Agent Ready CheckoutEdition . The pay layer for agents.

360 check, 9 Nov 2026

Delta Air Lines on the pay layer: the 360 agent-readiness check

In short

Delta Air Lines scores 13 of 100 on Ora's agent-readiness scan, an F, read 14 Nov 2026. The six payment checks did not apply to delta.com on this read, which is how Ora treats a site it does not read as a shop. A read that got no page back, on the lowest score among the sellers here.

On 14 Nov 2026 the public site at delta.com scored 13 of 100 on Ora's agent-readiness scan, an F, in Ora's Travel & Hospitality category. Delta Air Lines is the largest airline in the world by revenue, so this check reads the Payments layer first: the six checks that look for x402, MPP, UCP, ACP and AP2 on the domain, the same protocols this site's matrix tracks row by row. The other layers follow, with every check Ora ran and what it saw. Ora's one-line summary: Turns agents away at the door: no MCP server, no OpenAPI spec and no public API to call.

The score

Delta Air Lines on Ora, read 14 Nov 2026: points per layer, with the share of each layer's maximum. 4 checks pass, 1 are partial, 44 fail and 82 do not apply to this site.
LayerPointsShareWhat the layer asks
Discovery4 of 944%Can agents find and recommend it
Access0 of 330%Can agents read it
Usability3 of 506%Can agents use it
Payments0 of 0none applyCan agents pay
Total13 of 10013%Grade F

The pay layer

Ora did not run the six payment checks against delta.com on this read: it marks them not applicable on a site it does not read as a shop, so the layer has no maximum and costs nothing. A travel seller that sells online can still publish any of the five protocols; the matrix says which processors and platforms carry each one. Each protocol links to its matrix row, where the processors and platforms that carry it are dated and sourced.

The six Payments checks Ora runs, on delta.com, read 14 Nov 2026. A protocol not found costs nothing, and a check marked does not apply was not run against the site.
Payment checkResultPointsMatrix rowWhat Ora saw
x402Does not apply0 of 2x402 in the matrixNo x402 payment protocol support detected. No commerce signals detected - agent-payment protocols are optional for non-commerce sites
MPPDoes not apply0 of 2MPP in the matrixNo MPP (Machine Payments Protocol) support detected. No commerce signals detected - agent-payment protocols are optional for non-commerce sites
UCPDoes not apply0 of 3UCP in the matrixno UCP (Universal Commerce Protocol) signals detected. No commerce signals detected - agent-payment protocols are optional for non-commerce sites
ACPDoes not apply0 of 3ACP in the matrixno ACP (Agentic Commerce Protocol) signals detected. No commerce signals detected - agent-payment protocols are optional for non-commerce sites

The other layers, check by check

Every check Ora ran on delta.com, grouped by layer, with the result, the points and what Ora recorded where its wording passes this site's gate.

Discovery: 4 of 9

Discovery checks on delta.com, read 14 Nov 2026; 7 more checks in this layer did not apply to the site.
CheckResultPointsWhat Ora saw
ARD discoveryFail0 of 1No /.well-known/ard.json, no same-site rel="ard" link, and no legacy /.well-known/ai-catalog.json
Developer resource discoverabilityFail0 of 4In a search for your API docs, none of the 10 results is your official docs
Brand name discoverabilityPass3 of 3delta.com ranks #5 for "delta" (searched your brand name alone: we could not read a product term from your site)
NPM/PyPI SDK packagePass1 of 1Pass, no detail recorded.
Agent platform configsFail0 of 1Could not locate a public repo containing agent configs or rules. If our probes missed it, AI coding agents likely will too - link the repo from your homepage or docs so it's discoverable.
Agent Plugins manifestFail0 of 1No Agent Plugins manifest (plugin.json) found in discovered repos
ChatGPT app listedFail0 of 2Not found in ChatGPT app directory

