Agent MCP Directory

GoCardless: the 360 agent-readiness check

GoCardless scores 47 of 100 on Ora's agent-readiness scan, a D, read 9 November 2026. Of the five surfaces an agent acts on, Ora found 2: a public API, a command line. The lowest score of the sixty, six points of it a search for the word cardless.

On 9 November 2026 the public site at gocardless.com scored 47 of 100 on Ora's agent-readiness scan, a D, 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: GoCardless offers SDKs for developers, but lacks an OpenAPI specification.

The score

GoCardless on Ora, read 2026-11-09: points per layer, with the share of each layer's maximum. 28 checks pass, 4 are partial, 57 fail and 37 do not apply to this site.
LayerAsksPointsShare
UsabilityCan agents use it26 of 5448%
AccessCan agents read it34 of 6453%
DiscoveryCan agents find and recommend it8 of 2236%
PaymentsCan agents pay0 of 0none apply
TotalGrade D47 of 10047%

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.

In the directory, GoCardless 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 fail; 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: 17 checks Ora ran on gocardless.com, read 2026-11-09. The last column is Ora's own observation where it published one.
CheckResultPointsWhat Ora saw
MCP server / manifest mcp-serverFail0 of 6No MCP server or manifest found
MCP well-known discovery mcp-well-known-discoveryPass2 of 2MCP server referenced in llms.txt
Public API with reachable endpoints public-apiPass7 of 7REST API documentation found at https://docs.gocardless.com/docs/getting-started. Best-of-protocols score: 7/7.
Public API/docs linked from homepage public-api-docsPass3 of 3Documentation site found at https://docs.gocardless.com
Developer portal developer-portalPass6 of 6Developer portal found at /developers
OpenAPI spec published openapi-specFail0 of 7No OpenAPI/Swagger specification found
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
Agent discovery file agent-discovery-fileFail0 of 2No agent discovery file found
OAuth 2.0 support oauth-supportPartial3 of 5OAuth mentioned in documentation at https://docs.gocardless.com but no OAuth or OpenID Connect endpoint responded
OAuth Protected Resource metadata (RFC 9728) oauth-protected-resourceFail0 of 2No /.well-known/oauth-protected-resource found (RFC 9728)
auth.md exists auth-md-existsFail0 of 2No /auth.md found at site root
WebMCP support webmcpFail0 of 2No WebMCP support detected - no tool-attribute forms and no document.modelContext / navigator.modelContext usage found
NLWeb /ask endpoint nlweb-askFail0 of 1No NLWeb-conformant /ask endpoint found via GET or POST
CLI tool available cli-toolPass3 of 3CLI tool found on PyPI: gocardless
Multi-language SDK packages rest-sdk-packagesPass3 of 3SDK packages found across 3 ecosystems: npm, pypi, rubygems
JSON error responses json-error-responsesFail0 of 4API 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.

