NVIDIA: the 360 agent-readiness check
NVIDIA scores 77 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. The largest home page of the sixty, and an MCP server that is only a mention.
On 9 November 2026 the public site at nvidia.com scored 77 of 100 on Ora's agent-readiness scan, a B, in Ora's AI & ML 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: Nvidia excels at developer resource discoverability and SDK distribution, but lacks WebMCP support for agent integration.
The score
| Layer | Asks | Points | Share |
|---|---|---|---|
| Usability | Can agents use it | 35 of 51 | 69% |
| Access | Can agents read it | 38 of 50 | 76% |
| Discovery | Can agents find and recommend it | 14 of 15 | 93% |
| Payments | Can agents pay | 0 of 0 | none apply |
| Total | Grade B | 77 of 100 | 77% |
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, NVIDIA 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.
| Check | Result | Points | What Ora saw |
|---|---|---|---|
| MCP server / manifest mcp-server | Partial | 2 of 6 | MCP mentioned at https://docs.nvidia.com/switch-infrastructure/config-manager/config-manager/overview/mcp but no standard manifest endpoint found |
| MCP well-known discovery mcp-well-known-discovery | Fail | 0 of 2 | No MCP server URL discovered |
| Public API with reachable endpoints public-api | Pass | 7 of 7 | REST API documentation found at /docs/api. Best-of-protocols score: 7/7. |
| Public API/docs linked from homepage public-api-docs | Pass | 3 of 3 | Documentation site found at https://docs.nvidia.com |
| Developer portal developer-portal | Pass | 6 of 6 | Developer portal found at /developer |
| API catalog (RFC 9727) api-catalog-rfc9727 | Fail | 0 of 2 | No /.well-known/api-catalog found (RFC 9727) |
| OAuth 2.0 support oauth-support | Pass | 5 of 5 | OpenID Connect discovery endpoint found at https://login.nvidia.com |
| auth.md exists auth-md-exists | Fail | 0 of 2 | No /auth.md found at site root |
| WebMCP support webmcp | Fail | 0 of 5 | No WebMCP support detected - no document.modelContext / navigator.modelContext usage found (scanned 12 of 12 same-origin script bundle(s) for modelContext registrations) |
| NLWeb /ask endpoint nlweb-ask | Fail | 0 of 1 | No NLWeb-conformant /ask endpoint found via GET or POST |
| CLI tool available cli-tool | Pass | 3 of 3 | CLI package found on npm: @nvidia/foundations-react-core |
| Multi-language SDK packages rest-sdk-packages | Partial | 1 of 3 | SDK package found only in npm |
| JSON error responses json-error-responses | Fail | 0 of 4 | API does not return JSON error responses (or no API detected) |
At the door
What the site answers when a request arrives with an agent's user agent, and what robots.txt says to agents. One check in this group does not apply to this site and is left out.
| Check | Result | Points | What Ora saw |
|---|---|---|---|
| Not blocked by bot detection bot-detection | Pass | 2 of 2 | Site accessible to 4 agent user-agents (ChatGPT-User, OAI-SearchBot, Claude-User, PerplexityBot). |
| Agent crawler reachability agent-crawler-reachability | Pass | 2 of 2 | Reachable to every agent we tested - ChatGPT-User: reachable, OAI-SearchBot: reachable, Claude-User: reachable, PerplexityBot: reachable |
| robots.txt AI crawler policy robots-ai-policy-quality | Pass | 2 of 2 | AI 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-policy | Pass | 2 of 2 | No applicable crawl or usage restriction found for 3 user-triggered agents (chatgpt-user, claude-user, perplexity-user) on 1 public page: https://nvidia.com/. Declared policy only; |
| Content behind auth docs-auth-gate | Pass | 2 of 2 | All 5 sampled pages are publicly readable (5 with substantive content) |
| Homepage not hidden from search noindex-directives | Pass | 1 of 1 | No noindex on the homepage: no robots, googlebot or bingbot meta tag and no X-Robots-Tag header hides it from search. |
| Redirect hygiene redirect-hygiene | Pass | 1 of 1 | no detail published |
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.
