / 16 readiness11 / 11 foundations0 / 5 commerce

We score 16 of 16 on readiness, 11 of 11 on the AI search foundations and 0 of 5 on agentic commerce (27 of 27 on the ranked checks), from the same scan as everyone below. We publish this index, so we do not rank ourselves in it.

Our per-check breakdown

Missing · 5

Ranked on readiness and AI search foundations together: 27 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

Organizations ranked · 52 organizations, full check set

1Vercelvercel.com · Infrastructure11 / 16 readiness11 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 22 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

2Cloudflarecloudflare.com · Infrastructure9 / 16 readiness10 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 19 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

2Model Context Protocolmodelcontextprotocol.io · Standards body10 / 16 readiness9 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 19 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

4Webflowwebflow.com · Infrastructure7 / 16 readiness11 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 18 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

5LocalMightylocalmighty.com · AI search agency6 / 16 readiness11 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 17 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

6DeltaV Digitaldeltavdigital.com · AI search agency5 / 16 readiness11 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 16 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

6Fuel Onlinefuelonline.com · AI search agency5 / 16 readiness11 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 16 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

6Single Grainsinglegrain.com · AI search agency7 / 16 readiness9 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 16 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

9Azomaazoma.ai · Agentic commerce software4 / 16 readiness11 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 15 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

9Elogic Commerceelogic.co · Agentic commerce software4 / 16 readiness11 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 15 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

9NoGoodnogood.io · AI search agency5 / 16 readiness10 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 15 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

9Omniscient Digitalbeomniscient.com · AI search agency5 / 16 readiness10 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 15 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

9OuterBoxouterboxdesign.com · AI search agency5 / 16 readiness10 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 15 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

9PayPalpaypal.com · Payments4 / 16 readiness11 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 15 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

9ShopAgenticshopagentic.com · Agentic commerce software4 / 16 readiness11 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 15 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

9Stripestripe.com · Payments4 / 16 readiness11 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 15 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

9Tinuititinuiti.com · AI search agency4 / 16 readiness11 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 15 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

181Digital Agency1digitalagency.com · AI search agency3 / 16 readiness11 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 14 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

18Avenue Zavenuez.com · AI search agency5 / 16 readiness9 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 14 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

18Conductorconductor.com · AI visibility platform3 / 16 readiness11 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 14 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

18Enaiblexenaiblex.com · Agentic commerce software5 / 16 readiness9 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 14 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

18First Page Sagefirstpagesage.com · AI search agency5 / 16 readiness9 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 14 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

18iPullRankipullrank.com · AI search agency4 / 16 readiness10 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 14 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

18MaximusLabs AImaximuslabs.ai · AI search agency3 / 16 readiness11 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 14 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

18Mimvimimvi.com · AI search agency5 / 16 readiness9 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 14 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

18Rankettaranketta.com · AI search agency3 / 16 readiness11 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 14 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

18SCALZ.AIscalz.ai · AI search agency3 / 16 readiness11 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 14 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

18Searchabletrysearchable.com · AI visibility platform3 / 16 readiness11 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 14 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

18Semrushsemrush.com · AI visibility platform3 / 16 readiness11 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 14 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

18Shopifyshopify.com · Commerce platform3 / 16 readiness11 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 14 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

18Siege Mediasiegemedia.com · AI search agency3 / 16 readiness11 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 14 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

18Stratediastratedia.com · AI search agency5 / 16 readiness9 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 14 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

18Sure Oaksureoak.com · AI search agency4 / 16 readiness10 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 14 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

18Syndigosyndigo.com · Agentic commerce software4 / 16 readiness10 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 14 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

35Accenture Songaccenture.com · AI search agency3 / 16 readiness10 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 13 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

35Adyenadyen.com · Payments2 / 16 readiness11 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 13 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

35ETOS Consultingetosconsulting.com · AI search agency4 / 16 readiness9 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 13 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

35Eyeful Mediaeyefulmedia.com · AI search agency3 / 16 readiness10 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 13 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

35Seer Interactiveseerinteractive.com · AI search agency3 / 16 readiness10 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 13 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

35SEO.comseo.com · AI search agency3 / 16 readiness10 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 13 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

41Animalzanimalz.co · AI search agency4 / 16 readiness8 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 12 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

41Anthropicanthropic.com · AI platform3 / 16 readiness9 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 12 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

41Block (Square)squareup.com · Payments3 / 16 readiness9 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 12 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

