Agent MCP Directory

Box: the 360 agent-readiness check

Box scores 80 of 100 on Ora's agent-readiness scan, a B, read 9 November 2026. Of the five surfaces an agent acts on, Ora found 3: a public API, OAuth, a command line. A finished-looking act layer behind a shield that stopped three probes.

On 9 November 2026 the public site at box.com scored 80 of 100 on Ora's agent-readiness scan, a B, in Ora's Productivity 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. This check reads the act layer first, because that is what the directory records, then the door, what an agent can read, and whether the company is found and recommended. Ora's one-line summary: Box offers strong REST API access and comprehensive developer documentation, but lacks machine-readable OAuth2 scope declarations.

The score

Box on Ora, read 2026-11-09: points per layer, with the share of each layer's maximum. 46 checks pass, 14 are partial, 21 fail and 51 do not apply to this site.
LayerAsksPointsShare
UsabilityCan agents use it74 of 9380%
AccessCan agents read it38 of 4584%
DiscoveryCan agents find and recommend it12 of 1675%
PaymentsCan agents pay0 of 0none apply
TotalGrade B80 of 10080%

What an agent can do

The surfaces an agent acts on: an API it can find and call, an MCP server, an agent card, OAuth metadata, a command line. This is the layer the directory records, so it comes first. 6 checks in this group do not apply to this site and are left out.

In the directory, Box sign-in required, tools not seen, not counted; the connector run of 4 November 2026 is on the entry page. Ora's MCP server check for the same domain reads partial; the two look for different things, the directory for a server that answers a handshake and lists tools, Ora for a server it can find from the site.

What an agent can do: 13 checks Ora ran on box.com, read 2026-11-09. The last column is Ora's own observation where it published one.
CheckResultPointsWhat Ora saw
MCP server / manifest mcp-serverPartial5 of 6MCP server detected at https://mcp.box.com; 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 mcp-well-known-discoveryPartial1 of 2MCP server at https://mcp.box.com - list its server card, hosted on your own domain, in /.well-known/ai-catalog.json so MCP clients can discover it
Public API with reachable endpoints public-apiPass7 of 7REST API documentation found at https://docs.box.com/_llms/en/home.txt. GraphQL endpoint at https://api.box.com/v1/graphql is reachable; introspection requires authentication (API key / OAuth),
Public API/docs linked from homepage public-api-docsPass3 of 3Documentation site found at https://docs.box.com
Developer portal developer-portalPass6 of 6Developer documentation portal found at https://docs.box.com
API catalog (RFC 9727) api-catalog-rfc9727Fail0 of 2No /.well-known/api-catalog found (RFC 9727)
A2A / agent-card a2a-agent-cardFail0 of 2No A2A agent card found at /.well-known/agent-card.json
OAuth 2.0 support oauth-supportPass5 of 5OAuth authorization server metadata at https://api.box.com
OAuth Protected Resource metadata (RFC 9728) oauth-protected-resourcePass2 of 2no detail published
NLWeb /ask endpoint nlweb-askPass1 of 1NLWeb /ask endpoint exists but requires authentication (HTTP 403, via GET)
CLI tool available cli-toolPass3 of 3CLI package found on npm: @box/cli
Multi-language SDK packages rest-sdk-packagesPartial1 of 3SDK package found only in npm
Idempotency-Key support idempotency-key-supportFail0 of 3GraphQL introspection auth-gated and no idempotency documentation found on GraphQL-tagged pages

At the door

What the site answers when a request arrives with an agent's user agent, and what robots.txt says to agents.

At the door: 8 checks Ora ran on box.com, read 2026-11-09. The last column is Ora's own observation where it published one.
CheckResultPointsWhat Ora saw
Not blocked by bot detection bot-detectionPass2 of 2Site accessible to 4 agent user-agents (ChatGPT-User, OAI-SearchBot, Claude-User, PerplexityBot).
Agent crawler reachability agent-crawler-reachabilityPass2 of 2Reachable to every agent we tested - ChatGPT-User: reachable, OAI-SearchBot: reachable, Claude-User: reachable, PerplexityBot: reachable
robots.txt AI crawler policy robots-ai-policy-qualityPass2 of 2AI search crawlers: allowed in 3 of 3 checks (3 crawlers on 1 page). AI training crawlers: allowed in 2 of 2 checks (2 crawlers on 1 page), not scored.
robots.txt agent-user policy robots-agent-user-policyPass2 of 2No applicable crawl or usage restriction found for 3 user-triggered agents (chatgpt-user, claude-user, perplexity-user) on 1 public page: https://box.com/. Declared policy only;
Content behind auth docs-auth-gatePass2 of 2All 5 sampled pages are publicly readable (1 with substantive content)
Homepage not hidden from search noindex-directivesPass1 of 1No noindex on the homepage: no robots, googlebot or bingbot meta tag and no X-Robots-Tag header hides it from search.
Redirect hygiene redirect-hygienePartial0 of 1Redirect hygiene issues: https://www.box.com/customer-success/support-services uses a meta-refresh redirect, https://www.box.com/industries/cpg uses a meta-refresh redirect, and https://www.box.com/overview uses a meta-refresh redirect.
Web Bot Auth directory web-bot-auth-directoryFail0 of 2No /.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.

