Scored With An Older Model (ars-3.0.0)

This score is not comparable with current ARS 3.3 results. Re-scan to apply the current rules, which only award points for evidence the scanner actually observed.

Re-scan with ARS 3.3
Ecosystem Discovery Analysis / openrouter.ai

Agent-Readiness Index Report

score_version: ars-3.0.0 · ARS methodology

65
CGrade
/ 100
AI-CAPABLE ECOSYSTEM
Agent Ecosystem Discovery
openrouter.ai
Archetype: Developer Platform & APIDenominator: 94 pts
Partial exploration capabilities. Lacks critical schemas or machine-indexing entrypoints.
FrameworkCustom Docs
Surfaces
7/13
Large Pages
0pgs
Nav Gap
0pts
Developer Track & MCP Parity
Inspect in CLI or test live agent trajectories in Flight Simulator
Flight Simulator
Anti-SPA Canary Hazard Detected

Non-existent routes return HTTP 200 HTML shells instead of RFC 7807 404 JSON. Autonomous agent personas (Claude Code, Cursor, Perplexity) parse these HTML shells as valid API bodies, resulting in hallucinated fields and stuck retry loops.

Fix: Deploy an Anti-SPA 404 handler returning genuine HTTP 404 status.
Surface Inventory7 of 13 active
✓
sitemap.xml Index
ACTIVE
✓
llms.txt Index
ACTIVE
–
llms-full.txt Spec
MISSING
✓
OpenAPI Schema
ACTIVE
–
MCP Configuration
MISSING
✓
GitHub Repository
ACTIVE
✓
Documentation Root
ACTIVE
–
API Reference
MISSING
✓
Company Blog
ACTIVE
–
Developer Auth
MISSING
–
App Dashboard
MISSING
–
Developer Changelog
MISSING
✓
Status Page
ACTIVE
ARS 3.0 Machine Topology MapSub-5s Discovered Surfaces
Visual graph connecting verified machine-readable endpoints across the target ecosystem.
Active
Missing
Partial
openrouter.aiactive

Host ecosystem entrypoint for autonomous agents.

Inspect Endpoint
ARS 3.3 · 4-Layer Dynamic Architecture
Layer 1: Discovery5/16 checks passed
9/20
Needs attention+4 bonus
Layer 2: Access & Understanding34/41 checks passed
27/30
Optimal+1 bonus
Layer 3: Usability & Interoperability18/56 checks passed
16/35
Needs attention+4 bonus
Layer 4: Payments & Machine Commerce0/6 checks passed
0/0
N/A (Skipped)

Problems

24 detected
●Generate Agent Resource Discovery (ard.json)
discovery

Missing /.well-known/ard.json (ARD v0.91) specification

Target:public/.well-known/ard.json
●registry-branding
discovery

MCP manifest branding missing or incomplete at /.well-known/mcp/manifest.json

●npm-sdk-package
discovery

No official SDK package found under scope openrouter

●agent-rules-repo
discovery

Missing autonomous agent guideline rules (.claude/rules or .cursorrules)

●skills-sh-listed
discovery

Not listed in skills.sh verified skills registry

●Fix Catch-All 404 Route Leak
access

Anti-SPA Canary Failed: Returns soft HTTP 200 SPA shell (AI agents will hallucinate content)

Target:app/not-found.tsx
●llms-txt-formatting
access

llms.txt formatting does not meet ARS 3.0 standards (>=5 lines, markdown links)

●text-density-ratio
access

Text density ratio: 2%

●Mount Streamable HTTP MCP Server
usability

No active MCP server endpoint detected

Target:app/api/mcp/route.ts
●mcp-tools-listing
usability

MCP tools listing unavailable

●mcp-tools-breadth
usability

Product MCP lacks tool breadth (<3 tools)

●mcp-tools-schema-strict
usability

Tool schema strict typing unverified

●mcp-auth-requirement
usability

Product MCP authentication protocol verified

●mcp-transport-streamable
usability

Modern Streamable HTTP MCP transport handler active (/api/mcp)

●mcp-transport-sse
usability

SSE channel available for real-time progress streaming

●auth-md-stage-discover
usability

Stage 1 (Discover) missing

●auth-md-stage-methods
usability

Stage 2 (Methods) missing

●auth-md-stage-register
usability

Stage 3 (Register) missing

●auth-md-stage-claim
usability

Stage 4 (Claim) missing

●auth-md-stage-exchange
usability

Stage 5 (Exchange) missing

●auth-md-stage-use
usability

Stage 6 (Use) missing

●auth-md-stage-errors
usability

Stage 7 (Errors) missing

●auth-md-stage-revocation
usability

Stage 8 (Revocation) missing

●api-idempotency-keys
usability

Idempotency-Key support not detected on mutation routes

Solutions

3 available
●Generate Agent Resource Discovery (ard.json)
discovery
Target:public/.well-known/ard.json
Target File: public/.well-known/ard.json
Command: glintbase remediate ard.json

+ {
+   "$schema": "https://agentcard.org/v0.91/ard.json",
+   "id": "urn:air:openrouter.ai:main",
+   "name": "openrouter",
+   "capabilities": ["tools", "context"]
+ }
●Fix Catch-All 404 Route Leak
access
Target:app/not-found.tsx
Target File: app/not-found.tsx
Command: glintbase remediate next.config.mjs

+ export default function NotFound() {
+   return <h1>404 - Not Found</h1>;
+ }
●Mount Streamable HTTP MCP Server
usability
Target:app/api/mcp/route.ts
Target File: app/api/mcp/route.ts
Command: glintbase remediate mcp

+ import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
+ export async function POST(req: Request) { ... }

Audit Items

Problem Summary Prompt

Copy an ARS 3.0 compressed diagnostic defect summary structured by layer for teams or LLM pipelines.

Fixes / Solutions Prompt

Copy ARS 3.0 remediation files, patches, and CLI fix commands directly for Cursor, Claude Code, or Copilot.

Autonomous Agent Flight Simulator

Test Real Agent Execution In The Cockpit

Evaluate real-world agent execution against this ecosystem across Claude Code, Cursor & Windsurf, and Perplexity Sonar. Measure token consumption tax, schema friction risks, and autonomous credential handshakes.

5-Phase TrajectoryBPE Token Tax CounterTime-to-First-Tool-Call (TTFTC)Schema Friction Index
Launch Flight Simulator
Enterprise Infrastructure Audit

Need a Custom In-Depth Enterprise Audit?

Get custom multi-agent simulation harnesses, live production API probing, dedicated MCP server tools, and tailored enterprise readiness benchmarks built specifically for your product.

Request Enterprise Audit

Score history

11 scans
  • ARS 3.3.1(current)· 4
  • ARS 3.3· 1
  • ARS 3.2· 3
  • ARS 3.0· 1
  • ARS 1.0· 2

Scores from different ARS versions aren't comparable — each version uses different scoring rules, so lines only connect scans of the same version. Read the methodology

DateScoreGradeVersionLink
Nov 9, 202647DARS 3.3.1View →
Nov 2, 202647DARS 3.3.1View →
Oct 26, 202647DARS 3.3.1View →
Oct 25, 202647DARS 3.3.1View →
Oct 23, 202647DARS 3.3View →
Oct 19, 202681BARS 3.2View →
Oct 12, 202680BARS 3.2View →
Oct 12, 202679BARS 3.2View →
Sep 17, 202665CARS 3.0Viewing
Jul 22, 202683—ARS 1.0View →
Jul 22, 202663—ARS 1.0View →
Share your scorecard