At the door: 6 checks Ora ran on gocardless.com, read 2026-11-09. The last column is Ora's own observation where it published one.
CheckResultPointsWhat Ora saw
Agent crawler reachability agent-crawler-reachabilityFail0 of 2No major AI crawler can reach the homepage - ChatGPT-User: unknown, ClaudeBot: unknown, Google-Extended: unknown, ora-agent: unknown, DeepSeekBot: unknown
robots.txt AI crawler policy robots-ai-policy-qualityFail0 of 2No AI crawler directives in robots.txt
robots.txt agent-user policy robots-agent-user-policyPass2 of 2No robots.txt restriction on user-triggered agents - they can read the site
Content behind auth docs-auth-gatePass2 of 2All 5 sampled pages are publicly readable (5 with substantive content)
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: 17 checks Ora ran on gocardless.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-jsPass2 of 37637 chars with H1 but flat heading structure
Page token budget page-token-budgetPass1 of 1All 6 measured pages fit an agent context budget (largest ~3K tokens)
Sitemap exists sitemapPass2 of 2Valid sitemap found at https://gocardless.com/sitemap-index.xml with multiple sitemaps entries
Sitemap freshness (lastmod) sitemap-lastmodFail0 of 1None of the 500 sampled sitemap entries carries a lastmod date. Add <lastmod> (W3C datetime) so agents can prioritize fresh content.
llms.txt exists llms-txt-existsPass1 of 1Found the llms.txt at https://docs.gocardless.com/llms.txt.
llms.txt formatting llms-txt-formattingPass2 of 2The llms.txt is well-formatted: 136 lines with markdown links, 20,693 characters in total.
llms.txt links resolve llms-txt-links-resolvePass2 of 2no detail published
Markdown agent docs markdown-negotiationPass1 of 1Returns markdown when requested via Accept header
Markdown URL fallback markdown-url-fallbackFail0 of 2Homepage does not support the .md suffix. Probed https://gocardless.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 (GPTBot, ClaudeBot, ChatGPT-User, PerplexityBot, Google-Extended, Applebot-Extended, ora-agent, DeepSeekBot) receives markdown when requesting HTML.
Agent mode view agent-mode-viewFail0 of 2?mode=agent returns same content as homepage (no dedicated agent view)
JSON-LD structured data json-ldFail0 of 4No JSON-LD structured data found on homepage
Organization schema completeness org-schema-completenessFail0 of 2No JSON-LD found - Organization schema missing
JSON-LD entity linking (sameAs) json-ld-entity-linkingFail0 of 2No JSON-LD found - no entity linking possible
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-GB", og:image, og:type
Agent instruction / when-to-use agent-instructionFail0 of 3No 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: 9 checks Ora ran on gocardless.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-accuracyPass3 of 3gocardless.com appears at position #3 in a clean brand-name search for "GoCardless payments fintech" (4 total matches)
Wikipedia / Wikidata entity presence wikipedia-presencePass4 of 4Wikipedia "GoCardless" and Wikidata Q111418549 both verified - domain confirmed on both sources
Developer resource discoverability agentic-search-specificFail0 of 6Agent searched for "cardless" developer resources but found nothing relevant
Listed in MCP registries mcp-registry-listedFail0 of 1No bi-directionally verified MCP registry entry found. To pass, either publish the server under your own domain/npm scope, get a verified Smithery listing with non-zero usage, or link the registry entry from your homepage or docs.
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-listedFail0 of 1No official skills self-published on skills.sh (21 community skills with potential relation to this domain found, but only self-published official skills count)
ARD discovery ard-catalogFail0 of 3No /.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 gocardless.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 GoCardless, 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.

  • Developer resource discoverability: fail, 0 of 6, about 6.1 points to gain. Ora saw: Agent searched for "cardless" developer resources but found nothing relevant
  • MCP server / manifest: fail, 0 of 6, about 4.9 points to gain. Ora saw: No MCP server or manifest found
  • OpenAPI spec published: fail, 0 of 7, about 3.6 points to gain. Ora saw: No OpenAPI/Swagger specification found
  • JSON error responses: fail, 0 of 4, about 3.3 points to gain. Ora saw: API does not return JSON error responses (or no API detected)
  • ARD discovery: fail, 0 of 3, about 3 points to gain. Ora saw: No /.well-known/ai-catalog.json

Our read

GoCardless scores 47, the lowest in this directory's first sixty, and more than 6 of the missing points are a search Ora ran for the word cardless, which found nothing relevant and says more about the probe than the company. The act layer accounts for the rest: no MCP server or manifest at any URL Ora could discover, though llms.txt refers to one, no OpenAPI specification, OAuth described in the documentation with no endpoint answering, endpoints that do not answer errors as JSON and no AI catalog. The surfaces that count are the REST documentation at docs.gocardless.com with an llms.txt beside it, a gocardless CLI on PyPI, SDKs in npm, PyPI and rubygems, and markdown returned on request. The bot detection probe could not be run, so the door is unverified, and the home page carries no JSON-LD. For a direct debit network, an MCP server at the address its own llms.txt names would be the first fix.

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.