Access: 0 of 33

Access checks on delta.com, read 14 Nov 2026; 12 more checks in this layer did not apply to the site.
CheckResultPointsWhat Ora saw
Sitemap existsFail0 of 1No sitemap found
Not blocked by bot detectionNot run0 of 2Could not test bot user agents
Agent discovery fileFail0 of 2No agent discovery file found
A2A / agent-cardFail0 of 2No A2A agent card found at /.well-known/agent-card.json
Listed on skills.shPass1 of 1Pass, no detail recorded.
pricing.md existsFail0 of 2No pricing.md found - agents need machine-readable pricing to compare products and make purchase recommendations
NLWeb Schema FeedsFail0 of 1No robots.txt found - cannot check for Schema Feeds
MCP well-known discoveryFail0 of 2No MCP server URL discovered
HTTP Link headers (RFC 8288)Fail0 of 1No HTTP Link response headers (RFC 8288) found
Markdown URL fallbackFail0 of 2Homepage does not support the .md suffix. Probed https://delta.com/index.md and it did not return markdown (expected text/markdown content-type or a heading-led non-HTML body).
Modular llms.txt per product areaFail0 of 1No section-level llms.txt found. Tried /docs/llms.txt, /api/llms.txt, /developers/llms.txt, /guides/llms.txt, /reference/llms.txt. This is a bonus check: it can add a point and never costs one.
llms.txt existsFail0 of 1No llms.txt found at https://delta.com/llms.txt. Publish it at the site root, where agents that follow the llms.txt spec look for it.
llms.txt formattingFail0 of 2No llms.txt found to evaluate quality
JSON-LD structured dataNot run0 of 2Could not fetch homepage
Pricing info accessibleFail0 of 3No pricing page or pricing data found
Public API/docs linked from homepageFail0 of 4No public API or documentation page linked from homepage
Agent instruction / when-to-useFail0 of 1No agent instruction file with when-to-use guidance found
Skills.sh skill qualityPartial1 of 2Skills.sh presence exists but limited - 2 skills (goal: 5+), 87 installs (goal: 200+)
JSON-LD entity linking (sameAs)Not run0 of 1Not run, no detail recorded.
Metadata completenessNot run0 of 1Could not fetch homepage
Organization schema completenessNot run0 of 1Not run, no detail recorded.
Trust anchor pagesFail0 of 1No trust anchor pages found with sufficient content (About, Contact, Privacy)
OpenAPI spec publishedFail0 of 8No OpenAPI/Swagger specification found
Developer portalFail0 of 5No developer portal found
API catalog (RFC 9727)Fail0 of 2No /.well-known/api-catalog found (RFC 9727)
Markdown agent docsNot run0 of 1Could not fetch with Accept: text/markdown
Markdown content negotiation (acceptmarkdown.com)Fail0 of 1Could not probe both Accept: text/markdown and Accept: text/html on the homepage https://delta.com
Bot-UA markdown servingFail0 of 1No probed bot User-Agent (ChatGPT-User, Claude-User, Perplexity-User) receives markdown when requesting HTML. Optional: detect AI-bot UAs server-side and serve them a markdown representation directly.

