Huggingfacehuggingface.co
Hugging Face's API design and contract quality are strong, giving partners a solid technical foundation to build on. txt, no agent instructions file, no structured data, and inconsistent descriptions mean agents cannot discover, parse, or act on the APIs without guessing.
API DesignA clean, typed, well-governed API contract agents can reason about2 pass3 warn0 fail80A
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| warn | Schema coverage & depthvia sdk | 20.6/25 | 37 of 264 public signatures use loose types (anyTypeRatio=0.140). Investigated: sdk 82%, spec 67%. | Typed, complete request/response schemas are what make agent function-calling possible. |
| warn | Machine-readable, versioned contractvia spec | 18.8/25 | info.version="0.0.1" set but no versioning scheme (URL / header / media type) detected. Investigated: spec 75%, docs 50%. | A current OpenAPI version with a declared versioning scheme lets agents reason about the contract. |
| pass | Security & governance hygienevia spec | 15/15 | No credential-shaped strings detected in spec. Investigated: spec 100%, wellknown 100%. | No leaked secrets, no critical lint violations, no OWASP API Top-10 spec smells, and a published vulnerability-disclosure channel. |
| warn | Auth declared & discoverablevia docs | 12.5/25 | No securitySchemes declared. Investigated: docs 50%, spec 25%. | Agents can only authenticate when auth is declared, scoped, and discoverable. |
| pass | Example coveragevia spec | 10/10 | 0% example coverage. Investigated: spec 100%, sdk 100%, docs 0%. | Examples carry shape semantics schemas under-specify — for humans and agents alike. |
Developer ExperienceThe context both developers and agents need to integrate fast — onboarding, code samples, complete descriptions and worked examples1 pass1 warn3 fail48F
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| pass | Changelog publishedvia sdk | 13/13 | Newest official SDK activity 0 day(s) ago. Investigated: sdk 100%, spec 0%, docs 0%. | A published changelog lets partners track changes without surprise. |
| warn | Description completenessvia sdk | 12.3/15 | 94/115 operations carry a description. Investigated: sdk 82%, spec 0%. | Complete descriptions are the context humans and agents need to use endpoints. |
| fail | Self-service developer portalvia docs | 0/29 | No signup page detected across conventional paths (/signup, /sign-up, /register, /get-started, /console/signup, /dashboard/signup, /try, /try-free, /free, /free-trial, /start, /start-free). Investigated: docs 0%. | Self-serve key/account creation is the fast first call for partners, with no sales gate. |
| fail | Quickstart presentvia docs | 0/25 | No quickstart/getting-started page found at the conventional paths. Investigated: docs 0%. | A quickstart is the fastest path from landing page to first successful call. |
| fail | Code samples in docsvia docs | 0/18 | No detectable code samples across 7 sampled docs pages. Investigated: docs 0%. | Multi-language samples shorten time-to-first-call. |
Agent DiscoveryPartners and their agents can find your APIs — llms.txt, registries, crawlable and reachable docs1 pass2 warn1 fail68C
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| pass | Registry & SDK presencevia docs | 28/28 | Indexed on Context7 (bodaay/huggingfacemodeldownloader, 339 snippets). Investigated: docs 100%, sdk 100%, mcp 100%, cli 0%, wellknown 0%. | Listing in MCP registries and publishing SDKs puts the API where agents and their tooling look. |
| warn | Docs reachable, not hard auth-gatedvia docs | 22.5/30 | Server ignores Accept: text/markdown header (0/39 pages return markdown); 39 rate-limited (HTTP 429). Investigated: docs 75%. | Agents can only index and fetch docs they can reach — past auth gates and over correct HTTP semantics. |
| warn | Crawlable / AEOvia wellknown | 9/12 | Sitemap present (7 entries) but carries no lastmod values. Investigated: wellknown 75%. | Bots allowed plus a fresh sitemap make docs findable by agent crawlers. |
| fail | llms.txt present, valid & comprehensivevia docs | 0/30 | No llms.txt found at any candidate location (https://huggingface.co/docs/llms.txt, https://huggingface.co/llms.txt). Investigated: docs 0%, sdk 0%. | A valid, comprehensive llms.txt is the machine-readable entry point for agents. |
Agent UnderstandingAgents can correctly interpret your APIs — machine-readable errors, consistent descriptions, structured data, parseable docs1 pass2 warn3 fail65C
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| pass | Machine-readable errors (RFC 9457)via docs | 28/28 | 4 distinct 4xx/5xx response codes documented. Investigated: docs 100%, spec 50%. | RFC 9457 problem details and a documented error-code inventory let agents parse failures without burning tokens. |
| warn | Agent-navigable, token-efficient docsvia docs | 15.7/22 | No pages support .md URLs (0/39 tested). Investigated: docs 71%. | Server-rendered, clean, small-footprint docs are what an agent can cheaply fetch and parse correctly. |
| warn | Operation purpose clarityvia spec | 12.5/25 | 0% of operations are agent-inferable. Investigated: spec 50%. | Agents select the right endpoint from its summary + operationId; clear, named operations make tool-selection reliable — the strongest driver of correct tool choice. |
| fail | Agent instructions file (AGENTS.md)via wellknown | 0/10 | No AGENTS.md at the site root or /.well-known/. Investigated: wellknown 0%. | An AGENTS.md gives coding agents explicit setup, auth, and usage instructions to interpret and operate the API — beyond llms.txt's link index. |
| fail | Docs structured datavia docs | 0/8 | Neither JSON-LD nor OpenGraph/meta tags detected across 3 assessed pages (3 JS-rendered). Investigated: docs 0%. | Structured data (JSON-LD/schema.org) on docs pages gives agents an unambiguous parse target and is what answer engines cite. Detected on the JS-rendered head (Firecrawl) for a bounded page budget, so JS-injected JSON-LD is now caught; pages we can't render are excluded rather than failed. |
| fail | Description consistency across surfaces | 0/7 | Mean pairwise description similarity across 2 surfaces (spec, sdk) is 0% (threshold 35% for full credit). | Every surface tells the same story about what the product is. |
Agent UsabilityAgents have the context to use your APIs reliably, not just find them3 pass0 warn2 fail74B
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| pass | Idempotency documentedvia sdk | 27/27 | Built-in retry machinery is present (grep-derived). Investigated: sdk 100%, spec 0%, docs 0%. | Documented idempotency lets agents retry safely. |
| pass | Pagination documented & consistentvia spec | 22/22 | Pagination params detected on 36 list endpoint(s). Investigated: spec 100%, docs 100%. | Consistent, documented pagination lets agents traverse collections. |
| pass | Sandbox separationvia sdk | 20/20 | Sandbox environments are exposed (sandbox). Investigated: sdk 100%, spec 0%, docs 0%. | An isolated environment lets agents exercise destructive operations safely. |
| fail | Rate-limit signalingvia spec | 0/22 | No rate-limit response headers documented. Investigated: spec 0%, docs 0%. | Machine-readable rate-limit headers let agents throttle adaptively. |
| fail | Runnable collection with test scriptsvia platform | 0/9 | No public Postman workspace discovered for the org. Investigated: platform 0%. | A public, maintained collection with assertions is runnable truth agents validate against. |
Resources Discovered
The public resources we found for Huggingface — the evidence behind the score. All discovered from public sources; nothing here requires access to your systems.
| Agent hints | Context7 (339) |
|---|---|
| APIs analyzed | 2 — Hub API Endpoints, Text Generation Inference |