|

Vercel Introduces ‘Is Agentic’, a Free Agent-Readiness Scoring Tool That Audits Public Websites Using Ora’s 100+ Checks

ByRicardo

Vercel has launched Is Agentic, a public tool that scores how readily AI agents can uncover, entry, perceive, and use a web site. Scans are run and scored by Ora, an agent-experience analysis firm from period labs. Vercel operates the interface, report pages, storage, and the grouping that produces the displayed rating.

Is it deployable?

Yes — at zero price. Is Agentic is currently free, with no paid plans, subscription expenses, or per-report charges. The public web site, read-only API, CLI, and MCP server require no API key or billing account. Enter a URL within the browser, or run the CLI:

Copy Code
npx is-agentic <area>
npx is-agentic <area> --json

Which stage of firm: Any group proudly owning a public internet floor. Seed-stage startups get a free baseline audit with no procurement. Mid-market SaaS groups can wire --json output into CI as a regression gate. Enterprises can benchmark documentation portals, developer websites, and commerce surfaces throughout enterprise models.

Industries: Developer instruments and SaaS, e-commerce and retail, journey and hospitality, fintech, marketplaces, healthcare supplier directories, and media or documentation publishers. Anywhere an agent could store, guide, combine, or cite on a consumer’s behalf.

Applications: Pre-launch agent-readiness audits. CI checks that fail builds when server-rendered content material regresses. Competitive benchmarking towards public scores. Validating an MCP server or OpenAPI floor is definitely discoverable. Prioritizing technical fixes with copy-pasteable remediation prompts.

What Exactly it Measures

Ora’s methodology walks 4 layers an agent strikes by way of. Discovery carries 20 factors throughout 15 checks. Access carries 30 factors throughout 41 checks. Usability carries 40 factors throughout 56 checks. Payments carries 10 factors throughout 6 checks. That totals 118 checks, matching Vercel’s “100+ checks” declare. Ora says the guidelines is reverse-engineered from actual agent runs, not authored by opinion.

Ora additionally publishes a letter scale: A+ at 95–100, A at 86–94, B at 70–85, C at 48–69, D at 28–47, and F at 0–27.

Vercel regroups these checks into its personal displayed scoring model. Essential checks share an 80-point pool. Recommended checks share a 20-point pool. Emerging alerts add a bonus capped at 5 factors, and their absence by no means lowers a rating. Not-applicable checks are excluded quite than counted as failures. Partial outcomes obtain proportional credit score, and duplicated verify IDs throughout MCP surfaces are averaged.

That applicability logic issues. Recommended checks activate solely when scan proof positively identifies an API, OAuth stream, GraphQL endpoint, MCP server, developer portal, or commerce floor. A advertising and marketing web site will not be penalized for omitting an interface it by no means claimed to supply.

Inside a report

Every discovering ships with noticed proof and, the place obtainable, a concrete advice. A dwell API response exhibits the form: rating, score_label, scanned_at, eligible_checks, a score_breakdown with earned and obtainable factors per tier, and an points array. Each concern carries id, title, particulars, advice, outcome, and tier.

Real verify IDs embrace content-no-js, agent-friendly-404, markdown-negotiation-vary, json-ld, sitemap, trust-anchors, and metadata-completeness. The 404 verify asks for a actual HTTP 404 standing quite than a 200 serving an app shell.

Reports additionally embrace an noticed agent journey exhibiting the place one agent hit friction. Vercel retains that run exterior the numeric rating, since one process can’t characterize each agent. “Prompt to repair” converts actionable suggestions into an implementation temporary for a coding agent.

Machine interfaces

Three read-only surfaces expose accomplished stories. The report API lives at /api/v1/report, rate-limited to 120 requests per consumer IP per 60-second window. Errors use RFC 9457 drawback particulars with secure codes corresponding to invalid_url, report_not_found, and rate_limit_exceeded. The OpenAPI description is the supported integration contract, discoverable by way of an RFC 9727 API catalog. Deprecations sign through RFC 9745 headers, with Sunset introduced at the very least 90 days forward.

The MCP server at https://is-agentic.com/mcp exposes is_agentic_get_report, is_agentic_get_methodology, and is_agentic_get_developer_docs over Streamable HTTP. Hosts supporting MCP Apps render an interactive rating card. An official agent talent installs through npx expertise add vercel-labs/is-agentic.

The web site practices what it scores. Report pages render the rating within the preliminary HTML response, serve a Markdown variant below Accept: textual content/markdown, and set Vary: Accept so shared caches by no means combine representations.


Key Takeaways

  • Is Agentic scores public websites on agent discovery, entry, usability, and funds — free, with no API key.
  • Ora provides 118 checks throughout 4 weighted layers; Vercel regroups them into Essential 80, Recommended 20, Bonus 5.
  • Not-applicable checks are excluded, so advertising and marketing websites should not penalized for lacking APIs or commerce surfaces.
  • Reports ship as HTML, Markdown, JSON, CLI output, and MCP instruments, all read-only and unauthenticated.
  • Vercel states it isn’t a certification, safety audit, or accessibility evaluate — deal with it as a prioritized technical evaluate.

The put up Vercel Introduces ‘Is Agentic’, a Free Agent-Readiness Scoring Tool That Audits Public Websites Using Ora’s 100+ Checks appeared first on MarkTechPost.

Similar Posts