Mercury: the 360 agent-readiness check
Mercury scores 74 of 100 on Ora's agent-readiness scan, a B, read 14 November 2026. Of the five surfaces an agent acts on, Ora found 2: a public API, OAuth. A live MCP server behind OAuth and a tidy llms.txt, still waiting on an OpenAPI specification.
On 14 November 2026 the public site at mercury.com scored 74 of 100 on Ora's agent-readiness scan, a B, 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: Mercury offers a working MCP server and docs with clear discoverability, but lacks a published OpenAPI spec for agents to discover its endpoints.
The score
| Layer | Asks | Points | Share |
|---|---|---|---|
| Usability | Can agents use it | 62.209999999999994 of 86 | 72% |
| Access | Can agents read it | 33.83 of 45 | 75% |
| Discovery | Can agents find and recommend it | 14 of 18 | 78% |
| Payments | Can agents pay | 0 of 0 | none apply |
| Total | Grade B | 74 of 100 | 74% |
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.
Mercury is not in the directory's edition of 4 November 2026: no source read for that run named an MCP endpoint for mercury.com, so the MCP evidence here is Ora's alone. Its MCP server check reads partial.
| Check | Result | Points | What Ora saw |
|---|---|---|---|
| MCP server / manifest mcp-server | Partial | 8.33 of 10 | MCP server detected at https://mcp.mercury.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 mcp-well-known-discovery | Pass | 2 of 2 | MCP server discoverable via server-card.json at /.well-known/mcp/ |
| Public API with reachable endpoints public-api | Pass | 8 of 8 | REST API documentation found at https://docs.mercury.com/docs/welcome.md. Best-of-protocols score: 7/7. |
| Public API/docs linked from homepage public-api-docs | Pass | 4 of 4 | Documentation site found at https://docs.mercury.com |
| Developer portal developer-portal | Pass | 5 of 5 | Developer portal found at /dashboard |
| OpenAPI spec published openapi-spec | Fail | 0 of 8 | No OpenAPI/Swagger specification found |
| API catalog (RFC 9727) api-catalog-rfc9727 | Partial | 1 of 2 | api-catalog linkset[0] has no 'item' entries |
| 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 | Pass | 5 of 5 | OAuth authorization server metadata at https://mcp.mercury.com/ |
| OAuth Protected Resource metadata (RFC 9728) oauth-protected-resource | Pass | 2 of 2 | no detail published |
| auth.md exists auth-md-exists | Pass | 2 of 2 | no detail published |
| WebMCP support webmcp | Fail | 0 of 8 | No WebMCP support detected - no document.modelContext / navigator.modelContext usage found (scanned 37 of 37 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 | Fail | 0 of 3 | No CLI tool found |
| JSON error responses json-error-responses | Pass | 3 of 3 | no detail published |
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 12 of 12 checks (3 crawlers on 4 pages). AI training crawlers: allowed in 8 of 8 checks (2 crawlers on 4 pages), 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://mercury.com/. Declared policy only; |
| Content behind auth docs-auth-gate | Pass | 1 of 1 | All 3 sampled pages are publicly readable (3 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 | 3.33 of 5 | Homepage: 5765 chars with H1, but heading hierarchy skips H1 to H3; 1.8% content ratio is below the 5% target. 4 of 4 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 ~13K tokens) |
| Sitemap exists sitemap | Pass | 1 of 1 | Valid sitemap found at https://mercury.com/sitemap.xml with 166 entries |
| llms.txt exists llms-txt-exists | Pass | 1 of 1 | Found the llms.txt at https://docs.mercury.com/llms.txt. |
| llms.txt formatting llms-txt-formatting | Pass | 2 of 2 | The llms.txt is well-formatted: 156 lines with markdown links, 22,236 characters in total. |
| 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: /auth.md |
| Markdown URL fallback markdown-url-fallback | Fail | 0 of 2 | Homepage does not support the .md suffix. Probed https://mercury.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. |
| JSON-LD structured data json-ld | Partial | 1.5 of 2 | JSON-LD Organization found - missing description on this entity |
| Organization schema completeness org-schema-completeness | Pass | 1 of 1 | no detail published |
| JSON-LD entity linking (sameAs) json-ld-entity-linking | Pass | 1 of 1 | no detail published |
| Metadata completeness metadata-completeness | Pass | 1 of 1 | All metadata signals present: canonical URL, lang="en", og:image, og:type |
| Agent instruction / when-to-use agent-instruction | Fail | 0 of 1 | No agent instruction file with when-to-use guidance found |
Found and recommended
Whether an assistant can find the company by name, confirm what it is, and see it in the registries agents read.
| Check | Result | Points | What Ora saw |
|---|---|---|---|
| Brand name discoverability brand-search-accuracy | Pass | 3 of 3 | mercury.com ranks #4 for "Mercury" (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 |
| Listed in MCP registries mcp-registry-listed | 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, |
| NPM/PyPI SDK package npm-sdk-package | Fail | 0 of 1 | No NPM or PyPI SDK package found |
| ChatGPT app listed chatgpt-app-listed | Pass | 2 of 2 | no detail published |
| Registry branding registry-branding | Partial | 1 of 2 | MCP manifest has name and description but no icon at /.well-known/mcp/server-card.json |
| Listed on skills.sh skills-sh-listed | Fail | 0 of 1 | No official skills self-published on skills.sh (100 community skills with potential relation to this domain found, but only self-published official skills count) |
| ARD discovery ard-catalog | Pass | 1 of 1 | no detail published |
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 mercury.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 Mercury, 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.
- OpenAPI spec published: fail, 0 of 8, about 5.9 points to gain. Ora saw: No OpenAPI/Swagger specification found
- WebMCP support: fail, 0 of 8, about 4.1 points to gain. Ora saw: No WebMCP support detected - no document.modelContext / navigator.modelContext usage found (scanned 37 of 37 same-origin script bundle(s) for modelContext registrations)
- Listed in MCP registries: fail, 0 of 3, about 3.7 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,
- CLI tool available: fail, 0 of 3, about 1.6 points to gain. Ora saw: No CLI tool found
- Content without JavaScript: partial, 3.33 of 5, about 1.2 points to gain. Ora saw: Homepage: 5765 chars with H1, but heading hierarchy skips H1 to H3; 1.8% content ratio is below the 5% target. 4 of 4 sampled inner pages have text without JavaScript.
Our read
Mercury has done the hard part of the act layer and skipped the paperwork. An MCP server answers at mcp.mercury.com/mcp behind authentication, it is discoverable through a server card at /.well-known/mcp/, and OAuth authorization server metadata sits on the same host; the REST documentation at docs.mercury.com scores 7 of 7 on the protocol check, and docs pages come as markdown at paths such as /auth.md. What is missing is a description an agent can load: Ora found neither an OpenAPI specification nor an entry in the MCP Registry or on Smithery, and there is no CLI or SDK package. The Usability layer reads about 62 of 86. The door is open to ChatGPT-User, OAI-SearchBot, Claude-User and PerplexityBot, and robots.txt allows the AI search crawlers in 12 of 12 checks. The llms.txt is well formed, 156 lines in 22,236 characters. The fix worth most is an OpenAPI specification, about 5.9 points. A B at 74: the server is live, and the map of the API behind it is still unpublished.
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.