--- title: "The Atlantic agent readiness: the 360 check | Agent Ready Crawlers" description: "The Atlantic on Ora's agent-readiness scan, read 2026-11-12: 39 of 100, grade D. The door, what agents can read and do, the fixes worth most." canonical: https://agentreadycrawlers.com/blog/theatlantic-agent-readiness site: "Agent Ready Crawlers" last_updated: 2026-11-12 date: 2026-11-12 section: "360 checks" --- # The Atlantic agent readiness: the 360 check | Agent Ready Crawlers > The Atlantic on Ora's agent-readiness scan, read 2026-11-12: 39 of 100, grade D. The door, what agents can read and do, the fixes worth most. Source: https://agentreadycrawlers.com/blog/theatlantic-agent-readiness Site: Agent Ready Crawlers Last reviewed: 2026-11-12 Agent endpoints: https://agentreadycrawlers.com/llms.txt (index), https://agentreadycrawlers.com/openapi.json (API), https://agentreadycrawlers.com/mcp (MCP server), https://agentreadycrawlers.com/ask (search) Access: https://agentreadycrawlers.com/auth.md (no key). Pricing: https://agentreadycrawlers.com/pricing.md (free). 360 check, 12 November 2026 # The Atlantic: the 360 agent-readiness check In short The Atlantic scores 39 of 100 on Ora's agent-readiness scan, a D, read 12 November 2026. At the door, agents blocked: ChatGPT-User, OAI-SearchBot, Claude-User, PerplexityBot. 10 of 64 applicable checks pass; the gap worth most is OpenAPI spec published, about 7.6 points by Ora's estimate. Four agents blocked at the door, and an MCP server waiting on the support subdomain. The Atlantic is the Washington magazine of ideas and reporting. On 12 November 2026 its public site scored **39 of 100** on [Ora's](https://ora.ai/?utm_source=agentreadycrawlers.com&utm_medium=referral&utm_campaign=check) agent-readiness scan, a D, in Ora's News & Intelligence category. Ora probes a site the way an agent would: it requests pages with the agents' own user agents, reads robots.txt, looks for the files agents read, and tries the API, MCP and payment surfaces. The check below walks through all 138 of its checks for this one domain, grouped the way an agent meets them. Ora's one-line summary: Turns agents away at the door: bot detection blocks ChatGPT-User, OAI-SearchBot, Claude-User and PerplexityBot from the homepage. ## The score | Layer | Asks | Points | Share | | --- | --- | --- | --- | | Discovery | Can agents find and recommend it | 3.5 of 12 | 29% | | Access | Can agents read it | 10 of 35 | 29% | | Usability | Can agents use it | 29.759999999999998 of 57 | 52% | | Payments | Can agents pay | 0 of 0 | none apply | | Total | Grade D | 39 of 100 | 39% | ** 10 checks pass, 9 are partial, 45 fail and 74 do not apply to this site. Every check is defined in [Ora's catalog](https://ora.ai/api/checks?utm_source=agentreadycrawlers.com&utm_medium=referral&utm_campaign=check) (read 2026-11-05); the result for each one is in the groups below, with what Ora saw where it said. ## At the door What the site answers when a request arrives with an agent’s user agent, and what robots.txt says to the crawlers in the Index. 3 checks in this group do not apply to this site and are left out. Agents named in Ora's results, with their Index rows: [ChatGPT-User](https://agentreadycrawlers.com/crawlers/chatgpt-user/), [OAI-SearchBot](https://agentreadycrawlers.com/crawlers/oai-searchbot/), [Claude-User](https://agentreadycrawlers.com/crawlers/claude-user/), [PerplexityBot](https://agentreadycrawlers.com/crawlers/perplexitybot/), [Perplexity-User](https://agentreadycrawlers.com/crawlers/perplexity-user/). | Check | Result | Points | What Ora saw | | --- | --- | --- | --- | | Not blocked by bot detection | Fail | 0 of 2 | Agents blocked: ChatGPT-User, OAI-SearchBot, Claude-User, PerplexityBot | | Agent crawler