41IMPACT Commerceimpactcommerce.com · Agentic commerce software4 / 16 readiness8 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 12 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

41Klarnaklarna.com · Payments3 / 16 readiness9 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 12 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

41Microsoftmicrosoft.com · AI platform3 / 16 readiness9 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 12 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

41Peec AIpeec.ai · AI visibility platform4 / 16 readiness8 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 12 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

41Profoundtryprofound.com · AI visibility platform3 / 16 readiness9 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 12 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

41ReFiBuyrefibuy.ai · Agentic commerce software3 / 16 readiness9 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 12 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

41Salesforcesalesforce.com · Commerce platform3 / 16 readiness9 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 12 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

51Scrunchscrunch.com · AI visibility platform3 / 16 readiness7 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 10 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

52Envive AIenvive.ai · Agentic commerce software1 / 16 readiness8 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 9 of 27 checks, the full set of 27.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

Incomplete scans · 1 organization, not ranked · Couldn't check · 5 organizations · Blocked the scanner · 1 organization

The scanner could not reach a verdict on every ranked check for these sites, so each is scored out of fewer than 27. Their results are published in full, but a score out of a smaller base is not comparable to one measured on the whole set, so they are listed here rather than numbered alongside it. Each row states which checks were skipped and, where we know it, why. Sites marked couldn't check gave the scanner no answer this run, after a second attempt, most often because bot protection does not yet recognise it: they carry no score, which is not a score of zero, and it says nothing about whether they let AI agents in. Sites marked blocked refused the scanner outright, on both attempts. They carry no score either: a refusal is reported as a refusal, never as a zero.

Amazonamazon.com · Commerce platformPartial scan · 1 of 27 not evaluated2 / 15 readiness4 / 11 foundations0 / 5 commerce

Ranked on readiness and AI search foundations together: 6 of 26 checks evaluated, out of a full set of 27.

Not evaluated: Sitemap. The scanner could not run this check, so it is excluded from the score rather than counted as a failure. That leaves this row scored out of 26 rather than 27, so its total is not directly comparable to a row measured on the full set. Why: one other probe did not complete, and we do not publish a guess at why.

No agentic commerce protocol is implemented. These apply to sites that transact through agents. The index scores them for every organization, whether or not its site sells online.

Scanned 2026-10-05 · methodology 1.4.0

Coinbasecoinbase.com · PaymentsCouldn't check · bot protectionTried 2026-10-05, twice. No score, not a zero.
Googlegoogle.com · AI platformCouldn't check · rate-limitedTried 2026-10-05, twice. No score, not a zero.
OpenAIopenai.com · AI platformCouldn't check · bot protectionTried 2026-10-05, twice. No score, not a zero.
Perplexityperplexity.ai · AI platformCouldn't check · bot protectionTried 2026-10-05, twice. No score, not a zero.
WebFXwebfx.com · AI search agencyCouldn't check · rate-limitedTried 2026-10-05, twice. No score, not a zero.
Mastercardmastercard.com · PaymentsBlocks identified agentsRefused the scanner (HTTP 403) on 2026-10-05, twice. No score, not a zero.

How the scan works

The scan at the top of this page is Agent Ready Report, agenticplug.ai's own scanner, free and without an account. It checks 35 things in three groups: agent readiness, the AI search foundations that decide whether AI search can read and cite a site today, and, for sites that sell online, agentic commerce.

What it returns

One scan, taking a single address. Checks are site-wide, so a domain is enough. You get:

  • A tally for each group, never a grade or a level.
  • Every missing check, with what the site showed, what the check is in plain English and why it matters.
  • Every passing check.
  • Checks the scanner could not get an answer on, reported as “couldn't check” and never counted against you.
  • Agentic commerce scored only when the site sells online, and new standards labelled as emerging.

A site that turns the scanner away gets “couldn't check” on everything that could not run, with a note saying so, never a score of zero: the same rule the table applies to blocked sites.

Why your report can differ from a row

The rankings above are scored by Agent Ready Report too, in a weekly run, so anyone can re-run any row with the same scanner, free: the form above, or the connector in an AI assistant. A site can change between that weekly run and your report, so a listed company's report can differ from its row. Use the table to see where the field stands, and the report to see what to fix on your own site.

Scans from this page are rate limited per visitor. Repeat scans of the same site are answered from a cache, so a result can be up to about 25 minutes old, and each one says when it was scanned.

