◎ Discry Score
mollie.com
payments · API
B
0 / 100
DISCOVERY0
COMPREHENSION0
Category leader: 94 (A)
Discry your API →
PAYMENTS · RANK #5 OF 25

Mollie is Good to agents.

Discry independently scored how well an AI agent can discover and understand the Mollie API from what’s public — not whether it’s usable. Below: every signal we checked, what’s costing the score, and what to change.

Discry your API — freeView the docs ↗

SCORED UNDER RUBRIC 1.2 · A full re-launch under Discry Score 2.5 — a new behavioral instrument, not comparable to these scores — is in progress.

Discovery

45% of score · 71/100
OpenAPI specA machine-readable OpenAPI/Swagger spec agents can parse.Pass
llms.txtAn llms.txt index that points agents to the docs that matter.Pass
llms.txt qualityThe llms.txt is focused, current, and well under the size budget.Partial
llms-full.txtA full-text bundle agents can load in one request.Fail
AGENTS.mdAn AGENTS.md that tells coding agents how to build on the API.Fail
.well-known/mcp.jsonA discoverable MCP manifest at a well-known path.Fail
MCP registryThe API is listed in a public MCP registry.Pass
robots.txt AI directivesrobots.txt allows (or explicitly guides) AI crawlers.Pass
SitemapA sitemap so agents can enumerate the docs surface.Pass

Comprehension

55% of score · 96/100
Task-oriented descriptionsEndpoints described by what they accomplish, not just their shape.Pass
Realistic examplesRunnable, real-world request/response examples.Pass
Multi-step workflowsDocs that chain calls into complete jobs an agent can follow.Pass
Error-recovery guidanceDocumented failure modes and how to recover from them.Pass
Answer-first formatThe answer leads; preamble does not bury it.Pass
Capability boundariesClear limits — what the API can and cannot do.Partial
Naming consistencyConsistent, predictable naming across endpoints.Pass
Heading hierarchyClean heading structure agents can navigate.Pass
Markdown docsDocs available as clean markdown, not JS-rendered HTML only.Pass
Token efficiencyDocs are concise enough to fit an agent context window.Pass

What we found

  • An agent integrating Mollie can pull the entire API as clean markdown: every /reference/ endpoint serves a .md version with the embedded OpenAPI 3.1 definition, and a full machine-readable spec lives at github.com/mollie/openapi (specs.yaml). Parsing friction is near zero.
  • Mollie ships an official hosted MCP server (mcp.mollie.com), documented in its own guide — agents can create payments and other resources in natural language without building a custom integration. A rare first-party signal in the payments category.
  • Error recovery is genuinely agent-usable, not just a code table: the docs explain what to DO per status class (retry 5xx/502/503 later, slow down on 429, fix-your-code on 4xx) and return a `field` pointer on 422 validation errors so an agent knows exactly which parameter to correct.
  • Discovery is the weak dimension: there is no llms-full.txt, no .well-known/mcp.json, and no AGENTS.md in Mollie's GitHub SDK repos — so a coding agent cloning mollie-api-typescript or mollie-api-python gets no agent-specific build/auth guidance.
  • The llms.txt is a 104KB site-wide index bloated with plugin/platform guides (Shopware, Gambio, BigCommerce), and concrete rate-limit numbers are never published — an agent would discover request ceilings by hitting a 429 rather than by reading.

What to change

Prioritized by impact on discoverability. You (or your docs platform) deploy these — Discry never touches your API.

  1. 01Trim llms.txt to an API-focused index under 50KB (or split the plugin/platform integration guides into a separate file) so an agent can load the capability map in one cheap, high-signal fetch.
  2. 02Add AGENTS.md to the primary GitHub repos (mollie-api-typescript, mollie-api-python, mollie/openapi) with build/test/auth context so coding agents working in a Mollie SDK have predictable guidance.
  3. 03Publish concrete rate-limit thresholds and the Retry-After header behavior on a dedicated page so agents can pace requests proactively instead of reacting to 429 errors.
  4. 04Publish an llms-full.txt containing the consolidated API reference as markdown, enabling single-fetch comprehension for agents that prefer one document over crawling many pages.
  5. 05Add a .well-known/mcp.json that points to the existing mcp.mollie.com server so agents can auto-discover the MCP endpoint and its tool/auth declarations without reading prose docs.

Execution coverage · INFORMATIONAL, UNSCORED

Whether an agent can actually complete a call and recover from errors is the deeper Audit layer — documented here, but not part of the Discry Score.

API keyAdvanced access tokenApp access token (OAuth)Basic Auth✓ Error format documented✕ Rate limits documented✓ Pagination documented✓ Idempotency documented

Mollie documents four auth methods (API key, advanced access token, OAuth app tokens, Basic Auth) and a consistent machine-parseable hal+json error format with status/title/detail plus a field pointer on validation errors. Cursor-style pagination (from + _links.next) and idempotency-key support each get a dedicated reference page. Concrete rate-limit thresholds are not published — only the 429 response is documented.

See your own Discry Score.

Drop your API docs URL. See what an agent sees — in 60 seconds, free.

Discry your API — free