Scoring Methodology

How we calculate the Clarvia Score. Weights are based on real-world agent failure frequencies and developer pain points — not marketing narratives.

v1.1Updated 2026-03-25Total: 100 pts + 25 onchain bonus

This methodology is also available as structured JSON at GET /api/v1/methodology

API Accessibility

25 pts
Endpoint Existence

Publicly reachable endpoint returning 2xx

7
Response Speed

Median response time, target <200ms

6
Auth Documentation

OpenAPI security schemes documented

3
Rate Limit TransparencyNEW

#1 cause of agent failures — X-RateLimit-* headers

6
API Versioning

API version in URL path or header

1
SDK Availability

Official SDKs on PyPI/npm

1
Free Tier / Trial

Free tier or trial available

1

Data Structuring

25 pts
Schema Definition

OpenAPI/JSON Schema published with typed models

7
Pricing Quantified

Machine-readable pricing information

5
Error Structure

Structured JSON errors (RFC 7807 or equivalent)

5
Webhook Support

Webhook endpoints or documented webhook system

3
Batch API Support

Batch/bulk endpoints for efficient agent operations

3
Type Definitions

JSON Schema or TypeScript type definitions published

2

Agent Compatibility

25 pts
MCP Server Exists

Registered on mcp.so, Smithery, or Glama

7
robots.txt Agent Policy

Agent-friendly robots.txt with AI agent rules

5
Discovery Mechanism

Sitemap, ai-plugin.json, .well-known configs

5
Idempotency SupportNEW

Idempotency-Key header for safe retries

3
Pagination Pattern

Consistent cursor/offset pagination

2
Streaming SupportNEW

SSE/streaming endpoints for real-time data

3

Trust Signals

25 pts
Success Rate & Uptime

Public status page with uptime metrics and history

6
Documentation Quality

API reference, guides, code examples, changelogs

5
Update Frequency

Active changelog, recent updates within 30-90 days

4
Response Consistency

Identical responses across repeated requests

4
Error Response Quality

Error includes code, message, and documentation link

3
Deprecation Policy

Explicit deprecation/versioning policy documented

2
SLA / Uptime Guarantee

Published SLA or uptime commitment

1

v1.1 Weight Changes

Rate Limit Info: 3 → 6 pts

#1 cause of agent failures in production (429 errors)

MCP Server: 10 → 7 pts

Important but APIs work fine without MCP via OpenAPI specs

NEW: Idempotency Support (3 pts)

Critical for agent retry safety

NEW: Streaming Support (3 pts)

Essential for LLM-based API services

NEW: Pagination Pattern (2 pts)

Agents need to handle large datasets reliably

Trust Signals: restructured to 7 sub-factors

Response consistency, error quality, deprecation policy, and SLA now scored separately

Data Structuring: restructured to 6 sub-factors

Added webhook support, batch API, type definitions; removed CORS (moved to informational)

Scoring Philosophy

Clarvia Score measures how easily AI agents can discover and use your service. It does not measure company size, product quality, or business viability.

Weights are derived from agent-builder pain frequency: we prioritize factors that cause the most agent failures in production. Rate limit headers (6pts) outweigh SDK availability (1pt) because missing rate limits crash agents, while missing SDKs merely slow integration.

MCP support was reduced from 10 to 7 points because well-documented OpenAPI specs enable agent integration without MCP. We want to reward all paths to agent compatibility, not just one protocol.