Brex: the 360 agent-readiness check
Brex scores 48 of 100 on Ora's agent-readiness scan, a C, read 13 November 2026. Of the five surfaces an agent acts on, Ora found 1: a public API. An open door, a 256,923-character llms.txt, and no MCP server in front of the API.
On 13 November 2026 the public site at brex.com scored 48 of 100 on Ora's agent-readiness scan, a C, in Ora's Payments & Fintech 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: Brex offers a discoverable developer resource base and SDK packages, but lacks an MCP server and OpenAPI spec for agents to connect through.
The score
| Layer | Asks | Points | Share |
|---|---|---|---|
| Usability | Can agents use it | 12 of 54 | 22% |
| Access | Can agents read it | 29.17 of 46 | 63% |
| Discovery | Can agents find and recommend it | 10 of 13 | 77% |
| Payments | Can agents pay | 0 of 0 | none apply |
| Total | Grade C | 48 of 100 | 48% |
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. 2 checks in this group do not apply to this site and are left out.
Brex is not in the directory's edition of 4 November 2026: no source read for that run named an MCP endpoint for brex.com, so the MCP evidence here is Ora's alone. Its MCP server check reads fail.
| Check | Result | Points | What Ora saw |
|---|---|---|---|
| MCP server / manifest mcp-server | Fail | 0 of 10 | No MCP server or manifest 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 | 8 of 8 | REST API documentation found at /api. Best-of-protocols score: 7/7. |
| Public API/docs linked from homepage public-api-docs | Pass | 4 of 4 | Documentation site found at https://developer.brex.com |
| Developer portal developer-portal | Pass | 5 of 5 | Developer portal found at https://developer.brex.com |
| OpenAPI spec published openapi-spec | Fail | 0 of 8 | No OpenAPI/Swagger specification found |
| API catalog (RFC 9727) api-catalog-rfc9727 | Fail | 0 of 2 | No /.well-known/api-catalog found (RFC 9727) |
| A2A / agent-card a2a-agent-card | Fail | 0 of 2 | No A2A agent card found at /.well-known/agent-card.json |
| Agent discovery file agent-discovery-file | Fail | 0 of 2 | No agent discovery file found |
| OAuth 2.0 support oauth-support | Fail | 0 of 5 | No OAuth 2.0 or OpenID Connect support detected |
| OAuth Protected Resource metadata (RFC 9728) oauth-protected-resource | Fail | 0 of 2 | No /.well-known/oauth-protected-resource found (RFC 9728) |
| auth.md exists auth-md-exists | Fail | 0 of 2 | No /auth.md found at site root |
| WebMCP support webmcp | Fail | 0 of 8 | No WebMCP support detected - no document.modelContext / navigator.modelContext usage found (scanned 52 of 52 same-origin script bundle(s) for modelContext registrations) |
| NLWeb /ask endpoint nlweb-ask | Pass | 1 of 1 | NLWeb /ask endpoint exists but requires authentication (HTTP 403, via POST) |
| CLI tool available cli-tool | Fail | 0 of 3 | No CLI tool found |
| JSON error responses json-error-responses | Fail | 0 of 3 | 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.
| 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 | 1 of 1 | 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 | 1 of 1 | 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 | 1 of 1 | No applicable crawl or usage restriction found for 3 user-triggered agents (chatgpt-user, claude-user, perplexity-user) on 1 public page: https://brex.com/. Declared policy only; |
| Content behind auth docs-auth-gate | Pass | 1 of 1 | 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 |
| Web Bot Auth directory 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.
