--- title: "Perplexity agent readiness score: 46/100 · Agentrail" description: "Discovery is the strongest area, with Wikipedia or Wikidata entity presence and discoverable developer resources, while the MCP server or manifest and JSON error response checks were missed." canonical: "https://www.agentrail.co/agent-readiness/perplexity.ai" --- Full report ## See what each check found, and how to fix it. Evidence, step-by-step fixes and your score over time, for your own site. [Get started →](https://app.agentrail.co/login?utm%5Fsource=agentrail.co&utm%5Fmedium=website&utm%5Fcampaign=agent-readiness%2Fperplexity.ai&utm%5Fcontent=company-report) Free to start. No card. Access 23 to fix - Content without JavaScriptRequiredHow to fix → - Not blocked by bot detectionRequiredHow to fix → - Agent discovery fileRequiredHow to fix → - A2A / agent-cardRecommendedHow to fix → Fixes unlock with the full report Where the score comes from 41 of 90 points How perplexity.ai scores on each of the four questions agents ask. Discovery14/20 Access4/30 Usability23/40 Paymentsnot scored yet Strongest ### Discovery ARD discovery and Brand name discoverability are missing. 14/20 Most to gain ### Access Content without JavaScript, Not blocked by bot detection, and 15 more are missing. 4/30 Most to gain ### Usability Agent auth discovery metadata, agent\_auth endpoints reachable, and 3 more are missing. 23/40 Not scored yet ### Payments ( bonus ) 6 checks partly met. Counts when scoring opens. — Every check 125checks - Passed**11** - To fix**30** - Not in the score**84** 41 checks count toward the score. The other 84 are tracked for later. Discovery14 of 202 to fix4 passed ARD discoveryRequired0 / 1 Brand name discoverabilityRequired0 / 3 Developer resource discoverabilityRecommended3 / 3 Wikipedia / Wikidata entity presenceRecommended4 / 4 robots.txt AI crawler policyRequired2 / 2 NPM/PyPI SDK packageRecommended1 / 1 \+ 9 checks not in the score AI Catalog discoveryRecommendedNot counted ARD entry validityRecommendedNot counted ARD trust manifestRecommendedNot counted Category share of voiceRecommendedNot counted Listed in MCP registriesRecommendedNot counted Agent platform configsEmergingNot counted Agent Plugins manifestEmergingNot counted Registry brandingEmergingNot counted ChatGPT app listedRecommendedNot counted Access4 of 3017 to fix2 passed Content without JavaScriptRequired0 / 3 Not blocked by bot detectionRequired0 / 2 Agent discovery fileRequired0 / 2 A2A / agent-cardRecommended0 / 2 MCP well-known discoveryRecommended0 / 2 HTTP Link headers (RFC 8288)Required0 / 1 Sitemap freshness (lastmod)Recommended0 / 1 JSON-LD structured dataRequired0 / 4 Pricing info accessibleRequired0 / 3 JSON-LD entity linking (sameAs)Recommended0 / 2 Metadata completenessRequired0 / 2 Organization schema completenessRecommended0 / 2 Schema type breadthRecommended0 / 2 Trust anchor pagesRequired0 / 2 API catalog (RFC 9727)Required0 / 2 Markdown content negotiation (acceptmarkdown.com)Recommended0 / 1 Agent crawler reachabilityRecommended0 / 2 Sitemap existsRequired2 / 2 robots.txt agent-user policyRequired2 / 2 \+ 23 checks not in the score Agent Skills index conformance (v0.2.0)EmergingNot counted Listed on skills.shEmergingNot counted pricing.md existsEmergingNot counted NLWeb Schema FeedsEmergingNot counted Agent mode viewEmergingNot counted Markdown URL fallbackEmergingNot counted Modular llms.txt per product areaEmergingNot counted llms.txt existsRequiredNot counted llms.txt formattingRecommendedNot counted Public API/docs linked from homepageRequiredNot counted Agent instruction / when-to-useRequiredNot counted Skills.sh