Is docs.arbitrum.io agent-ready?

What we tested

Probed live on 23 Aug 2026 against rubric v1. 3 of 5 checks passed.

PROBE-VERIFIEDtier 2 of 3

✓Markdown negotiationAccept: text/markdown

✓Markdown twin at a predictable URL/page.md

✓llms.txt/llms.txt

—API catalogRFC 9727

—MCP server answers/.well-known/mcp/server-card.json → tools/list

What an agent could do here

Read from the page’s own content, with the wording each was drawn from. Inference is kept separate from tested facts — an agent completing the action is tier 3.

UNVERIFIED

read“Find quickstarts, guides, and reference docs for building dApps”

download“Nitro whitepaper”

https://docs.arbitrum.io/nitro-whitepaper.pdf

Context

32 sites in the index share the category blockchain developer documentation, of which 8 are transactional.

How we grade

Three tiers. Every listing shows which one it has reached, and when. The rubric.

tier 1

Declared

The site says agents are welcome in its robots.txt. A permission, not a capability.

✓

tier 2

Probe-verified

We fetched the site and tested each signal ourselves. Dated, repeatable, re-checked on a schedule.

this site · 23 Aug 2026

tier 3

Behaviourally verified

An agent completed the action end to end — booked, bought, submitted — and it worked.

coming

Own this site?

2 checks did not pass when we last looked: API catalog, MCP server answers. Each is a small, specific fix; the rubric says exactly what we look for.

Behavioural verification — an agent completing your booking, purchase or contact flow end to end, with the date published here — opens to a small founding cohort first. Leave an email to be in it.