---
title: "Cursor agent readiness score: 48/100 · Agentrail"
description: "The website is strongest in discovery, passing checks for developer resource discoverability and Wikipedia/Wikidata entity presence, but missing checks for WebMCP support and a developer portal."
canonical: "https://www.agentrail.co/agent-readiness/cursor.com?h=47VHWRRSGKCXS00J"
---

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%2Fcursor.com&utm%5Fcontent=company-report)

Free to start. No card.

Access

21 to fix

- Content without JavaScriptRequiredHow to fix →
- Agent discovery fileEmergingHow to fix →
- Agent Skills index conformance (v0.2.0)EmergingHow to fix →
- A2A / agent-cardEmergingHow to fix →

Fixes unlock with the full report

Where the score comes from

44 of 90 points

How cursor.com scores on each of the four questions agents ask.

Discovery19/20

Access19/30

Usability6/40

Paymentsnot scored yet

Strongest

### Discovery

ARD discovery is missing.

19/20

Most to gain

### Usability

WebMCP support and Agent-friendly 404s are missing.

6/40

Most to gain

### Access

Content without JavaScript, llms.txt formatting, and 6 more are missing.

19/30

Not scored yet

### Payments ( bonus )

Counts when scoring opens.

—

Agent path

## How an agent moved through the site

We asked an agent a question about cursor.comand recorded every request it made.

**C**cursor.comAnsweredRan Nov 20, 2026

Question

I want to start using Cursor (cursor.com). Find its setup and getting-started guide.

14

Steps

1m 52s

Duration

12

Pages opened

5

Failed

5 of 6 addresses the agent typed itself didn’t load. Every link it followed loaded.

1. 1cursor.com /Named in the question _→_ **Read**
2. 2/docsA link on a page it read _→_ **Read**
3. 3/docs/get-startedTyped by the agent _→_ **Didn’t load · 404**
4. 4/learnA link on a page it read _→_ **Read**
5. 5/downloadA link on a page it read _→_ **Read**
6. 6/helpA link on a page it read _→_ **Read**
7. 7/help/getting-startedTyped by the agent _→_ **Didn’t load · 404**
8. 8/help/getting-started/installationTyped by the agent _→_ **Didn’t load · 404**
9. 9/docs/llms.txtTyped by the agent _→_ **Read**
10. 10/docs/get-started/quickstartA link on a page it read _→_ **Read**
11. 11/docs/get-startedTyped by the agent _→_ **Didn’t load · 404**
12. 12/docsA link on a page it read _→_ **Read again**
13. 13/docs/get-started/models-and-pricingTyped by the agent _→_ **Didn’t load · 404**
14. 14cursor.com /Named in the question _→_ **Read again**

14/14 steps

StepsHow it found itCame back as

Step 14 of 14

`cursor.com /`

How it got here

Named in the question

Response

already read

Came back as

—

58%

Pages that loaded

42%

Followed site links

43%

Read as markdown

How it found each page

Named in the question**2**

A link on a page it read**6**

Typed by the agent**6**

A search result**0**

What it reached

Home page**Step 1**

Pricing**Never reached**

Docs**Step 2**

Its answer

Answers aren’t shown publicly

See what agents answer about your own site.

Run agents on your site and read every answer, with every page they opened.

[Get started →](https://app.agentrail.co/login?utm%5Fsource=agentrail.co&utm%5Fmedium=website&utm%5Fcampaign=agent-readiness%2Fcursor.com&utm%5Fcontent=journey-answer)

Free to start. No card.

Every check

139checks

- Passed**19**
- To fix**11**
- Not in the score**109**

30 checks count toward the score. The other 109 are tracked for later.

