◎ Discry Score
mailersend.com
communication · API
B
0 / 100
DISCOVERY0
COMPREHENSION0
Category leader: 98 (A)
Discry your API →
COMMUNICATION · RANK #8 OF 24

MailerSend is Good to agents.

Discry independently scored how well an AI agent can discover and understand the MailerSend 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 · 67/100
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.Partial

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.Pass
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.Partial

What we found

  • An agent integrating MailerSend would succeed quickly: every endpoint leads with the HTTP method and URL plus a plain-language purpose, and ships copy-pasteable examples in seven languages (raw JSON, PHP, Node.js, Python, Go, Java, Ruby) using realistic values.
  • An agent that hits an error can self-correct — the docs pair a full HTTP status table, field-level 422 validation errors, and a coded error catalog (#MS42207, #MS42206, etc.) with explicit recovery guidance for each error.
  • Capability boundaries are unusually explicit: rate limits, daily quotas, recipient caps (50 TO / 10 CC / 10 BCC), a 25MB attachment limit, and send_at ≤ now+72h are all tabulated, so an agent learns limits from the docs rather than by failing.
  • Discovery is the weak spot: the API docs live on a separate developers.mailersend.com subdomain that the marketing sitemap doesn't cover, and there is no AGENTS.md, no llms-full.txt, and no .well-known/mcp.json — an agent crawling the www sitemap would never reach the API reference.
  • Positive discovery signals: a clean robots.txt (no AI-bot blocks), an official OpenAPI 3.1 collection on SwaggerHub, an official hosted MCP server, and a product llms.txt that links to the API reference all help agents find MailerSend.

What to change

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

  1. 01Add an AGENTS.md to the primary SDK repos (mailersend-nodejs, mailersend-python, mailersend-php) — the cheapest single discovery win, currently scoring zero on a weight-3 check.
  2. 02Publish an API-focused llms.txt or llms-full.txt on developers.mailersend.com that concatenates the core endpoints as markdown; the current llms.txt is marketing-oriented and lives on www, so this would fix llms-full.txt (fail) and improve token efficiency.
  3. 03Extend the sitemap to include developers.mailersend.com pages (or add a sitemap on the docs subdomain) so crawlers can discover the API reference from a machine-readable index.
  4. 04Serve a .well-known/mcp.json advertising the existing official MCP server so agents can auto-discover its tool declarations and auth requirements.
  5. 05Document pagination (page/limit) and idempotency explicitly in the General API resources so agents chaining list and create calls know how to page and safely retry.

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.

Bearer API tokenSMTP credentials✓ Error format documented✓ Rate limits documented✕ Pagination documented✕ Idempotency documented

Execution characteristics are well documented: Bearer-token auth in an Authorization header, machine-parseable JSON errors with a field-level 422 validation structure plus a coded error catalog (e.g. #MS42207), and explicit rate limits (60/min general, 120/min email) with standard headers (x-ratelimit-limit, retry-after, x-ratelimit-reset) and daily quotas. Pagination and idempotency are not prominently documented in the General API resources.

See your own Discry Score.

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

Discry your API — free