Usability: 3 of 50

Usability checks on delta.com, read 14 Nov 2026; 58 more checks in this layer did not apply to the site.
CheckResultPointsWhat Ora saw
Public API with reachable endpointsFail0 of 8No publicly reachable API surface detected (REST and GraphQL both absent or auth-gated)
OAuth 2.0 supportFail0 of 5No OAuth 2.0 or OpenID Connect support detected
Scoped permissionsFail0 of 5No declared OAuth scopes, security schemes, or scoped-permission documentation found
Agent onboarding frictionFail0 of 2Insufficient content to evaluate onboarding friction
Web Bot Auth directoryFail0 of 2No /.well-known/http-message-signatures-directory found
auth.md existsFail0 of 2No /auth.md found at site root
auth.md structureFail0 of 2No /auth.md found at site root
Agent auth discovery metadataFail0 of 3Neither /.well-known/oauth-protected-resource nor /.well-known/oauth-authorization-server found. Probed: delta.com, api.delta.com.
Agent auth WWW-Authenticate hintFail0 of 1No 401 with WWW-Authenticate: Bearer resource_metadata=... found. Probed [https://delta.com/api, https://delta.com/api/v1, https://delta.com/v1, https://delta.com/v2, https://delta.com/agent/identity, https://delta.com/agent/auth
agent_auth endpoints reachableFail0 of 2No agent_auth endpoint URIs found in AS metadata or /auth.md prose; nothing to probe
MCP server / manifestFail0 of 10No MCP server or manifest found
WebMCP supportFail0 of 8No WebMCP support detected - no document.modelContext / navigator.modelContext usage found
JSON error responsesFail0 of 3API does not return JSON error responses (or no API detected)
CLI tool availablePass3 of 3CLI package found on npm: @delta-agentcloud/cli
NLWeb /ask endpointFail0 of 1No response from /ask endpoint
NLWeb streaming supportFail0 of 1No response from /ask endpoint for streaming request
MCP server-card.jsonFail0 of 2No MCP server card found (checked /.well-known/mcp/server-card.json, the site's ai-catalog.json, servers[].card in mcp.json, and <server>/server-card)
Product + docs MCP coverageFail0 of 2This bonus needs two MCP servers: one for your product so agents can take actions, and a separate one for your documentation so agents can answer questions from your docs.
Agent-friendly 404sNot run0 of 2Not run, no detail recorded.
API schema complexity analysisFail0 of 2No API schema detected
Function calling compatibilityFail0 of 2No API spec found - function calling requires discoverable endpoints

The fixes worth most points

Ora attaches an estimate to each failing or partial check: how many points the site would gain by passing it. These are the 5 with the largest estimates for Delta Air Lines.

Developer resource discoverability
Fail, 0 of 4, about 9.9 points to gain. Ora saw: In a search for your API docs, none of the 10 results is your official docs.
MCP server / manifest
Fail, 0 of 10, about 8.9 points to gain. Ora saw: No MCP server or manifest found.
OpenAPI spec published
Fail, 0 of 8, about 8.1 points to gain. Ora saw: No OpenAPI/Swagger specification found.
Public API with reachable endpoints
Fail, 0 of 8, about 7.1 points to gain. Ora saw: No publicly reachable API surface detected (REST and GraphQL both absent or auth-gated).
WebMCP support
Fail, 0 of 8, about 7.1 points to gain. Ora saw: No WebMCP support detected - no document.modelContext / navigator.modelContext usage found.

Our read

Delta's 13 is the lowest score among the sellers read here, and most of it is a read that never started: Ora's request for the home page got no page back, the agent user agents could not be tested and robots.txt could not be fetched, so the door, content, policy and structured-data rows are unverified and the Access layer reads 0 of 45. Ora found no commerce signals, so the six payment checks did not apply on this read, on the airline with the largest revenue of any in the world. What could be probed came back empty: no publicly reachable API, neither a developer portal nor an OpenAPI specification, and neither an MCP server nor OAuth discovery. A search for the API documentation returned no official page in ten results, 6.7 points, and the brand search placed delta.com sixth for a word with other meanings. Whether the airline rate-limited the scanner or turned it away is for a second scan; the act layer is empty either way.

Test your own checkout

The scan above is free and needs no account: enter a domain at ora.ai and read the same layers for your own site, with the six payment checks mapped to this matrix on the Ora Payments page. The command below runs the same audit from a terminal and exits with 1 under the score you set, so it can gate a deploy. Why Ora, and its limits.

npx ax@0.10 audit https://example.com --min-score 70

All 360 checks, one company a day. Corrections to the corrections page.

Sources

  1. ora.ai/api/score/delta.com, Ora's scan (vendor), read 14 Nov 2026
  2. Ora's scoring rules, version 3 (vendor), read 14 Nov 2026
  3. Ora check catalog (GET /api/checks), read 14 Nov 2026
  4. delta.com, the company's site, read 14 Nov 2026

Last reviewed