In Claude, ChatGPT or another assistant

Agent Ready Report is also an MCP connector. Add it to your assistant and ask about any public website: it runs the same scan as the form above, and your assistant can walk you through each finding. No sign-in.

Endpoint
https://scan.agenticplug.ai/mcp
Setup
Step-by-step for each assistant

For agents: software calling over HTTP should connect to the endpoint above (Streamable HTTP, no sign-in). An agent reading this page in a browser that supports WebMCP will also find the same scan registered on document.modelContext. Running a scan does not add you to this index: listing stays editorial, and the request form is below.

What we measure

Every organization in this index is put through the same 32 checks, in six groups: discoverability, content accessibility, bot access control, API and agent interfaces, AI search foundations, and agentic commerce. Each one asks whether a single specific artifact is published in the form its standard defines: a sitemap, a Link response header, an MCP server card, a signed DNS record, a priced HTTP 402 response. A check passes or it does not: there is no partial credit, no weighting, and no judgement about the company behind the site. The 16 readiness checks, the 11 AI search foundations and the 5 agentic commerce protocols are scored and shown separately. Rows are ranked on the first two together, 27 checks; commerce is kept apart because it is not the same measurement: readiness is a spread, commerce is a floor nobody has yet stepped off. Where the scanner could not reach a verdict on a check, that check is dropped from the site's total as well as its score, which is why some rows are scored out of fewer than 27 and are listed apart from the ranking rather than inside it.

Discoverability

4 scored

Can an agent find the site, and the endpoints it offers, without guessing at URLs?

  • robots.txtRFC 9309

    /robots.txt answering HTTP 200 with a robots.txt file, not an HTML page, carrying at least one User-agent rule group.

    Tells crawlers what they may fetch, and points them at the sitemap.

    52 of 53 benchmarked organizations pass this check.

  • Sitemapsitemaps.org

    A sitemaps.org XML document (<urlset> or <sitemapindex>) at a Sitemap: URL named in robots.txt or at /sitemap.xml.

    Lists every URL worth crawling, so nothing depends on link discovery.

    52 of 53 benchmarked organizations pass this check.

  • Link headersRFC 8288 · RFC 9727

    A Link: response header on the homepage with at least one of rel api-catalog, service-desc, service-doc or describedby, or rel alternate with a JSON type.

    Advertises the API catalog and docs in the HTTP response itself, before the page is parsed.

    19 of 53 benchmarked organizations pass this check.

  • DNS-AID + DNSSECRFC 9460 · DNS-AID draft

    At least one ServiceMode SVCB/HTTPS record under _index._agents, _a2a._agents or _mcp._agents.<domain>, resolving with DNSSEC validation.

    Publishes agent endpoints in DNS, signed, so they can be found without fetching the site.

    0 of 53 benchmarked organizations pass this check.

Content accessibility

1 scored

Can an agent read the content without rendering and parsing a page built for human eyes?

  • Markdown negotiationHTTP content negotiation

    Markdown returned for the homepage when it is requested with Accept: text/markdown: a text/markdown Content-Type and a Markdown body, not HTML.

    Serves clean Markdown to agents that ask for it, instead of making them parse HTML.

    10 of 53 benchmarked organizations pass this check.

Bot access control

2 scored · 1 informational

Has the site stated, in machine-readable form, which agents may do what with its content?

  • AI crawler rulesRFC 9309

    robots.txt rules that apply to AI crawlers: a User-agent group naming one (GPTBot, OAI-SearchBot, ClaudeBot, PerplexityBot, Google-Extended and the rest), or a User-agent: * group with at least one Allow or Disallow rule.

    States what AI crawlers may do, by name or through rules that apply to every crawler.

    51 of 53 benchmarked organizations pass this check.

  • Content-Signalcontentsignals.org

    At least one Content-Signal: directive in robots.txt setting search, ai-input or ai-train to yes or no.

    Declares how content may be used: search, ai-input and ai-train, each set separately.

    6 of 53 benchmarked organizations pass this check.

  • Web Bot AuthHTTP Message Signatures

    A JWKS with at least one public key at /.well-known/http-message-signatures-directory, so the site's own bots can sign their requests.

    Lets a site tell a real agent from something wearing its user agent string.

    Reported by the scanner but never scored, so it is excluded from every tally on this page.

API, auth and agent interfaces

9 scored

Can an agent call the site rather than only read it, and authenticate when it has to?

  • API catalogRFC 9727 · RFC 9264

    /.well-known/api-catalog answering with JSON: a linkset array (RFC 9264) with at least one entry naming an anchor.