reachability | Fail | 0 of 1 | No agent we tested can reach the homepage - ChatGPT-User: blocked, OAI-SearchBot: blocked, Claude-User: blocked, PerplexityBot: blocked | | robots.txt AI crawler policy | Partial | 0.5 of 1 | AI search crawlers: allowed in 1 of 3 checks (3 crawlers on 1 page). AI training crawlers: allowed in 1 of 2 checks (2 crawlers on 1 page), not scored. robots.txt restricts 2/3 evaluated search page/crawler pairs. | | robots.txt agent-user policy | Partial | 0.5 of 1 | robots.txt restricts 2/3 evaluated page/crawler pairs. Checked 3 user-triggered agents (chatgpt-user, claude-user, perplexity-user) on 1 public page. Restricted: claude-user at https://theatlantic.com/ (Disallow: /, | | Web Bot Auth directory | Fail | 0 of 2 | No /.well-known/http-message-signatures-directory found | ## What an agent can read Whether the text is in the first response, what the site publishes for agents, and how it describes itself to them. 3 checks in this group do not apply to this site and are left out. | Check | Result | Points | What Ora saw | | --- | --- | --- | --- | | Sitemap exists | Fail | 0 of 1 | No sitemap found | | llms.txt exists | Fail | 0 of 1 | No llms.txt found at https://theatlantic.com/llms.txt. Publish it at the site root, where agents that follow the llms.txt spec look for it. | | llms.txt formatting | Fail | 0 of 2 | No llms.txt found to evaluate quality | | Markdown agent docs | Fail | 0 of 1 | Missing markdown content negotiation. Homepage returned text/html when probed with Accept: text/markdown (expected text/markdown), and none of the well-known root paths (/llms.md, /auth.md, /agents.md, /developers.md, | | Markdown URL fallback | Fail | 0 of 2 | Homepage does not support the .md suffix. Probed https://theatlantic.com/index.md and it did not return markdown (expected text/markdown content-type or a heading-led non-HTML body). | | Bot-UA markdown serving | Fail | 0 of 1 | No 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. | | JSON-LD structured data | Fail | 0 of 2 | No JSON-LD structured data found on homepage | | Organization schema completeness | Fail | 0 of 1 | No JSON-LD found - Organization schema missing | | JSON-LD entity linking (sameAs) | Fail | 0 of 1 | No JSON-LD found - no entity linking possible | | Metadata completeness | Partial | 0.5 of 1 | Only 1/4 metadata signals present - missing: canonical URL, og:image, og:type | | Agent instruction / when-to-use | Fail | 0 of 1 | No agent instruction file with when-to-use guidance found | ## What an agent can do The surfaces an agent acts on: an API it can find and call, an MCP server, an agent card, a command line. 3 checks in this group do not apply to this site and are left out. | Check | Result | Points | What Ora saw | | --- | --- | --- | --- | | Public API with reachable endpoints | Partial | 3.43 of 8 | API described in documentation at https://accounts.google.com but no machine-verifiable API surface confirmed. Best-of-protocols score: 3/7. | | Public API/docs linked from homepage | Pass | 4 of 4 | Documentation site found at https://accounts.google.com | | Developer portal | Pass | 5 of 5 | Developer documentation portal found at https://accounts.google.com | | OpenAPI spec published | Fail | 0 of 8 | No OpenAPI/Swagger specification found | | API catalog (RFC 9727) | Fail | 0 of 2 | No /.well-known/api-catalog found (RFC 9727) | | MCP server / manifest | Partial | 8.33 of 10 | MCP server detected at https://support.theatlantic.com/mcp; it requires authentication. Presence is verified (5/6), but Ora could not inspect its tools or verify access scopes without credentials. | | MCP well-known discovery | Partial | 1 of 2 | MCP server at https://support.theatlantic.com/mcp - list its server card, hosted