◎ Discry Score
digitalocean.com
infrastructure · API
B
0 / 100
DISCOVERY0
COMPREHENSION0
Category leader: 98 (A)
Discry your API →
INFRASTRUCTURE · RANK #35 OF 68

DigitalOcean is Good to agents.

Discry independently scored how well an AI agent can discover and understand the DigitalOcean 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 · 81/100
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.Pass
llms-full.txtA full-text bundle agents can load in one request.Pass
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 · 71/100
Task-oriented descriptionsEndpoints described by what they accomplish, not just their shape.Partial
Realistic examplesRunnable, real-world request/response examples.Partial
Multi-step workflowsDocs that chain calls into complete jobs an agent can follow.Partial
Error-recovery guidanceDocumented failure modes and how to recover from them.Partial
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

  • DigitalOcean has one of the most agent-friendly discovery setups scanned — llms.txt with structured JSON index, chunked llms-full.txt to avoid timeout issues, and markdown mirrors for every page via index.html.md suffix
  • The robots.txt explicitly allows its own DigitalOceanGenAICrawler and provides Llms-txt/Llms-index directives, signaling active investment in AI discoverability
  • An official MCP server exists (digitalocean-labs/mcp-digitalocean) and is listed on PulseMCP and Glama, making agent integration straightforward
  • No AGENTS.md exists in any primary DigitalOcean GitHub repo despite having 200+ public repos — a missed signal for coding agents building on the DO API
  • Documentation is comprehensive but spread across 4 separate APIs (main API, Spaces, OAuth, Metadata) which increases token cost for agents needing to understand the full platform

What to change

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

  1. 01Add .well-known/mcp.json pointing to the official mcp-digitalocean server and tool declarations
  2. 02Add AGENTS.md to digitalocean/openapi or digitalocean/pydo repos with context for coding agents building DO integrations
  3. 03Create a focused API quickstart guide that chains common workflows (create Droplet -> configure firewall -> add DNS -> deploy app) to help agents understand multi-step patterns
  4. 04Add idempotency key support documentation to help agents safely retry operations

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_keyoauth2✓ Error format documented✓ Rate limits documented✓ Pagination documented✕ Idempotency documented

Well-documented execution characteristics. Personal access token and OAuth2 auth. Rate limits documented (250 requests per hour for most endpoints). Cursor-based pagination. JSON error responses with id, message, and request_id fields. No idempotency key support documented.

See your own Discry Score.

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

Discry your API — free