Agent Readiness Compare

Agent readiness in 2026 so far: the announcements, layer by layer

Dated announcements from February to November 2026, regrouped by the part of the stack they change.

In short

The act layer moved most from February to September 2026: MCP became stateless, A2A reached v1.0 and joined the Agentic AI Foundation, and Cloudflare previewed WebMCP at the edge. Reading gained llms.txt v2 and Markdown for Agents, trust gained Web Bot Auth checks, and payment gained x402 batch settlement. AgentReady.org followed in October.

The recap groups dated announcements by layer

This dispatch regroups dated announcements by the layer of the readiness stack they affect, so a team can see which part of its site each change touches. Most items run from 12 February to 25 September 2026; a last section covers October and early November. The news page lists the current items with their sources.

Discovery changed with one Cloudflare setting

On 15 September Cloudflare added a Disallow AI Training setting that uses robots.txt Disallow rules to block AI training while keeping a site discoverable in search. It also added an Accountable designation for crawler operators that meet stated opt-out and reporting requirements. For site owners on Cloudflare, training and search can now be separated with one setting rather than by maintaining user agent groups by hand.

robots.txt itself did not change. RFC 9309 still describes rules that "are not a form of access authorization".

Reading gained Markdown for Agents and llms.txt v2

On 12 February Cloudflare launched Markdown for Agents in beta. When a client sends Accept: text/markdown, Cloudflare converts the HTML to markdown at the edge and adds an x-markdown-tokens header. Cloudflare's documentation lists it at no cost on Pro, Business and Enterprise plans and SSL for SaaS.

On 10 August the llms.txt proposal was revised to v2. It adds link relations so a page can point to its markdown version and to the llms.txt that covers it, accepts both page.html.md and page.md URL forms, and defines what a subpath file covers. Markdown versions of pages are what the new link relations point to. See the llms.txt standard page.

Acting saw most of the year's movement

  • 12 March: A2A v1.0.0 updated OAuth 2.0 flows (device code and PKCE added, implicit and password grants removed), added a tasks/list method and simplified the message Part structure. v1.0.1 followed on 28 May.
  • 28 July: the MCP 2026-07-28 specification made the protocol stateless, removing the initialize handshake and session IDs, and deprecated Dynamic Client Registration. See the MCP standard page.
  • 6 August: Cloudflare opened a developer preview of WebMCP at the edge, injecting a bridge script that registers tool packs for browser agents with no origin code change.
  • 17 August: A2A joined the Agentic AI Foundation as a hosted project next to MCP.
  • 22 August: the MCP maintainers published a roadmap with five priorities, including HTTP-native transport and agent identity.

For a site that runs an MCP server, the July specification is the item that needs action. The others change governance or add options.

Payment and trust moved less

On 11 May the x402 project introduced batch settlement, which it says lets agents transact at low latency and fractions of a cent using cryptographic vouchers redeemed onchain in bulk. On 28 August Cloudflare moved bot submissions to a BotBase dashboard for operators, with review status and automatic validation of verification methods, including Web Bot Auth signatures.

Neither changes what most sites must do. BotBase matters to anyone who operates an agent and wants it verified; see the Web Bot Auth standard page and the x402 standard page.

Testing tools shipped new methods

On 7 July Ora said it released Deep Scan v2, which it says derives its checklist from agents run on real tasks and separates Verified signals from Emerging ones. That is a vendor claim. On 20 August Ora and Vercel launched is-agentic.com, with every scan run and scored by Ora; see the is-agentic.com profile. Cloudflare's scanner remained a free public page.

The scanner profiles compare these tools on one rubric.

October and November brought a spec and method changes

  • 19 October: Ora launched AgentReady.org, an open specification of what a product should implement so agents can use it, with 24 identifiers in version 2.0. AR-ACT-10, an MCP server or a CLI, became a MUST. The spec does not score anyone.
  • 20 October: agent-ready.dev stopped crediting an HTML catch-all page as an llms.txt, sitemap.md or AGENTS.md file. Single-page sites lose those checks, and older scans were not re-scored.
  • 21 October: the AgentReady repository recorded its v2.0 changelog, adding an AI Catalog, first-party pricing, agent payments and NLWeb identifiers and retiring the AGENTS.md identifier.
  • 4 November: Cloudflare's scanner listed 23 checks in five categories, up from four dimensions at launch. The same day Ora's API listed 132 checks at contract 1.38.0 while its methodology page said 126.

The AgentReady.org standard page holds the identifiers.

Agent skills sit beside the site, not on it

On 25 September Vercel published a report on agent skills, which it defines as reusable instructions that give an agent the context for a particular job. It said the skills.sh registry reached one million skills and nearly 280 million installs in seven months. Skills sit on the agent's side rather than the website's, but they shape how agents approach tasks on sites.

A web team can act on four of these items

  • If you run an MCP server, plan the move to the 2026-07-28 specification.
  • If you publish markdown versions of pages, add the llms.txt v2 link relations.
  • If you are on Cloudflare, review the AI training setting and the default content-signal header against your written policy.
  • If you operate an agent, check how it is verified under BotBase.

Each maps to an item in the checklist.

Sources

  1. Cloudflare blog: Markdown for Agents in beta. https://blog.cloudflare.com/markdown-for-agents/, read 2026-09.
  2. Cloudflare, Markdown for Agents documentation. https://developers.cloudflare.com/fundamentals/reference/markdown-for-agents/, read 2026-09.
  3. A2A releases on GitHub. https://github.com/a2aproject/A2A/releases, read 2026-09.
  4. x402.org writing: batch settlement. https://www.x402.org/, read 2026-09.
  5. Ora blog: Deep Scan v2. https://ora.ai/blog/deep-scan-v2, read 2026-09.
  6. MCP blog: the 2026-07-28 specification. https://blog.modelcontextprotocol.io/posts/2026-07-28/, read 2026-09.
  7. Cloudflare blog: WebMCP developer preview. https://blog.cloudflare.com/webmcp/, read 2026-09.
  8. llmstxt.org: llms.txt changes. https://llmstxt.org/changes.html, read 2026-09.
  9. Agentic AI Foundation: A2A joins AAIF. https://aaif.io/blog/a2a-joins-aaif, read 2026-11-04.
  10. Ora blog: is-agentic.com with Vercel. https://ora.ai/blog/is-agentic-with-vercel, read 2026-11-04.
  11. MCP blog: roadmap. https://blog.modelcontextprotocol.io/posts/mcp-roadmap/, read 2026-09.
  12. Cloudflare blog: BotBase for operators. https://blog.cloudflare.com/botbase-for-operators/, read 2026-09.
  13. Cloudflare blog: accountable mixed-use AI crawlers. https://blog.cloudflare.com/accountable-mixed-use-ai-crawlers/, read 2026-09.
  14. Vercel blog: state of agent skills. https://vercel.com/blog/state-of-agent-skills, read 2026-09.
  15. Ora blog: AgentReady launch. https://ora.ai/blog/agentready-launch, read 2026-11-04.
  16. AgentReady repository changelog. https://github.com/agentready-org/standard/blob/main/CHANGELOG.md, read 2026-11-04.
  17. agent-ready.dev, methodology. https://agent-ready.dev/methodology, read 2026-11-04.
  18. Cloudflare, isitagentready.com llms.txt. https://isitagentready.com/llms.txt, read 2026-11-04.
  19. Ora, check catalog. https://ora.ai/api/checks, read 2026-11-04.
  20. RFC 9309. https://www.rfc-editor.org/rfc/rfc9309.html, read 2026-09.

Last reviewed 2026-11-05