◎ Discry Score
airtable.com
productivity · API
F
0 / 100
DISCOVERY0
COMPREHENSION0
Category leader: 92 (A)
Discry your API →
PRODUCTIVITY · RANK #23 OF 24

Airtable is Not Agent-Ready to agents.

Discry independently scored how well an AI agent can discover and understand the Airtable 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 · 29/100
OpenAPI specA machine-readable OpenAPI/Swagger spec agents can parse.Fail
llms.txtAn llms.txt index that points agents to the docs that matter.Fail
llms.txt qualityThe llms.txt is focused, current, and well under the size budget.Fail
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 · 43/100
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.Fail
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.Fail
Markdown docsDocs available as clean markdown, not JS-rendered HTML only.Fail
Token efficiencyDocs are concise enough to fit an agent context window.Fail

What we found

  • Airtable's developer documentation is entirely JS-rendered and returns empty/broken content when scraped �� an agent cannot programmatically access any API documentation without a browser runtime
  • No llms.txt, no llms-full.txt, no OpenAPI spec, no AGENTS.md, no .well-known/mcp.json — Airtable has invested zero in agent discovery infrastructure despite being a popular automation target
  • Rate limits and error handling are well-documented but only accessible through support.airtable.com articles rather than the developer portal, fragmenting the information agents need
  • Community MCP servers exist on PulseMCP and Glama filling the gap, but these are third-party implementations without official backing
  • The API itself has good design patterns (performUpsert for batch operations, structured error responses) but the documentation delivery is completely agent-hostile

What to change

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

  1. 01Make developer documentation accessible without JavaScript — add server-side rendering or provide markdown mirrors via llms.txt and llms-full.txt
  2. 02Publish an official OpenAPI specification for the Web API — this is the highest-impact single change for agent accessibility
  3. 03Add llms.txt at airtable.com/developers/llms.txt with structured links to all API documentation in a format agents can consume
  4. 04Provide an official MCP server or endorse a community implementation via .well-known/mcp.json to connect the strong community ecosystem to a standard discovery path
  5. 05Consolidate API documentation (rate limits, errors, getting started) into the developer portal rather than scattering across support.airtable.com

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.

personal_access_tokenoauth2✓ Error format documented✓ Rate limits documented✓ Pagination documented✕ Idempotency documented

Personal access tokens and OAuth2 authentication. Rate limit of 5 requests per second per base, 50 per second per user. JSON error responses with error and message fields. Cursor-based pagination with offset parameter. performUpsert for batch operations. All info accessible only via JS-rendered pages or support articles.

See your own Discry Score.

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

Discry your API — free