| Check | Result | Points | What Ora saw |
|---|---|---|---|
| Content without JavaScript content-no-js | Partial | 1.67 of 5 | Homepage: 5588 chars with H1, but heading hierarchy skips H2 to H4; 4.4% content ratio is below the 5% target. Sampled pages with almost no text without JavaScript (2 of 9):. |
| Page token budget page-token-budget | Pass | 1 of 1 | All 13 measured pages fit an agent context budget (largest ~9K tokens) |
| Sitemap exists sitemap | Pass | 1 of 1 | Valid sitemap found at https://www.brex.com/sitemap/sitemap.xml with 1493 entries |
| llms.txt exists llms-txt-exists | Pass | 1 of 1 | Found the llms.txt at https://developer.brex.com/llms.txt. |
| llms.txt formatting llms-txt-formatting | Fail | 0 of 2 | The llms.txt at https://brex.com/llms.txt is 256,923 characters. Agents truncate an llms.txt past 100,000 characters, so the links after that point are never read. |
| llms.txt links resolve llms-txt-links-resolve | Pass | 2 of 2 | no detail published |
| Markdown agent docs markdown-negotiation | Pass | 1 of 1 | Path-suffix markdown docs served with text/markdown content-type: /api.md, /index.md |
| Markdown URL fallback markdown-url-fallback | Pass | 2 of 2 | no detail published |
| 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. |
| JSON-LD structured data json-ld | Partial | 0.5 of 2 | 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 1 | No Organization type found in JSON-LD |
| JSON-LD entity linking (sameAs) json-ld-entity-linking | Fail | 0 of 1 | No sameAs entity linking in JSON-LD - agents cannot disambiguate your brand |
| Metadata completeness metadata-completeness | Pass | 1 of 1 | All metadata signals present: canonical URL, lang="en-US", og:image, og:type |
| Agent instruction / when-to-use agent-instruction | Pass | 1 of 1 | no detail published |
Found and recommended
Whether an assistant can find the company by name, confirm what it is, and see it in the registries agents read. 2 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 | Partial | 1 of 3 | brex.com ranks #7 for "Brex" (searched your brand name alone: no main product term from your homepage qualified) |
| Developer resource discoverability agentic-search-specific | Pass | 4 of 4 | no detail published |
| NPM/PyPI SDK package npm-sdk-package | Pass | 1 of 1 | no detail published |
| ChatGPT app listed chatgpt-app-listed | Pass | 2 of 2 | no detail published |
| Listed on skills.sh skills-sh-listed | Fail | 0 of 1 | No official skills self-published on skills.sh (14 community skills with potential relation to this domain found, but only self-published official skills count) |
| 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 brex.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 Brex, 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.
- MCP server / manifest: fail, 0 of 10, about 8.2 points to gain. Ora saw: No MCP server or manifest found
- WebMCP support: fail, 0 of 8, about 6.6 points to gain. Ora saw: No WebMCP support detected - no document.modelContext / navigator.modelContext usage found (scanned 52 of 52 same-origin script bundle(s) for modelContext registrations)
- OpenAPI spec published: fail, 0 of 8, about 5.8 points to gain. Ora saw: No OpenAPI/Swagger specification found
- OAuth 2.0 support: fail, 0 of 5, about 4.1 points to gain. Ora saw: No OAuth 2.0 or OpenID Connect support detected
- Scoped permissions: fail, 0 of 5, about 4.1 points to gain. Ora saw: No declared OAuth scopes, security schemes, or scoped-permission documentation found
Our read
Brex has the API and none of the plumbing that lets an agent pick it up unaided. Ora found REST documentation at /api, scored 7 of 7 on the protocol check, and a developer portal at developer.brex.com, but neither an MCP server nor an OpenAPI specification; OAuth, OpenID Connect, declared scopes and a CLI are all missing too, and an NLWeb /ask endpoint answers 403 without authentication. Usability reads 12 of 54. The door is wide open: ChatGPT-User, OAI-SearchBot, Claude-User and PerplexityBot all reached the home page, and robots.txt allows the AI search crawlers in 3 of 3 checks. The reading layer is generous to a fault: the llms.txt at brex.com runs to 256,923 characters, far past the 100,000 at which agents truncate one, while the docs serve markdown at paths such as /api.md. The fix worth most is an MCP server, about 8.2 points. A C at 48: the docs are public, and an agent still needs a person to wire them up.
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.