Agent MCP Directory

Wise: the 360 agent-readiness check

Wise scores 77 of 100 on Ora's agent-readiness scan, a B, read 11 November 2026. Of the five surfaces an agent acts on, Ora found 3: a public API, OAuth, a command line. A live MCP server, a 7 of 7 API, and no declared OAuth scopes.

On 11 November 2026 the public site at wise.com scored 77 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: Wise offers a broad API, MCP server, and SDK packages, but lacks declared OAuth scopes and scoped-permission documentation for agents.

The score

Wise on Ora, read 2026-11-11: points per layer, with the share of each layer's maximum. 33 checks pass, 15 are partial, 27 fail and 63 do not apply to this site.
LayerAsksPointsShare
UsabilityCan agents use it35.33 of 5071%
AccessCan agents read it37.04 of 4582%
DiscoveryCan agents find and recommend it11.67 of 1483%
PaymentsCan agents pay0 of 0none apply
TotalGrade B77 of 10077%

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. 4 checks in this group do not apply to this site and are left out.

Wise is not in the directory's edition of 4 November 2026: no source read for that run named an MCP endpoint for wise.com, so the MCP evidence here is Ora's alone. Its MCP server check reads partial.

What an agent can do: 14 checks Ora ran on wise.com, read 2026-11-11. The last column is Ora's own observation where it published one.
CheckResultPointsWhat Ora saw
MCP server / manifest mcp-serverPartial8.33 of 10MCP server detected at https://mcp.wise.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-discoveryPartial1 of 2MCP server at https://mcp.wise.com/mcp - 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-apiPass8 of 8REST API documentation found at https://docs.wise.com/guides/developer/language-support.md. Best-of-protocols score: 7/7.
Public API/docs linked from homepage public-api-docsPass4 of 4Documentation site found at https://docs.wise.com
Developer portal developer-portalPass5 of 5Developer documentation portal found at https://docs.wise.com
OpenAPI spec published openapi-specPartial5.71 of 8OpenAPI spec (YAML) found at https://docs.wise.com/_bundle/api-reference/@legacy/webhook/tmp/generated/openapi.yaml
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 endpoint found at https://wise.com/oauth/authorize
OAuth Protected Resource metadata (RFC 9728) oauth-protected-resourcePass2 of 2no detail published
auth.md exists auth-md-existsFail0 of 2No /auth.md found at site root
NLWeb /ask endpoint nlweb-askFail0 of 1No NLWeb-conformant /ask endpoint found via GET or POST
CLI tool available cli-toolPass3 of 3CLI package found on npm: @wise/wds-codemods
JSON error responses json-error-responsesPass3 of 3no 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.

At the door: 8 checks Ora ran on wise.com, read 2026-11-11. 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-reachabilityPass1 of 1Reachable to every agent we tested - ChatGPT-User: reachable, OAI-SearchBot: reachable, Claude-User: reachable, PerplexityBot: reachable
robots.txt AI crawler policy robots-ai-policy-qualityPass1 of 1AI search crawlers: allowed in 9 of 9 checks (3 crawlers on 3 pages). AI training crawlers: allowed in 6 of 6 checks (2 crawlers on 3 pages), not scored.
robots.txt agent-user policy robots-agent-user-policyPass1 of 1No applicable crawl or usage restriction found for 3 user-triggered agents (chatgpt-user, claude-user, perplexity-user) on 1 public page: https://wise.com/. Declared policy only;
Content behind auth docs-auth-gatePass1 of 1All 2 sampled pages are publicly readable (2 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-hygienePass1 of 1no detail published
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.