    A single document listing every API the site offers.

    1 of 53 benchmarked organizations pass this check.

  • OAuth discoveryRFC 8414 · OIDC Discovery

    /.well-known/oauth-authorization-server (or /.well-known/openid-configuration) answering with JSON that carries an issuer URL and a token_endpoint.

    Tells an agent where and how to authenticate.

    15 of 53 benchmarked organizations pass this check.

  • Protected resource metadataRFC 9728 §3.3

    /.well-known/oauth-protected-resource answering with JSON whose resource is identical to the site's own origin.

    Says which authorization server guards a given resource.

    0 of 53 benchmarked organizations pass this check.

  • auth.mdworkos.com/auth.md

    /auth.md in Markdown with an H1 naming auth.md. Where the site publishes OAuth metadata, that metadata must also carry an agent_auth block naming one complete registration method; otherwise auth.md itself must document how an agent registers and uses its credentials.

    Plain-language instructions for an agent on obtaining credentials.

    0 of 53 benchmarked organizations pass this check.

  • MCP server cardSEP-2127 (draft) · MCP Registry

    /.well-known/mcp/server-card.json (or a server card listed in /.well-known/ai-catalog.json) carrying serverInfo.name, or a name with remotes or packages in the MCP Registry server.json format.

    Declares an MCP server that agents can actually call.

    3 of 53 benchmarked organizations pass this check.

  • A2A agent cardA2A protocol

    /.well-known/agent-card.json with a name and a service URL (supportedInterfaces or url).

    Declares an agent that other agents can talk to.

    1 of 53 benchmarked organizations pass this check.

  • Agent Skills indexAgent Skills Discovery v0.2.0

    /.well-known/agent-skills/index.json (or the older /.well-known/skills/index.json) listing at least one named skill.

    Publishes executable skills an agent can load and run.

    5 of 53 benchmarked organizations pass this check.

  • WebMCPW3C CG draft

    Tools the homepage registers through document.modelContext (navigator.modelContext in older Chrome builds), or declarative form tools, found by loading the page in a real browser.

    Exposes in-page tools to agents through document.modelContext.

    4 of 53 benchmarked organizations pass this check.

  • ARD / ai-catalogARD v0.9 · ai-catalog

    /.well-known/ai-catalog.json served as JSON with Access-Control-Allow-Origin: *, carrying a specVersion and at least one valid entry (identifier, displayName, type, and exactly one of url or data).

    A capability manifest listing the servers, agents and tools on offer.

    1 of 53 benchmarked organizations pass this check.

AI search foundations

11 scored · 2 informational

Can AI search engines read, understand and cite the site today?

  • HTTPSweb.dev · Google Search

    The homepage served over HTTPS, with plain http:// redirecting to it (or not served at all).

    Search engines prefer secure sites, and AI tools and browsers increasingly avoid insecure ones.

    53 of 53 benchmarked organizations pass this check.

  • AI search crawler accessRFC 9309 · crawler docs

    robots.txt allowing / for the AI search and user-triggered crawlers (OAI-SearchBot, ChatGPT-User, Claude-SearchBot, Claude-User, PerplexityBot, Perplexity-User), and the server answering their published user agents the way it answers a normal visitor.

    If these crawlers are blocked, AI assistants cannot read the site, so they cannot recommend or cite it. Blocking AI training crawlers is a separate choice and does not count here.

    50 of 53 benchmarked organizations pass this check.

  • Indexable homepageRobots meta tag · X-Robots-Tag

    No noindex or none directive in the homepage's robots meta tags or X-Robots-Tag header.

    A noindex instruction keeps the page out of the search indexes AI search features draw on.

    53 of 53 benchmarked organizations pass this check.

  • Content readable without JavaScriptGoogle JavaScript SEO

    At least 80 visible words in the homepage's raw HTML, with scripts and styles removed.

    Many AI crawlers do not run JavaScript; text that only appears afterwards is invisible to them.

    52 of 53 benchmarked organizations pass this check.

  • Heading structureW3C WAI · HTML

    At least one h1, at least one h2 in the main content, and no skipped levels going down (an h2 followed directly by an h4).

    A clear heading outline tells a machine where each topic starts and ends, so it can quote the right passage.

    31 of 53 benchmarked organizations pass this check.

  • Page title and descriptionHTML title · meta description

    A non-empty <title> and <meta name="description"> on the homepage.

    The quickest way for a machine to understand what the business is, and often the text shown to people.

