◎ Discry Score
amplitude.com
analytics · API
B
0 / 100
DISCOVERY0
COMPREHENSION0
Category leader: 92 (A)
Discry your API →
ANALYTICS · RANK #5 OF 29

Amplitude is Good to agents.

Discry independently scored how well an AI agent can discover and understand the Amplitude 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.Fail
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.Pass
AGENTS.mdAn AGENTS.md that tells coding agents how to build on the API.Pass
.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.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.Pass

What we found

  • Amplitude is the most agent-aware analytics platform scanned — it has an official MCP server with OAuth flow, a dedicated Wizard CLI with --agent mode and NDJSON streaming, and AGENTS.md in the docs repo.
  • An agent would discover Amplitude documentation effortlessly: robots.txt explicitly names and allows 12 AI bots (GPTBot, ClaudeBot, anthropic-ai, Google-Extended, CCBot, PerplexityBot, etc.).
  • The llms.txt is comprehensive and well-structured covering all product areas with .md links, but the llms-full.txt at 5.2MB is too large for practical agent consumption without chunking.
  • An agent needing to integrate Amplitude would get exceptional workflow guidance: the Wizard CLI documents a complete plan -> apply -> verify pipeline designed specifically for agent execution.
  • The one significant gap is no publicly accessible OpenAPI spec — this is a surprising omission given the otherwise exemplary agent infrastructure.

What to change

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

  1. 01Publish a public OpenAPI spec at amplitude.com/docs/openapi.json — this single addition would add 5 weight points and push discovery from C to B grade.
  2. 02Add .well-known/mcp.json pointing to the official MCP server configuration — would formalize what already exists in registries.
  3. 03Create a condensed llms-api.txt (<50KB) focused specifically on the HTTP API v2 and key analytics APIs, separate from the 5.2MB full documentation dump.
  4. 04Add explicit error recovery guidance with actionable steps for common API errors (rate limiting backoff strategy, auth token refresh flow, event validation failures).
  5. 05Consolidate the domain redirect: docs.developers.amplitude.com -> amplitude.com/docs is confusing for agents caching the old URL.

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 KeySecret KeyOAuth2✓ Error format documented✓ Rate limits documented✓ Pagination documented✓ Idempotency documented

Comprehensive execution documentation. Multiple auth methods documented with clear key types. Rate limits specified per endpoint. Error responses documented with status codes. The Wizard CLI provides agent-specific execution patterns with --agent mode, NDJSON streaming, and plan/apply/verify workflow.

See your own Discry Score.

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

Discry your API — free