Discovery19 of 201 partly6 passed

ARD discoveryRequired0 / 1

Developer resource discoverabilityRecommended4 / 4

Brand name discoverabilityRequired3 / 3

Wikipedia / Wikidata entity presenceRecommended4 / 4

robots.txt AI crawler policyRequired1 / 1

NPM/PyPI SDK packageRecommended1 / 1

Homepage not hidden from searchRecommended1 / 1

\+ 8 checks not in the score

AI Catalog discoveryEmergingNot counted

ARD entry validityRecommendedNot counted

ARD trust manifestEmergingNot counted

Listed in MCP registriesRecommendedNot counted

Agent platform configsEmergingNot counted

Agent Plugins manifestEmergingNot counted

Registry brandingEmergingNot counted

ChatGPT app listedRecommendedNot counted

Access19 of 304 to fix4 partly12 passed

llms.txt formattingRecommended0 / 2

Agent instruction / when-to-useRequired0 / 1

Developer portalRecommended0 / 5

Markdown content negotiation (acceptmarkdown.com)Recommended0 / 1

Content without JavaScriptRequired1.7 / 5

Organization schema completenessRecommended0.5 / 1

Trust anchor pagesRequired0.5 / 1

Redirect hygieneRecommended0 / 1

Sitemap existsRequired1 / 1

Not blocked by bot detectionRequired2 / 2

robots.txt agent-user policyRequired1 / 1

llms.txt existsRequired1 / 1

JSON-LD structured dataRequired2 / 2

Pricing info accessibleRequired3 / 3

Public API/docs linked from homepageRequired4 / 4

JSON-LD entity linking (sameAs)Recommended1 / 1

Metadata completenessRequired1 / 1

Page token budgetRecommended1 / 1

Content behind authRecommended1 / 1

Agent crawler reachabilityRecommended1 / 1

\+ 20 checks not in the score

Agent discovery fileEmergingNot counted

Agent Skills index conformance (v0.2.0)EmergingNot counted

A2A / agent-cardEmergingNot counted

Listed on skills.shEmergingNot counted

pricing.md existsEmergingNot counted

NLWeb Schema FeedsEmergingNot counted

MCP well-known discoveryEmergingNot counted

HTTP Link headers (RFC 8288)EmergingNot counted

Markdown URL fallbackEmergingNot counted

Modular llms.txt per product areaEmergingNot counted

Skills.sh skill qualityEmergingNot counted

llms.txt links resolveRecommendedNot counted

Markdown alternate linkEmergingNot counted

Markdown frontmatter metadataEmergingNot counted

Code fence validityEmergingNot counted

OpenAPI spec publishedRequiredNot counted

API catalog (RFC 9727)EmergingNot counted

Markdown agent docsEmergingNot counted

Bot-UA markdown servingEmergingNot counted

Content starts near the topEmergingNot counted

Usability6 of 402 to fix1 passed

WebMCP supportRequired0 / 8

Agent-friendly 404sRecommended0 / 2

CLI tool availableRecommended3 / 3

\+ 76 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

OAuth 2.0 supportRequiredNot counted

Scoped permissionsRecommendedNot counted

MCP auth mechanismRecommendedNot counted

MCP OAuth metadataRecommendedNot counted

MCP PKCE S256 supportRecommendedNot counted

Agent onboarding frictionRecommendedNot counted

Web Bot Auth directoryEmergingNot counted

OAuth Protected Resource metadata (RFC 9728)RequiredNot counted

auth.md existsEmergingNot counted

auth.md structureEmergingNot counted

auth.md walkthrough simulationEmergingNot counted

Agent auth discovery metadataEmergingNot counted

Agent auth WWW-Authenticate hintEmergingNot counted

agent\_auth endpoints reachableEmergingNot counted

MCP server / manifestRequiredNot counted

MCP error handlingRecommendedNot counted

MCP modern transportRecommendedNot counted

Rate limit response headersRecommendedNot counted

Idempotency-Key supportRecommendedNot counted

JSON error responsesRequiredNot counted

REST typed error modelRecommendedNot counted

REST versioning / deprecation policyRecommendedNot counted

REST pagination patternRecommendedNot counted

REST async-job patternRecommendedNot counted

NLWeb /ask endpointEmergingNot counted

NLWeb streaming supportEmergingNot counted

REST response schema coverageRecommendedNot counted

MCP tool annotationsRecommendedNot counted

MCP server-card.jsonEmergingNot counted

Product + docs MCP coverageRecommendedNot counted

Sandbox / test environmentRecommendedNot 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

Accessible document structureEmergingNot counted

Native interactive controlsEmergingNot counted

Accessible names on controlsEmergingNot counted

Form control labelingEmergingNot counted

Accessibility-tree injection safety (bonus)EmergingNot 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

MCP server instructionsRecommendedNot counted

MCP tools are distinguishableRecommendedNot counted

MCP tool output schemasRecommendedNot counted

MCP Apps checkout viewEmergingNot counted

WebMCP schema validityRecommendedNot counted

WebMCP schema detailRecommendedNot counted

WebMCP real toolsRecommendedNot counted

WebMCP entry pointRecommendedNot counted

WebMCP tool namesRecommendedNot counted

WebMCP read-only hintsRecommendedNot counted

WebMCP honest hintsRecommendedNot counted

WebMCP untrusted content hintRecommendedNot counted

WebMCP consequential hintRecommendedNot counted

WebMCP coverageRecommendedNot counted

Personal Agent Protocol discovery fileEmergingNot counted

PAP issuer bindingEmergingNot counted

PAP sign-in and extension configEmergingNot counted

PAP API and agent entriesEmergingNot counted

PAP endpoints reject unauthenticated agentsEmergingNot counted

PAP agrees with ARD and auth.mdEmergingNot counted

PaymentsNot scored yet

\+ 5 checks not in the score

MPP payment protocolRequiredNot counted

x402 payment protocolRequiredNot counted

UCP - Universal Commerce ProtocolRequiredNot counted

ACP - Agentic Commerce ProtocolRequiredNot counted

Agent wallet checkoutRequiredNot counted
