kusiai.es
Finalizing the report
Preparing the stored Is Agentic score
kusiai.es
Preparing the stored Is Agentic score
kusiai.es
These checks describe whether an ordinary agent can enter, read, and operate the public site.
Agents can reach the site
Crawler access and bot defenses.
Core content is available
Useful content remains accessible without a fragile browser-only path.
Navigation fails safely
Redirects and missing pages give agents a recoverable path.
Controls are understandable
Forms and interactive controls expose usable names and structure.
The public website is always evaluated. Optional surfaces appear when the scan finds positive evidence that they apply.
Strong
Weighted across 17 applicable checks
Strong
Weighted across 12 applicable checks
Ready with gaps
Weighted across 3 applicable checks
Strong
Weighted across 3 applicable checks
Critical access gaps come first, followed by other applicable readiness gaps.
No material issues were found in the applicable checks.
Checks are grouped by relevance for Business sites.
Homepage: 20347 chars, semantic headings (1 H1 + 10 H2s + 24 H3s), 27.5% content ratio. 5 of 5 sampled inner pages have text without JavaScript.
Site accessible to 4 agent user-agents (ChatGPT-User, OAI-SearchBot, Claude-User, PerplexityBot).
No meta-refresh or JavaScript-redirect stubs across 9 checked pages
All 5 sampled pages are publicly readable (5 with substantive content)
Canonical URL serves text/markdown and text/html via Accept negotiation with Vary: Accept
Nonexistent paths return HTTP 404 with markdown guidance for agents - the strongest 404 contract
kusiai.es ranks #1 for "KusiAI KusiGEO" but is not in the top 10 for "KusiAI Agencia GEO España"
No noindex on the homepage: no robots, googlebot or bingbot meta tag and no X-Robots-Tag header hides it from search.
Valid sitemap found at https://kusiai.es/sitemap-index.xml with multiple sitemaps entries
Rich JSON-LD identity: SoftwareApplication with name, description, url, and category/offers (2 blocks)
All metadata signals present: canonical URL, lang="es", og:image, og:type
Organization schema complete with contactPoint and address
All trust anchor pages verified: About, Contact, Privacy
All 9 measured pages fit an agent context budget (largest ~5K tokens)
ARD catalog valid at /.well-known/ard.json (spec 1.0) - 4/4 entries
Valid AI Catalog at /.well-known/ai-catalog.json (spec 1.0) - 4/4 entries
All 4 entries valid with domain-anchored urn:air identifiers (catalog at /.well-known/ard.json)
Wikidata Q140386267 (Julio Arévalo) verified - draft a Wikipedia page with cited references to complete knowledge graph coverage
How to pass
Establish a Wikipedia article and a Wikidata entity for your brand, with the domain set as the official website (Wikidata property P856) and a corresponding external link on Wikipedia. Wikipedia is the largest single source of citations in ChatGPT and a primary input to Knowledge Graphs across Google, Bing, and LLM training data. Earn third-party press coverage first to satisfy notability, then draft the article with cited references rather than self-promotion.
MCP manifest has full branding (name, icon, description) at https://kusiai.es/.well-known/mcp/server-card.json
Agent Skills index (agentskills.io) found at /.well-known/agent-skills/index.json with 1 skill(s)
Index v0.2.0 conformant; verified SHA-256 of "KusiAI_Audit" (skill-md)
A2A Agent Card found: "KusiAI Autonomous Agent Node"
Structured pricing.md found at /pricing.md (42 lines)
MCP server discoverable at standard path https://kusiai.es/.well-known/mcp.json
Rich agent mode view at ?mode=agent with 5 agent signals and navigation links
RFC 8288 Link header advertises: api-catalog
Partial markdown fallback support. Homepage (https://kusiai.es/index.md) returns markdown, but 3 of 3 sampled content pages do not: https://kusiai.es/about.md, https://kusiai.es/blog/benchmark-visibilidad-ia-2026.md, https://kusiai.es/blog/geo-vs-seo-marketing-2026.md. To earn full credit, serve a .md twin for each content page (e.g. /docs/auth -> /docs/auth.md, or /docs/index.md for a section root like /docs) with text/markdown content-type or a heading-led non-HTML body.
How to pass
Let agents fetch markdown by appending .md to page URLs. Required for any credit: serve a markdown homepage at /index.md. For full credit (2/2): also serve a .md twin for each content page (e.g. /docs/auth -> /docs/auth.md). Content-Type should be text/markdown and the body should start with a top-level heading (not HTML).
Modular llms.txt files found for sections: docs, kusigeo, developers, api
100% of 65 sampled sitemap entries carry lastmod; newest is 1 day(s) old
Found the llms.txt at https://kusiai.es/llms.txt.
The llms.txt is well-formatted: 76 lines with markdown links, 12,310 characters in total.
Pricing page found at /pricing
API/docs link found on homepage and resolves: /developers/
Agent instruction with when-to-use guidance at /agents.md
Strong entity linking via sameAs: wikidata.org, github.com, linkedin.com
Schema types that match what the homepage shows: FAQPage. Lists on the homepage with no schema type: "Tecnología Propietaria" (4 items)
All 5 probed llms.txt links resolve to real content
Markdown alternate advertised and verified: https://kusiai.es/index.md serves markdown
Code fences balanced across 2 markdown documents
OpenAPI spec found at https://kusiai.es/openapi.json (version: 3.1.0)
Developer portal found at /developers
RFC 9727 api-catalog with 1 API link(s) and rfc9727 profile
Path-suffix markdown docs served with text/markdown content-type: /auth.md, /index.md
All 2 tools on product MCP have detailed descriptions (>= 20 chars)
2/2 tools on product MCP have parameter schemas, 2 with required fields
product MCP exposes 2 tool(s) - consider adding more for comprehensive agent coverage
How to pass
Expose your tools via your MCP server's tools/list endpoint. A product MCP server scores on breadth: 3 or more tools that cover read, write, and search. A docs MCP server scores on focus: 3 tools or fewer, such as one search tool and one fetch tool. Keep every outputSchema valid and self-contained: a $ref that points outside the schema, such as #/components/schemas/... copied from an OpenAPI file, makes clients built on the official TypeScript SDK 1.x reject your whole tool list.