skill qualityEmergingNot counted llms.txt links resolveRecommendedNot counted Markdown alternate linkEmergingNot counted Markdown frontmatter metadataEmergingNot counted Redirect hygieneRecommendedNot counted Page token budgetRecommendedNot counted Code fence validityEmergingNot counted Content behind authRecommendedNot counted OpenAPI spec publishedRequiredNot counted Developer portalRecommendedNot counted Markdown agent docsEmergingNot counted Bot-UA markdown servingEmergingNot counted Usability23 of 404 to fix1 partly5 passed agent\_auth endpoints reachableRecommended0 / 2 MCP server / manifestRequired0 / 6 Rate limit response headersRecommended0 / 2 JSON error responsesRequired0 / 4 Agent auth discovery metadataRecommended1 / 3 OAuth 2.0 supportRequired5 / 5 Scoped permissionsRecommended5 / 5 OAuth Protected Resource metadata (RFC 9728)Required2 / 2 Agent auth WWW-Authenticate hintRecommended1 / 1 CLI tool availableRecommended3 / 3 \+ 52 checks not in the score MCP tool descriptionsRecommendedNot counted MCP parameter schemasRecommendedNot counted MCP server identityRecommendedNot counted MCP tool listingRecommendedNot counted MCP tool namingRecommendedNot counted Public API with reachable endpointsRequiredNot counted MCP auth mechanismRecommendedNot counted MCP OAuth metadataRecommendedNot counted MCP PKCE S256 supportRecommendedNot counted Agent onboarding frictionRecommendedNot counted Web Bot Auth directoryEmergingNot counted auth.md existsRequiredNot counted auth.md structureRecommendedNot counted auth.md walkthrough simulationRecommendedNot counted MCP error handlingRecommendedNot counted MCP modern transportRecommendedNot counted WebMCP supportRequiredNot counted Idempotency-Key supportRecommendedNot counted REST typed error modelRecommendedNot counted REST versioning / deprecation policyRecommendedNot counted REST pagination patternRecommendedNot counted REST async-job patternRecommendedNot counted Multi-language SDK packagesRecommendedNot counted NLWeb /ask endpointEmergingNot counted NLWeb streaming supportEmergingNot counted REST response schema coverageRecommendedNot counted MCP tool annotationsRecommendedNot counted MCP server-card.jsonRecommendedNot counted Product + docs MCP coverageRecommendedNot counted Sandbox / test environmentRecommendedNot counted REST batch / bulk endpointRecommendedNot counted MCP resources exposedRecommendedNot counted GraphQL typed error modelRecommendedNot counted GraphQL versioning / deprecation policyRecommendedNot counted GraphQL pagination patternRecommendedNot counted GraphQL async-job patternRecommendedNot counted GraphQL schema description coverageRecommendedNot counted GraphQL batch mutationsRecommendedNot counted Agent-friendly 404sRecommendedNot counted Accessible document structureRecommendedNot counted Native interactive controlsRecommendedNot counted Accessible names on controlsRecommendedNot counted Form control labelingRecommendedNot counted Accessibility-tree injection safety (bonus)RecommendedNot counted MCP Apps supportRecommendedNot counted A2UI / generative UI supportEmergingNot counted MCP Apps UI qualityRecommendedNot counted MCP App view reachableRecommendedNot counted MCP App view CSPRecommendedNot counted API schema complexity analysisRecommendedNot counted Function calling compatibilityRecommendedNot counted MCP resource qualityRecommendedNot counted PaymentsNot scored yet6 partly MPP payment protocolRequired0 / 2 x402 payment protocolRequired0 / 2 UCP - Universal Commerce ProtocolRequired0 / 3 ACP - Agentic Commerce ProtocolRequired0 / 3 ACP delegate paymentRecommended0 / 3 AP2 - Agent Payments ProtocolRecommended0 / 3