---
title: "Devin agent readiness score: 84/100 · Agentrail"
description: "The website is strongest in discovery, with its brand name and developer resources discoverable, but misses checks for a developer portal and ARD discovery."
canonical: "https://www.agentrail.co/agent-readiness/devin.ai?h=1VZJZQRVEKNK400V"
---

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%2Fdevin.ai&utm%5Fcontent=company-report)

Free to start. No card.

Access

16 to fix

- Content without JavaScriptRequiredHow to fix →
- Agent discovery fileEmergingHow to fix →
- A2A / agent-cardEmergingHow to fix →
- Listed on skills.shEmergingHow to fix →

Fixes unlock with the full report

Where the score comes from

75 of 90 points

How devin.ai scores on each of the four questions agents ask.

Discovery18/20

Access23/30

Usability34/40

Paymentsnot scored yet

Strongest

### Discovery

ARD discovery and Wikipedia / Wikidata entity presence are missing.

18/20

Most to gain

### Access

Content without JavaScript, Organization schema completeness, and 2 more are missing.

23/30

Most to gain

### Usability

Agent onboarding friction, MCP server / manifest, and 5 more are missing.

34/40

Not scored yet

### Payments ( bonus )

4 checks partly met. Counts when scoring opens.

—

Agent path

## How an agent moved through the site

We asked an agent a question about devin.aiand recorded every request it made.

**D**devin.aiAnsweredRan Nov 4, 2026

Question

I want to start using Devin (devin.ai). Find its setup and getting-started guide.

2

Steps

21s

Duration

2

Pages opened

0

Failed

Every address the agent typed itself loaded.

1. 1devin.ai /Named in the question _→_ **Read**
2. 2devin.ai /Typed by the agent _→_ **Read**

2/2 steps

StepsHow it found itCame back as

Step 2 of 2

`docs.devin.ai /`

How it got here

Typed by the agent

Response

307 → 200

Came back as

Markdown

100%

Pages that loaded

0%

Followed site links

100%

Read as markdown

How it found each page

Named in the question**1**

A link on a page it read**0**

Typed by the agent**1**

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%2Fdevin.ai&utm%5Fcontent=journey-answer)

Free to start. No card.

Every check

116checks

- Passed**34**
- To fix**17**
- Not in the score**65**

51 checks count toward the score. The other 65 are tracked for later.

Discovery18 of 201 to fix1 partly5 passed

ARD discoveryRequired0 / 1

Wikipedia / Wikidata entity presenceRecommended2 / 4

Developer resource discoverabilityRecommended3 / 3

Brand name discoverabilityRequired3 / 3

robots.txt AI crawler policyRequired2 / 2

Listed in MCP registriesRecommended1 / 1

NPM/PyPI SDK packageRecommended1 / 1

\+ 7 checks not in the score

AI Catalog discoveryEmergingNot counted

ARD entry validityRecommendedNot counted

ARD trust manifestEmergingNot counted

Agent platform configsEmergingNot counted

Agent Plugins manifestEmergingNot counted

Registry brandingEmergingNot counted

ChatGPT app listedRecommendedNot counted

Access23 of 301 to fix3 partly16 passed

Developer portalRecommended0 / 6

Content without JavaScriptRequired2 / 3

Organization schema completenessRecommended1 / 2

Trust anchor pagesRequired1 / 2

Sitemap existsRequired2 / 2

Not blocked by bot detectionRequired2 / 2

robots.txt agent-user policyRequired2 / 2

llms.txt existsRequired1 / 1

llms.txt formattingRecommended2 / 2

JSON-LD structured dataRequired4 / 4

Pricing info accessibleRequired3 / 3

Public API/docs linked from homepageRequired3 / 3

JSON-LD entity linking (sameAs)Recommended2 / 2

Metadata completenessRequired2 / 2

llms.txt links resolveRecommended2 / 2

Redirect hygieneRecommended1 / 1

Page token budgetRecommended1 / 1

OpenAPI spec publishedRequired7 / 7

Markdown content negotiation (acceptmarkdown.com)Recommended1 / 1

Agent crawler reachabilityRecommended2 / 2

\+ 19 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

Agent instruction / when-to-useRequiredNot counted

Skills.sh skill qualityEmergingNot counted

Markdown alternate linkEmergingNot counted

Markdown frontmatter metadataEmergingNot counted

Code fence validityEmergingNot counted

Content behind authRecommendedNot counted

API catalog (RFC 9727)EmergingNot counted

Markdown agent docsEmergingNot counted

Bot-UA markdown servingEmergingNot counted

Usability34 of 404 to fix3 partly13 passed

Agent onboarding frictionRecommended0 / 2

Rate limit response headersRecommended0 / 2

Idempotency-Key supportRecommended0 / 3

Sandbox / test environmentRecommended0 / 2

MCP server / manifestRequired5 / 6

REST async-job patternRecommended1 / 2

Agent-friendly 404sRecommended1 / 2

Public API with reachable endpointsRequired7 / 7

OAuth 2.0 supportRequired5 / 5

Scoped permissionsRecommended5 / 5

MCP auth mechanismRecommended2 / 2

MCP OAuth metadataRecommended2 / 2

MCP PKCE S256 supportRecommended2 / 2

OAuth Protected Resource metadata (RFC 9728)Required2 / 2

JSON error responsesRequired4 / 4

REST typed error modelRecommended3 / 3

REST versioning / deprecation policyRecommended3 / 3

CLI tool availableRecommended3 / 3

API schema complexity analysisRecommended2 / 2

Function calling compatibilityRecommended2 / 2

\+ 39 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

Web Bot Auth directoryEmergingNot 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 error handlingRecommendedNot counted

MCP modern transportRecommendedNot counted

WebMCP supportRequiredNot counted

REST pagination 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

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

MCP resource qualityRecommendedNot counted

PaymentsNot scored yet4 partly

MPP payment protocolRequired0 / 2

x402 payment protocolRequired0 / 2

UCP - Universal Commerce ProtocolRequired0 / 3

ACP - Agentic Commerce ProtocolRequired0 / 3
