Vercel is Agent-Ready to agents.

Item: Vercel API
Rating: 93
Author: Discry

Discry independently scored how well an AI agent can discover and understand the Vercel 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 — free View 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 · 90/100

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.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

Vercel is a near-perfect example of agent-ready documentation — llms.txt, llms-full.txt, AGENTS.md, OpenAPI spec, and official MCP server all present and well-maintained.
The robots.txt uses the emerging Content-Signal header (ai-input=yes, ai-train=no), showing leadership in standardizing AI access signals.
AGENTS.md files exist across multiple repos (vercel/vercel, next.js, agent-skills) providing context-specific guidance for coding agents.
The REST API section of llms.txt includes the OpenAPI URL, base URL, SDK install command, and full endpoint listing — everything an agent needs to get started in one file.
The only gap is .well-known/mcp.json — despite having an official MCP server, there is no machine-discoverable pointer at the well-known path.

What to change

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

01Add .well-known/mcp.json pointing to the official Vercel MCP server �� this is the only significant discovery gap remaining.
02Consider splitting llms.txt into a smaller overview (<50KB) with the full content remaining at llms-full.txt for optimal agent consumption.
03Add explicit error recovery steps to the errors reference (e.g., 'If rate limited, check X-RateLimit-Reset header and retry after that timestamp').

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 tokenOAuth2SSO token exchange✓ Error format documented✓ Rate limits documented✓ Pagination documented✕ Idempotency documented

Comprehensive execution documentation with dedicated errors reference page, detailed rate limits and plan-based limits page, type-safe TypeScript SDK (@vercel/sdk), and OAuth2 authentication flow. Pagination documented for list endpoints.

See your own Discry Score.

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

Discry your API — free