| Check | Result | Points | What Ora saw |
|---|---|---|---|
| Content without JavaScript content-no-js | Pass | 3 of 3 | Homepage: 21731 chars, semantic headings (1 H1 + 8 H2s + 83 H3s), 5.4% content ratio. 5 of 5 sampled inner pages have text without JavaScript. |
| Page token budget page-token-budget | Pass | 1 of 1 | All 6 measured pages fit an agent context budget (largest ~5K tokens) |
| Sitemap exists sitemap | Pass | 2 of 2 | Valid sitemap found at https://www.nvidia.com/sitemap_index.xml with multiple sitemaps entries |
| Sitemap freshness (lastmod) sitemap-lastmod | Pass | 1 of 1 | no detail published |
| llms.txt exists llms-txt-exists | Pass | 1 of 1 | Found the llms.txt at https://docs.nvidia.com/llms.txt. |
| llms.txt formatting llms-txt-formatting | Pass | 2 of 2 | The llms.txt is well-formatted: 224 lines with markdown links, 18,321 characters in total. |
| llms.txt links resolve llms-txt-links-resolve | Pass | 2 of 2 | no detail published |
| Markdown agent docs markdown-negotiation | 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 markdown-url-fallback | Fail | 0 of 2 | Homepage does not support the .md suffix. Probed https://nvidia.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 agent-ua-markdown | 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. |
| Agent mode view agent-mode-view | Fail | 0 of 2 | ?mode=agent returns same content as homepage (no dedicated agent view) |
| JSON-LD structured data json-ld | Partial | 1 of 4 | JSON-LD found (1 block(s)) but no identity type - use SoftwareApplication, Product, Organization, Person, or Article so agents can tell what this site is |
| Organization schema completeness org-schema-completeness | Fail | 0 of 2 | No Organization type found in JSON-LD |
| JSON-LD entity linking (sameAs) json-ld-entity-linking | Partial | 1 of 2 | Entity linking to linkedin.com - add more authority profiles (Wikipedia, Wikidata, LinkedIn, GitHub) |
| Schema type breadth schema-type-breadth | Fail | 0 of 2 | No extended schema types found - AI can only answer basic questions about this entity |
| Metadata completeness metadata-completeness | Pass | 2 of 2 | All metadata signals present: canonical URL, lang="en-us", og:image, og:type |
| Agent instruction / when-to-use agent-instruction | Partial | 2 of 3 | When-to-use guidance found at https://docs.nvidia.com |
Found and recommended
Whether an assistant can find the company by name, confirm what it is, and see it in the registries agents read. 3 checks in this group do not apply to this site and are left out.
| Check | Result | Points | What Ora saw |
|---|---|---|---|
| Brand name discoverability brand-search-accuracy | Pass | 3 of 3 | nvidia.com ranks #1 for "NVIDIA GPU computing" |
| Wikipedia / Wikidata entity presence wikipedia-presence | Pass | 4 of 4 | Wikipedia "Nvidia" and Wikidata Q182477 both verified - domain confirmed on both sources |
| Developer resource discoverability agentic-search-specific | Pass | 3 of 3 | no detail published |
| NPM/PyPI SDK package npm-sdk-package | Pass | 1 of 1 | no detail published |
| Listed on skills.sh skills-sh-listed | Pass | 1 of 1 | no detail published |
| ARD discovery ard-catalog | Fail | 0 of 1 | No /.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 nvidia.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 NVIDIA, 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.
- WebMCP support: fail, 0 of 5, about 4.4 points to gain. Ora saw: No WebMCP support detected - no document.modelContext / navigator.modelContext usage found (scanned 12 of 12 same-origin script bundle(s) for modelContext registrations)
- JSON error responses: fail, 0 of 4, about 3.5 points to gain. Ora saw: API does not return JSON error responses (or no API detected)
- MCP server / manifest: partial, 2 of 6, about 3.5 points to gain. Ora saw: MCP mentioned at https://docs.nvidia.com/switch-infrastructure/config-manager/config-manager/overview/mcp but no standard manifest endpoint found
- JSON-LD structured data: partial, 1 of 4, about 2 points to gain. Ora saw: JSON-LD found (1 block(s)) but no identity type - use SoftwareApplication, Product, Organization, Person, or Article so agents can tell what this site is
- Pricing info accessible: fail, 0 of 3, about 2 points to gain. Ora saw: No pricing page or pricing data found
Our read
NVIDIA's corporate domain is a hardware company's site read by a software checklist, and it does better than that framing suggests. The home page is the largest in this directory, 21,731 characters at a 5.4 percent text ratio with one H1, eight H2s and eighty-three H3s, five of five sampled pages read, docs.nvidia.com carries an llms.txt and the REST documentation scores 7 of 7; OpenID Connect discovery is at login.nvidia.com. The MCP credit stops at a mention in the switch-infrastructure documentation, with no endpoint at a URL Ora could discover, and three probes were answered 403 by a bot shield, the OpenAPI specification, the A2A agent card and the agent skills index, so those rows are unverified. The JSON-LD on the home page has no identity type, there is no pricing information and none of the twelve script bundles registers a WebMCP tool. The domain ranks first for GPU computing. The act layer here is the chips, and the site says so.
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 70All 360 checks, one company a day. Corrections to the corrections page.