What an agent can read: 14 checks Ora ran on wise.com, read 2026-11-11. The last column is Ora's own observation where it published one.
CheckResultPointsWhat Ora saw
Content without JavaScript content-no-jsPartial3.33 of 5Homepage: 6856 chars with H1, but heading hierarchy skips H1 to H5; 4.4% content ratio is below the 5% target. 2 of 2 sampled inner pages have text without JavaScript.
Page token budget page-token-budgetPass1 of 1All 3 measured pages fit an agent context budget (largest ~2K tokens)
Sitemap exists sitemapPass1 of 1Valid sitemap found at https://wise.com/sitemap with multiple sitemaps entries
llms.txt exists llms-txt-existsPass1 of 1Found the llms.txt at https://docs.wise.com/llms.txt.
llms.txt formatting llms-txt-formattingPartial1 of 2The llms.txt is well-formatted with markdown links, but at 40,865 characters it exceeds the 30,000-character recommendation for a navigation index.
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,
Markdown URL fallback markdown-url-fallbackFail0 of 2Homepage does not support the .md suffix. Probed https://wise.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-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.
JSON-LD structured data json-ldPartial1 of 2JSON-LD Organization found - missing description on this entity
Organization schema completeness org-schema-completenessPartial0.5 of 1Organization schema found but missing: contactPoint, address
JSON-LD entity linking (sameAs) json-ld-entity-linkingPartial0.5 of 1Entity linking to linkedin.com - add more authority profiles (Wikipedia, Wikidata, LinkedIn, GitHub)
Metadata completeness metadata-completenessPass1 of 1All metadata signals present: canonical URL, lang="en-GB", og:image, og:type
Agent instruction / when-to-use agent-instructionFail0 of 1No 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.

Found and recommended: 8 checks Ora ran on wise.com, read 2026-11-11. The last column is Ora's own observation where it published one.
CheckResultPointsWhat Ora saw
Brand name discoverability brand-search-accuracyPass3 of 3wise.com ranks #5 for "Wise" (searched your brand name alone: no main product term from your homepage qualified)
Developer resource discoverability agentic-search-specificPartial2.67 of 4In a search for your API docs, your docs came up at #2 (https://docs.wise.com/guides/developer). 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 mcp-registry-listedPass3 of 3no detail published
NPM/PyPI SDK package npm-sdk-packagePass1 of 1no detail published
ChatGPT app listed chatgpt-app-listedFail0 of 2Not found in ChatGPT app directory
Registry branding registry-brandingFail0 of 2No registry branding (name, icon, description) found
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 wise.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 Wise, 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.

  • Scoped permissions: fail, 0 of 5, about 4.4 points to gain. Ora saw: No declared OAuth scopes, security schemes, or scoped-permission documentation found
  • Developer resource discoverability: partial, 2.67 of 4, about 2.1 points to gain. Ora saw: In a search for your API docs, your docs came up at #2 (https://docs.wise.com/guides/developer). 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
  • MCP OAuth metadata: fail, 0 of 2, about 1.8 points to gain. Ora saw: OAuth protected-resource metadata was found for https://mcp.wise.com/mcp, but its resource field identifies https://mcp.wise.com/. The resource must exactly match the requested endpoint (RFC 9728).
  • MCP PKCE S256 support: fail, 0 of 2, about 1.8 points to gain. Ora saw: No code_challenge_methods_supported in OAuth metadata for product MCP
  • OpenAPI spec published: partial, 5.71 of 8, about 1.7 points to gain. Ora saw: OpenAPI spec (YAML) found at https://docs.wise.com/_bundle/api-reference/@legacy/webhook/tmp/generated/openapi.yaml

Our read

Wise has built most of the act layer and tripped on the paperwork around it. Ora found an MCP server at mcp.wise.com/mcp that requires authentication and verifies at 5 of 6, an OAuth endpoint, a REST API scoring 7 of 7, a developer portal at docs.wise.com and an OpenAPI file that sits under a webhook path and scores 5.71 of 8. Declared OAuth scopes are missing, the largest gap at about 4.4 points; the server's protected-resource metadata names https://mcp.wise.com/ while the endpoint is /mcp, which RFC 9728 does not allow, and no PKCE S256 method is declared. The door is open: all four test agents got in, and robots.txt allowed the AI search crawlers in 9 of 9 checks. The llms.txt runs 40,865 characters against a 30,000 recommendation. The WebMCP and agent discovery rows are unverified rather than failed, since a bot shield answered with a 403. A B at 77, and the next points sit in a scopes list and one trailing slash.

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.