Skip to content

API Scoring – Getting Started

Know exactly how AI-ready your API is — before an agent tries to use it.

The Jentic API Scorecard evaluates any OpenAPI document against the Jentic API AI Readiness Framework (JAIRF) across six dimensions and returns a single grade with prioritized, actionable recommendations.

Use it however fits your workflow:

Choose your mode

The fastest way to score any OpenAPI document from your terminal. Requires Node.js and Docker.

Score a public OAK spec — no key needed:

npx @jentic/api-scorecard-cli@latest score \
  https://raw.githubusercontent.com/jentic/jentic-public-apis/refs/heads/main/apis/openapi/swagger-api/petstore/1.0.27/openapi.json

Score your own spec — get a free key at app.jentic.com/scorecard:

JENTIC_API_KEY=<your-key> npx @jentic/api-scorecard-cli@latest score ./openapi.yaml

→ Full CLI reference

Install the Jentic API Scorecard as an agent skill so your AI coding agent scores OpenAPI documents on demand.

Claude Code:

/plugin marketplace add jentic/jentic-api-scorecard
/plugin install api-scorecard@jentic-api-scorecard

Once installed, ask naturally:

> Score ./openapi.yaml for AI-readiness
> How AI-ready is https://petstore3.swagger.io/api/v3/openapi.json?

Vercel skills CLI:

npx skills add jentic/jentic-api-scorecard --skill jentic-api-scorecard

→ Full Agent Skill guide

Add a scoring step to your CI pipeline — gates builds, uploads SARIF findings to the Security tab, and attaches an HTML report as a workflow artifact.

- uses: jentic/jentic-api-scorecard@v1
  with:
    input: ./openapi.yaml
    api-key: ${{ secrets.JENTIC_API_KEY }}
    min-score: '70'

→ Full GitHub Action reference

No install, no CLI — paste a URL or drop a file at jentic.com/scorecard and get an instant scorecard in your browser.

Ideal for quick checks, sharing results with non-technical stakeholders, or exploring the framework before integrating it into your workflow.

What it scores

Each OpenAPI document is evaluated across six dimensions:

Dimension What it measures
Foundational Compliance (FC) Structural validity and OpenAPI conformance
Developer Experience & Jentic Compatibility (DXJ) Documentation quality and tooling compatibility
AI-Readiness & Agent Experience (ARAX) Semantic clarity for LLM reasoning
Agent Usability (AU) Safe, predictable multi-step orchestration
Security (SEC) Auth schemes and trust boundaries
AI Discoverability (AID) How easily AI systems can find and parse the spec

Scores combine into a single AI-Readiness Index (0–100) mapped to five levels from Not Ready to Agent-Optimized.

→ Full framework specification

Next steps