What an agent can read: 14 checks Ora ran on box.com, read 2026-11-09. The last column is Ora's own observation where it published one.
CheckResultPointsWhat Ora saw
Content without JavaScript content-no-jsPartial2 of 35226 chars with H1, but heading hierarchy skips H1 to H3
Page token budget page-token-budgetPartial0 of 11 of 3 measured pages exceed ~25K tokens of extracted text: https://developer.box.com/sample-code/ (~26K tokens). Agents truncate what does not fit - split these into focused pages.
Sitemap exists sitemapPass2 of 2Valid sitemap found at https://www.box.com/sitemap.xml with multiple sitemaps entries
llms.txt exists llms-txt-existsPass1 of 1Found the llms.txt at https://docs.box.com/llms.txt.
llms.txt formatting llms-txt-formattingPass2 of 2The llms.txt is well-formatted: 56 lines with markdown links, 7,005 characters in total.
llms.txt links resolve llms-txt-links-resolvePass2 of 2no detail published
Markdown agent docs markdown-negotiationFail0 of 1Missing 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,
Bot-UA markdown serving agent-ua-markdownFail0 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.
Agent mode view agent-mode-viewPass2 of 2no detail published
JSON-LD structured data json-ldPass4 of 4Rich JSON-LD identity: Organization with name, description, url, and sameAs/logo/address (1 block(s))
Organization schema completeness org-schema-completenessPass2 of 2no detail published
JSON-LD entity linking (sameAs) json-ld-entity-linkingPartial1 of 2Entity linking to linkedin.com - add more authority profiles (Wikipedia, Wikidata, LinkedIn, GitHub)
Schema type breadth schema-type-breadthFail0 of 2No extended schema types found - AI can only answer basic questions about this entity
Metadata completeness metadata-completenessPass2 of 2All metadata signals present: canonical URL, lang="en", og:image, og:type

Found and recommended

Whether an assistant can find the company by name, confirm what it is, and see it in the registries agents read. One check in this group does not apply to this site and is left out.

Found and recommended: 8 checks Ora ran on box.com, read 2026-11-09. The last column is Ora's own observation where it published one.
CheckResultPointsWhat Ora saw
Brand name discoverability brand-search-accuracyPartial1 of 3box.com ranks #7 for "Box content management"
Wikipedia / Wikidata entity presence wikipedia-presencePartial2 of 4Wikidata Q4951483 (Box) verified - draft a Wikipedia page with cited references to complete knowledge graph coverage
Developer resource discoverability agentic-search-specificPass3 of 3no detail published
Listed in MCP registries mcp-registry-listedFail0 of 1No bi-directionally verified MCP registry entry found. To pass, either publish the server from a package whose homepage, repository or maintainer email names your domain, get a verified Smithery listing with non-zero usage,
NPM/PyPI SDK package npm-sdk-packagePass1 of 1no detail published
ChatGPT app listed chatgpt-app-listedPass2 of 2no detail published
Listed on skills.sh skills-sh-listedPass1 of 1no detail published
ARD discovery ard-catalogFail0 of 1No /.well-known/ard.json, no same-site rel="ard" link, and no legacy /.well-known/ai-catalog.json

Payments

The agent payment protocols Ora probes for. A site that sells nothing has nothing here, and Ora scores the layer out of zero when none applies. None of the 6 payment checks applied to box.com.

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 Box, with what Ora observed. The wording of each fix is Ora's; the 28 checks it runs on an MCP server are listed with their layer and tier.

  • Brand name discoverability: partial, 1 of 3, about 2.8 points to gain. Ora saw: box.com ranks #7 for "Box content management"
  • Schema type breadth: fail, 0 of 2, about 1.5 points to gain. Ora saw: No extended schema types found - AI can only answer basic questions about this entity
  • ARD discovery: fail, 0 of 1, about 1.4 points to gain. Ora saw: No /.well-known/ard.json, no same-site rel="ard" link, and no legacy /.well-known/ai-catalog.json
  • GraphQL typed error model: fail, 0 of 3, about 1.4 points to gain. Ora saw: GraphQL introspection auth-gated and no typed graphql error model documentation found on GraphQL-tagged pages
  • Idempotency-Key support: fail, 0 of 3, about 1.4 points to gain. Ora saw: GraphQL introspection auth-gated and no idempotency documentation found on GraphQL-tagged pages

Our read

Box's B is earned on the surfaces Ora could reach and clouded by the ones it could not. The MCP server at mcp.box.com answers and requires authentication, OAuth authorization server metadata is at api.box.com, the REST documentation at docs.box.com carries an llms.txt, @box/cli is on npm and the Organization block on the home page is complete. Three probes were answered 403 by a bot shield, the OpenAPI specification at /api-docs and /v2/api-docs, the agent discovery file and the skills listing, so those rows are unverified and drop out of the maximum, which is why Access reads 38 of 45 and the Usability share is high. The WebMCP check could read none of the one script bundle. The deductions Ora could confirm are small: a gated GraphQL introspection without a typed error model, neither an ARD catalog nor extended schema types, and a heading tree that skips from H1 to H3. The shield decides this read; the act layer behind it looks finished.

Test your own surfaces

The scan above is free and needs no account: enter a domain at ora.ai and read the same four layers for your own site. For an MCP server, Ora scans the server URL itself and runs 28 of its 132 public checks on it, which is why it is the check this directory recommends; the reasons, the limits and the alternatives are on their own 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.

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

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