on your own domain, in /.well-known/ai-catalog.json so MCP clients can discover it | | A2A / agent-card | Fail | 0 of 2 | No A2A agent card found at /.well-known/agent-card.json | | Agent discovery file | Fail | 0 of 2 | No agent discovery file found | | OAuth 2.0 support | Pass | 5 of 5 | OAuth authorization server metadata at https://support.theatlantic.com/mcp/oauth | | OAuth Protected Resource metadata (RFC 9728) | Pass | 2 of 2 | Metadata at /.well-known/oauth-protected-resource (RFC 9728) that tells agents your auth requirements up front, instead of leaving them to trial and error. | | auth.md exists | Fail | 0 of 2 | No /auth.md found at site root | | WebMCP support | Fail | 0 of 8 | No WebMCP support detected - no document.modelContext / navigator.modelContext usage found | | NLWeb /ask endpoint | Pass | 1 of 1 | NLWeb /ask endpoint exists but requires authentication (HTTP 403, via GET) | | JSON error responses | Pass | 3 of 3 | When something breaks, agents need a structured JSON error, not an HTML error page. One is recoverable, the other is a dead end. | ## Found and recommended Whether an assistant can find the company by name, confirm what it is, and see it in the registries agents read. 1 check in this group does not apply to this site and is left out. | Check | Result | Points | What Ora saw | | --- | --- | --- | --- | | Brand name discoverability | Pass | 3 of 3 | theatlantic.com ranks #5 for "atlantic" (searched your brand name alone: we could not read a product term from your site) | | Developer resource discoverability | Fail | 0 of 4 | In a search for your API docs, none of the 10 results is your official docs. In a search for your MCP server, SDK or CLI, none of the 10 results is your own, although the scan found one on your site | | Listed in MCP registries | Fail | 0 of 3 | No verified entry in the official MCP Registry or on Smithery, and no npm or PyPI package of yours that runs as an MCP server. To pass, | | ChatGPT app listed | Fail | 0 of 2 | Not found in ChatGPT app directory | | Registry branding | Fail | 0 of 2 | No registry branding (name, icon, description) found | | Listed on skills.sh | Fail | 0 of 1 | No official skills self-published on skills.sh | | ARD discovery | Fail | 0 of 1 | No /.well-known/ard.json, no same-site rel="ard" link, and no legacy /.well-known/ai-catalog.json | ## 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 The Atlantic, with what Ora observed. The wording of each fix is Ora's job; the links go to the check in its catalog. OpenAPI spec published Fail, 0 of 8, about 7.6 points to gain. Ora saw: No OpenAPI/Swagger specification found Developer resource discoverability Fail, 0 of 4, about 7.4 points to gain. Ora saw: In a search for your API docs, none of the 10 results is your official docs. In a search for your MCP server, SDK or CLI, none of the 10 results is your own, although the scan found one on your site WebMCP support Fail, 0 of 8, about 6.2 points to gain. Ora saw: No WebMCP support detected - no document.modelContext / navigator.modelContext usage found Listed in MCP registries Fail, 0 of 3, about 5.6 points to gain. Ora saw: No verified entry in the official MCP Registry or on Smithery, and no npm or PyPI package of yours that runs as an MCP server. To pass, Scoped permissions Fail, 0 of 5, about 3.9 points to gain. Ora saw: No declared OAuth scopes, security schemes, or scoped-permission documentation found ## Our read The Atlantic shuts its door before an agent reads a line. Bot detection blocked ChatGPT-User, OAI-SearchBot, Claude-User and PerplexityBot at the home page, and robots.txt adds its own limits: the AI search crawlers were allowed in 1 of 3 checks, and 2 of 3 pairs checked for user-triggered agents are