    51 of 53 benchmarked organizations pass this check.

  • Canonical URLrel="canonical"

    A canonical link on the homepage pointing to the homepage itself, on the same site.

    Makes sure search engines and AI credit the right address instead of splitting it or crediting a copy.

    50 of 53 benchmarked organizations pass this check.

  • Structured dataschema.org · JSON-LD

    At least one valid JSON-LD block, or microdata or RDFa markup, on the homepage.

    Spells out facts for machines, so AI gets them right instead of guessing from the page text.

    43 of 53 benchmarked organizations pass this check.

  • Business identity markupschema.org Organization · sameAs

    An Organization or LocalBusiness node in the homepage's JSON-LD with a name, a url and at least one sameAs link.

    Lets AI be sure the business on the site, its listings and its profiles are the same business.

    31 of 53 benchmarked organizations pass this check.

  • Content-type markupschema.org

    Content-type nodes (FAQPage, Product, Service, Event, Menu and the like) in the homepage's JSON-LD.

    Useful where it fits, but not needed on every homepage, so it is never scored.

    Reported by the scanner but never scored, so it is excluded from every tally on this page.

  • Page languageHTML lang attribute

    A valid language tag (such as en or en-US) on the <html> element.

    Helps AI and search engines match the page to people searching in that language, and read it correctly.

    53 of 53 benchmarked organizations pass this check.

  • Response timeweb.dev TTFB

    Time to first byte of the homepage of 800 ms or less, measured from the scanner.

    Slow sites are crawled less often, and agents working on a time budget may give up.

    52 of 53 benchmarked organizations pass this check.

  • llms.txtllmstxt.org proposal

    A text file at /llms.txt starting with an H1 title.

    No major AI platform has said it reads llms.txt, so it is reported and never scored.

    Reported by the scanner but never scored, so it is excluded from every tally on this page.

Agentic commerce

5 scored

Can an agent transact and pay without a person completing the checkout?

These apply to sites that sell through agents. On a documentation or marketing domain their absence is expected rather than a deficiency. Read the five together, not as five separate failures.

  • ACPAgentic Commerce Protocol

    An ACP surface (/.well-known/acp.json and its checkout endpoints) that an agent can drive end to end.

    Agentic Commerce Protocol. Lets an agent complete a purchase through the merchant's existing checkout.

    0 of 53 benchmarked organizations pass this check.

  • UCPUniversal Commerce Protocol

    /.well-known/ucp publishing catalog and checkout in the shape UCP defines.

    Universal Commerce Protocol. Publishes catalog and checkout in a form agents can transact against.

    0 of 53 benchmarked organizations pass this check.

  • AP2Agent Payments Protocol

    AP2 mandate support, carried on the A2A agent card, so a purchase arrives with cryptographic proof the buyer authorized it.

    Agent Payments Protocol. Carries a verifiable mandate proving the buyer authorized the purchase.

    0 of 53 benchmarked organizations pass this check.

  • x402x402

    An HTTP 402 response that prices a resource, so an agent can pay for a single request without holding an account.

    Prices a resource over HTTP 402 so an agent can pay per request.

    0 of 53 benchmarked organizations pass this check.

  • MPPMachine Payments Protocol

    MPP payment metadata in the OpenAPI document: an x-payment-info block describing how an agent settles.

    Machine Payments Protocol. Lets agents settle payments programmatically.

    0 of 53 benchmarked organizations pass this check.

One point per passing check, 32 available, reported as three numbers: 16 readiness checks, 11 AI search foundations and 5 agentic commerce protocols. Rows are ranked on the first two together, 27 checks. Commerce is kept apart because it behaves differently: it is at zero for almost everyone, and a blended fraction would read as a distribution when part of it is a floor. The ranked total is shown on every row. A check the scanner could not run is recorded as not evaluated and left out of the score rather than counted against the site, and left out of the total too, so that row is shown as scored out of fewer than 27 and the fraction stays honest. Those rows are listed under the ranking rather than inside it. A commerce protocol the scanner ruled not applicable is a different thing: it was evaluated, so it stays in the total as a non-pass. Rows are ranked by raw passing checks. A site that refuses the scanner outright is reported as blocked, never as a zero. A site that rate-limits the scanner or does not answer is listed as couldn’t check, also never a zero.

Scores come from Agent Ready Report, agenticplug.ai's agent-readiness scanner, methodology 1.4.0, the same scan the form above runs. Anyone can re-run any row of the table above and check it, and the same scan scores every row, including our own. Seeing an error? Request a correction.

