◎ Discry Score
hugging face.com
ai · API
C
0 / 100
DISCOVERY0
COMPREHENSION0
Category leader: 99 (A)
Discry your API →
AI · RANK #36 OF 43

Hugging Face is Needs Work to agents.

Discry independently scored how well an AI agent can discover and understand the Hugging Face 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 · 43/100
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.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 · 91/100
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.Partial

What we found

  • Hugging Face has world-class comprehension quality — OpenAI-compatible API, built-in MCP client, provider/task compatibility tables, and realistic examples — but almost zero AI-native discovery infrastructure.
  • An agent searching for HF via llms.txt would find nothing, despite HF literally being the home of LLMs — a stark irony that no llms.txt exists for the platform that coined the format.
  • An agent would find HF in MCP registries (official server on PulseMCP) and AGENTS.md in both huggingface_hub and transformers repos — showing selective but incomplete agent awareness.
  • The InferenceClient documentation is exceptionally agent-friendly: OpenAI drop-in compatibility, function calling, structured outputs, MCP client integration, and multi-provider routing in one unified interface.
  • An agent looking for an OpenAPI spec would fail entirely — HF's API surface is documented through Python SDK docs rather than machine-readable specifications.

What to change

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

  1. 01Add llms.txt covering the Inference API, Hub API, and key SDK capabilities — HF should be the gold standard for this format given its role in the AI ecosystem.
  2. 02Publish an OpenAPI spec for the Hub API and Inference Providers API — would add 5 weight points and enable automated client generation.
  3. 03Add .well-known/mcp.json at huggingface.co pointing to the official MCP server configuration with tool declarations.
  4. 04Create llms-full.txt with comprehensive markdown covering the complete API surface (Hub, Inference, Endpoints, Spaces).
  5. 05Add explicit error recovery documentation for common inference failures: model loading timeouts, provider unavailability, rate limit handling across different providers.

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.

User Access Token (Bearer)API Key (per provider)OAuth (via HF routing) Error format documented Rate limits documented Pagination documented Idempotency documented

Authentication supports HF tokens routed through HF infrastructure or direct provider API keys. Error handling includes timeout exceptions. Rate limits managed per-provider. Built-in MCP client for tool calling. OpenAI-compatible chat completion API with streaming support.

See your own Discry Score.

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

Discry your API — free