All 2 tool names follow consistent convention, descriptive, and non-generic
REST API documentation found at https://kusiai.es/developers/. Best-of-protocols score: 7/7.
OpenID Connect discovery endpoint found at https://kusiai.es
scopes_supported declares 3 scope(s) in RFC 9728 metadata (e.g. read, data, llms)
Verified live: GET https://kusiai.es/api/v1/search answered 200 without credentials (zero-auth access). Described but not verified live: free tier available, self-serve key generation, sandbox/test environment
How to pass
Offer a free tier or trial, self-serve API key generation, and a sandbox environment. Agents can't fill out 'contact sales' forms.
Web Bot Auth directory with 1 Ed25519 key(s), all with kid + nbf/exp
RFC 9728 metadata: resource=https://kusiai.es, authorization_servers (1), scopes_supported (3), bearer_methods_supported
auth.md at https://kusiai.es/auth.md served as text/markdown; charset=utf-8 (5000 chars)
WorkOS auth.md structure at https://kusiai.es/auth.md - 7/8 walkthrough sections (found Discover, Pick a method, Register, Claim, Use credential, Errors, and Revocation); anchors: oauth-protected-resource, oauth-authorization-server, and agent_auth; register shapes: id-jag shape
Static fallback (deep check disabled): PRM + AS metadata both reachable with agent_auth.identity_endpoint (https://kusiai.es/auth/register) (advertised under the pre-v0.2 register_uri key); walkthrough discoverable end-to-end
PRM + AS metadata cross-linked; agent_auth has identity_endpoint (https://kusiai.es/auth/register) (advertised under the pre-v0.2 register_uri key), identity_types_supported [identity_assertion, anonymous] with the required per-type blocks, and skill -> https://kusiai.es/auth.md (also advertised: claim_endpoint, events_endpoint; events_supported absent)
agent_auth endpoints reachable (source: AS metadata agent_auth block) - identity_endpoint: HTTP 200, claim_endpoint: HTTP 200, events_endpoint: HTTP 200
All 8 requirements that apply are met.
Same organization: the ARD catalog host is "KusiAI Research Lab", poppy.json names "KusiAI".
How to pass
Keep poppy.json consistent with your other agent surfaces: list the same MCP server and organization as your ARD catalog (/.well-known/ard.json), and, when one issuer serves both PAP and auth.md, list every grant both protocols send to its token endpoint in grant_types_supported. Publish a poppy.json on every domain your issuer lists in protected_resources, naming no other issuer, and point every 401 at the same resource_metadata URL. A file declaring 0.1 or 0.2 also names the OAuth issuer that your protected resource metadata lists. Spec: https://personalagentprotocol.org/docs/1.0/spec
MCP server connected via Streamable HTTP - kusiai-mcp-server v1.0.0 (protocol 2024-11-05)
product MCP returns structured JSON-RPC errors with code and message
product MCP uses modern Streamable HTTP transport
Imperative WebMCP API detected (document.modelContext.registerTool in inline script).
The live API operation https://kusiai.es/api/search returns IETF RateLimit headers: ratelimit-limit, ratelimit-policy, ratelimit-remaining.
REST Idempotency-Key header referenced on POST /api/v1/audit via #/components/parameters/IdempotencyKey
API returns JSON error responses (200 at https://kusiai.es/api/v1/orank-probe-test)
OpenAPI uses application/problem+json (RFC 7807) for 4xx/5xx responses
API versioning strategy found (URL versioning) with Deprecation and Sunset headers documented at https://kusiai.es/openapi.json
Cursor-based pagination found in OpenAPI spec response schemas or query parameters
Async job pattern detected: 202 Accepted with a Location header or job-tracking fields on the 202 body
CLI tool mentioned in llms.txt
How to pass
Publish an official CLI tool on npm, PyPI, or Homebrew. A CLI lets agents and developers script interactions with your product without building API integrations from scratch.
90% of operations define typed response schemas, 90% use application/json
MCP server card found at https://kusiai.es/.well-known/mcp/server-card.json (2 tools advertised)
MCP server exposes 2 resource(s) via resources/list
Server HTML is a well-structured document (main=true, landmarks=4/4, h1=1, maxHeadingSkip=1).
61 native controls, 0 non-native div-soup affordances (100% native).
61/61 interactive elements have a computable accessible name (100%).
No hidden instruction text detected in accessibility-tree attributes or off-screen content.
REST: agent-friendly schema (10 operations, 100% with operationIds, 100% documented by description or summary)
Compatible: 10/10 ops with IDs, 10/10 with typed schemas
2/2 resources read with valid mimeType and non-empty content
What does kusiai.es do and who is it for? Explain it back to me.
Sign me up for Vercel product updates and marketing emails.
Unsubscribe anytime. Privacy Notice
Source: Ora API
What does kusiai.es do and who is it for? Explain it back to me.
3 steps1 reasoning step
The agent successfully gathered a comprehensive overview of KusiAI's GEO services by fetching the homepage and pricing page. The site was navigable via direct URL guessing (/precios), but lacked clear navigation and publishable pricing figures, forcing the agent to assemble answers from fragmented content and flag multiple unsourced claims and terminological inconsistencies.