Adoption by check

How many of the 53 benchmarked organizations pass each check. Our own row is excluded here as it is from the table, so a perfect score of ours cannot inflate the field it is compared against. Adoption concentrates in the long-established checks: robots.txt and sitemaps are near-universal, and 51 of 53 publish rules for AI crawlers. The newer discovery standards (MCP server cards, agent skills indexes, ai-catalog manifests) remain in low single digits, and the five commerce protocols sit at the bottom.

  • HTTPS53 / 53
  • Indexable homepage53 / 53
  • Page language53 / 53
  • robots.txt52 / 53
  • Sitemap52 / 53
  • Content readable without JavaScript52 / 53
  • Response time52 / 53
  • AI crawler rules51 / 53
  • Page title and description51 / 53
  • AI search crawler access50 / 53
  • Canonical URL50 / 53
  • Structured data43 / 53
  • Heading structure (H1–H6)31 / 53
  • Business identity markup31 / 53
  • Link headers (RFC 8288)19 / 53
  • OAuth discovery (RFC 8414)15 / 53
  • Markdown negotiation10 / 53
  • Content-Signal6 / 53
  • Agent Skills index5 / 53
  • WebMCP4 / 53
  • MCP server card (SEP-2127)3 / 53
  • API catalog (RFC 9727)1 / 53
  • A2A agent card1 / 53
  • ARD / ai-catalog1 / 53
  • DNS-AID + DNSSEC0 / 53
  • Protected resource metadata (RFC 9728)0 / 53
  • auth.md0 / 53
  • ACP0 / 53
  • UCP0 / 53
  • AP20 / 53
  • x4020 / 53
  • MPP0 / 53

Not one of the 53 organizations benchmarked here passes a single agentic commerce protocol. ACP, UCP, AP2, x402 and MPP are all at zero, including among the companies building them.

Where this is heading

What is agent readiness?

Agent readiness is how easily an AI agent can discover, understand and use a website without a person involved. It is measured as a set of published files, HTTP response headers and DNS records: a machine-readable API catalog, an MCP server card, clean Markdown, signed agent endpoints. Together these let software find what a site offers and act on it. A site can rank well in search and still be unreadable to an agent.

Why does agent readiness matter?

Agent readiness matters because the exchange that funded the web is changing. For most of the web's history a crawler indexed your pages, a search engine sent you a visitor, and the visit was what you monetized. An AI assistant reads the page, answers the question, and the visit may never happen. The content still creates value, but the site does not necessarily capture it. Readiness determines whether a site can still be found, used and paid when the visitor is software rather than a person.

What does agent readiness let a website do?

Agent readiness lets a website do three things it otherwise cannot:

Be found without a search engine
Discovery files, DNS records and catalogs let an agent locate what a site offers directly, instead of inferring it from rendered HTML.
Be used, not only read
An MCP server card or an A2A agent card turns a site from a document into something another piece of software can call and act on.
Be paid, not only crawled
Metered access over HTTP 402 makes it possible to charge for a resource an agent consumes, rather than serving it free by default.

Can a website charge AI agents for access?

Yes, though the rails are newer than the idea and worth reading precisely. The x402 protocol moved to a vendor-neutral foundation under the Linux Foundation in July 2026, and Coinbase Business now accepts agent payments through the same checkouts a merchant already uses, over x402, with funds settling instantly in USDC. Cloudflare's monetization gateway prices any asset behind its network and enforces payment at the edge, with no prior account needed from the buyer, and is in early access. AWS shipped Bedrock AgentCore payments in preview, holding an agent to a spending limit per session.

None of this depends on predicting how quickly agents arrive. Each check is independently useful today and most take hours rather than weeks. This index only records who has done them.

Get listed in the index

Different ask from the scorecard above. These two put a row in the table, or refresh one that is already there. Listing is free, never paid for, and decided editorially.

Not listed yet? Request a listing.

For companies that are not in the table. We'll scan you and add a row if you meet the inclusion rule above. We scan companies whether they ask or not, which is what makes the index worth reading.

Already listed? Request a re-scan.

For companies already in the table. Shipped changes since your last result? We'll re-scan and update your row, and send you the before-and-after.

Coming soon

Agent-Native Certification

A verifiable attestation of which checks a site passes, re-verified monthly and expiring if it lapses. Published criteria, automated verification, no opinion about the business. It is a measurement, not an endorsement.