---
title: "Cumbuca agent readiness score: 62/100 · Agentrail"
description: "Agents can access and understand the site, which publishes an OpenAPI specification and does not block them with bot detection, but it is not listed in MCP registries and its developer resources are hard to discover."
canonical: "https://www.agentrail.co/agent-readiness/cumbuca.com?h=FY42YZMRS5V1B00Q"
---

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

Free to start. No card.

Usability

22 to fix

- MCP parameter schemasRecommendedHow to fix →
- MCP tool listingRecommendedHow to fix →
- OAuth 2.0 supportRequiredHow to fix →
- MCP auth mechanismRecommendedHow to fix →

Fixes unlock with the full report

Where the score comes from

56 of 90 points

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

Discovery9/20

Access22/30

Usability25/40

Paymentsnot scored yet

Strongest

### Access

Content without JavaScript, Public API/docs linked from homepage, and 2 more are missing.

22/30

Most to gain

### Usability

MCP parameter schemas, MCP tool listing, and 12 more are missing.

25/40

Most to gain

### Discovery

ARD discovery, Developer resource discoverability, and 3 more are missing.

9/20

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 cumbuca.comand recorded every request it made.

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

Question

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

6

Steps

4m 43s

Duration

6

Pages opened

0

Failed

Every link it followed loaded.

1. 1cumbuca.com /Named in the question _→_ **Read**
2. 2/ferramentasA link on a page it read _→_ **Read**
3. 3/llms.txtA link on a page it read _→_ **Read**
4. 4/guias/licenca-propria-ou-as-a-serviceA link on a page it read _→_ **Read**
5. 5/ferramentas/open-finance-data-mcpA link on a page it read _→_ **Read**
6. 6juspay.io/pt-br/open-financeA link on a page it read _→_ **Read**

6/6 steps

StepsHow it found itCame back as

Step 6 of 6

`juspay.io/pt-br/open-finance · not cumbuca.com`

How it got here

A link on a page it read

Response

200

Came back as

Web page

100%

Pages that loaded

83%

Followed site links

67%

Read as markdown

How it found each page

Named in the question**1**

A link on a page it read**5**

Typed by the agent**0**

A search result**0**

What it reached

Home page**Step 1**

Pricing**Never reached**

Docs**Never reached**

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%2Fcumbuca.com&utm%5Fcontent=journey-answer)

Free to start. No card.

Every check

139checks

- Passed**38**
- To fix**23**
- Not in the score**78**

61 checks count toward the score. The other 78 are tracked for later.

Discovery9 of 204 to fix1 partly3 passed

ARD discoveryRequired0 / 1

Wikipedia / Wikidata entity presenceRecommended0 / 4

Listed in MCP registriesRecommended0 / 3

NPM/PyPI SDK packageRecommended0 / 1

Developer resource discoverabilityRecommended1.3 / 4

Brand name discoverabilityRequired3 / 3

robots.txt AI crawler policyRequired1 / 1

Homepage not hidden from searchRecommended1 / 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

Access22 of 303 to fix1 partly17 passed

Public API/docs linked from homepageRequired0 / 4

Agent instruction / when-to-useRequired0 / 1

Developer portalRecommended0 / 5

Content without JavaScriptRequired3.3 / 5

Sitemap existsRequired1 / 1

Not blocked by bot detectionRequired2 / 2

robots.txt agent-user policyRequired1 / 1

llms.txt existsRequired1 / 1

llms.txt formattingRecommended2 / 2

JSON-LD structured dataRequired2 / 2

JSON-LD entity linking (sameAs)Recommended1 / 1

Metadata completenessRequired1 / 1

Organization schema completenessRecommended1 / 1

Trust anchor pagesRequired1 / 1

llms.txt links resolveRecommended2 / 2

Redirect hygieneRecommended1 / 1

Page token budgetRecommended1 / 1

Content behind authRecommended1 / 1

OpenAPI spec publishedRequired8 / 8

Markdown content negotiation (acceptmarkdown.com)Recommended1 / 1

Agent crawler reachabilityRecommended1 / 1

\+ 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

Pricing info accessibleRequiredNot counted

Skills.sh skill qualityEmergingNot counted

Markdown alternate linkEmergingNot counted

Markdown frontmatter metadataEmergingNot counted

Code fence validityEmergingNot counted

API catalog (RFC 9727)EmergingNot counted

Markdown agent docsEmergingNot counted

Bot-UA markdown servingEmergingNot counted

Content starts near the topEmergingNot counted

Usability25 of 409 to fix5 partly18 passed

MCP tool listingRecommended0 / 3

OAuth 2.0 supportRequired0 / 5

MCP OAuth metadataRecommended0 / 2

MCP PKCE S256 supportRecommended0 / 2

Agent onboarding frictionRecommended0 / 2

JSON error responsesRequired0 / 3

REST pagination patternRecommended0 / 2

CLI tool availableRecommended0 / 3

Sandbox / test environmentRecommended0 / 2

MCP parameter schemasRecommended2.8 / 3

MCP auth mechanismRecommended1 / 2

WebMCP supportRequired0 / 8

Rate limit response headersRecommended1 / 2

REST versioning / deprecation policyRecommended2 / 3

MCP tool descriptionsRecommended4 / 4

MCP tool namingRecommended2 / 2

Scoped permissionsRecommended5 / 5

OAuth Protected Resource metadata (RFC 9728)Required2 / 2

MCP server / manifestRequired10 / 10

MCP error handlingRecommended2 / 2

MCP modern transportRecommended1 / 1

Idempotency-Key supportRecommended3 / 3

REST typed error modelRecommended3 / 3

REST async-job patternRecommended2 / 2

REST response schema coverageRecommended2 / 2

MCP tool annotationsRecommended3 / 3

Agent-friendly 404sRecommended2 / 2

API schema complexity analysisRecommended2 / 2

Function calling compatibilityRecommended2 / 2

MCP server instructionsRecommended1 / 1

MCP tools are distinguishableRecommended2 / 2

MCP tool output schemasRecommended3 / 3

\+ 47 checks not in the score

MCP server identityRecommendedNot counted

Public API with reachable endpointsRequiredNot 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

NLWeb /ask endpointEmergingNot counted

NLWeb streaming supportEmergingNot 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

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