restricted. The Access layer reads 10 of 35. With no home page read, rows such as text without JavaScript and noindex are unverified rather than failed; what Ora could confirm is thin, with neither a sitemap nor an llms.txt, no JSON-LD and metadata at 1 of 4. The surprise sits on a subdomain: an MCP server at support.theatlantic.com/mcp that requires authentication and verifies at 5 of 6, with OAuth metadata beside it. The developer docs Ora credited sit at accounts.google.com, which describes the probe, not the magazine. The fix worth most is an OpenAPI specification, about 7.6 points. A D at 39: the support site speaks MCP while the front door turns the readers' agents away. ## Check your own door The scan above is free and needs no account: enter a domain at [ora.ai](https://ora.ai/?utm_source=agentreadycrawlers.com&utm_medium=referral&utm_campaign=check) and read the same four layers for your own site, then compare the door with the [Block Rate Report](https://agentreadycrawlers.com/block-rates/) for sites of your rank and kind. Our [guide to testing whether agents can reach your site](https://agentreadycrawlers.com/guides/test-whether-ai-agents-can-reach-your-site/) has the curl commands for a manual check, and the [robots.txt builder](https://agentreadycrawlers.com/robots-builder/) writes a policy file from the Index. Payments did not apply to this site; a site that sells would read that layer against the [vendors at the door](https://agentreadycrawlers.com/vendors/ranking/). [Scan your own domain on Ora](https://ora.ai/?utm_source=agentreadycrawlers.com&utm_medium=referral&utm_campaign=check) [All 360 checks](https://agentreadycrawlers.com/blog/). One company a day; corrections to [the corrections page](https://agentreadycrawlers.com/corrections/). ** The check we recommend [Ora](https://ora.ai/?utm_source=agentreadycrawlers.com&utm_medium=referral&utm_campaign=check) scans a public URL: 16 Discovery checks and 42 Access checks, read from its catalog on 2026-11-05. Its Journey sends a real agent to the site. [How to run it](https://agentreadycrawlers.com/guides/test-whether-ai-agents-can-reach-your-site/). **Limits.** Ora reads public URLs only, and what it records as blocked comes from its own network. It says the same scan run twice converges within a couple of points ([Ora's Deep Scan post](https://ora.ai/blog/introducing-deep-scan?utm_source=agentreadycrawlers.com&utm_medium=referral&utm_campaign=check)), and the pages we read give no repeat-scan figures. Its fixing product is behind a waitlist ([Ora's home page](https://ora.ai/?utm_source=agentreadycrawlers.com&utm_medium=referral&utm_campaign=check)). ## Sources - [Ora's scan of theatlantic.com, GET /api/score (vendor)](https://ora.ai/api/score/theatlantic.com?utm_source=agentreadycrawlers.com&utm_medium=referral&utm_campaign=check) read 2026-11-12 - [Ora's scoring rules, version 3 (vendor)](https://ora.ai/api/ranker/releases/3/rules?utm_source=agentreadycrawlers.com&utm_medium=referral&utm_campaign=check) read 2026-11-12 - [Ora's check catalog, GET /api/checks (vendor)](https://ora.ai/api/checks?utm_source=agentreadycrawlers.com&utm_medium=referral&utm_campaign=check) read 2026-11-05 - [The Atlantic home page](https://www.theatlantic.com/) read 2026-11-12 - [How to test whether AI agents can reach your site (this site)](https://agentreadycrawlers.com/guides/test-whether-ai-agents-can-reach-your-site/) read 2026-11-04 - [Ora: Deep Scan v2 (vendor)](https://ora.ai/blog/introducing-deep-scan?utm_source=agentreadycrawlers.com&utm_medium=referral&utm_campaign=check) read 2026-11-05 - [Ora home page, waitlist (vendor)](https://ora.ai/?utm_source=agentreadycrawlers.com&utm_medium=referral&utm_campaign=check) read 2026-11-05 Last reviewed 2026-11-12