Ecosystem Discovery Analysis / exa.ai

Agent-Readiness Index Report

score_version: ars-3.3.1 · ARS methodology

80
BGrade
/ 100
AI-FRIENDLY ECOSYSTEM
Agent Ecosystem Discovery
exa.ai
Archetype: Developer Platform & APIDenominator: 123 pts
AI-ready surfaces with complete discovery paths. Minor updates needed to reach elite index.
FrameworkCustom Docs
Surfaces
10/13
Large Pages
0pgs
Nav Gap
0pts
Developer Track & MCP Parity
Inspect in CLI or test live agent trajectories in Flight Simulator
Flight Simulator
Surface Inventory10 of 13 active
✓
sitemap.xml Index
ACTIVE
✓
llms.txt Index
ACTIVE
✓
llms-full.txt Spec
ACTIVE
✓
OpenAPI Schema
ACTIVE
✓
MCP Configuration
ACTIVE
✓
GitHub Repository
ACTIVE
✓
Documentation Root
ACTIVE
–
API Reference
MISSING
✓
Company Blog
ACTIVE
–
Developer Auth
MISSING
–
App Dashboard
MISSING
✓
Developer Changelog
ACTIVE
✓
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
exa.aiactive

Host ecosystem entrypoint for autonomous agents.

Inspect Endpoint
ARS 3.3 · 4-Layer Dynamic Architecture92 of 137 checks measured
Layer 1: Discovery6/18 checks passed
15/20
Needs attentionLow evidence+5 bonus
Layer 2: Access & Understanding33/47 checks passed
38/30
Optimal+10 bonus
Layer 3: Usability & Interoperability32/66 checks passed
46/35
Needs attention+23 bonus
Layer 4: Payments & Machine Commerce0/6 checks passed
0/0
N/A (Skipped)

Problems

21 detected
●registry-branding
discovery

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

●npm-sdk-package
discovery

No npm package named "exa" that links back to exa.ai

●skills-sh-listed
discovery

No skills.sh skills published from exa.ai or a "exa" GitHub owner

●llms-txt-links-resolve
access

Only 6/8 sampled llms.txt links resolve (broken: https://dashboard.exa.ai/api-keys, https://mcp.exa.ai/mcp)

●markdown-html-parity
access

Markdown endpoint strips code snippets or tables present in HTML (potential semantic truncation)

●nojs-fact-integrity
access

API endpoints or authentication credentials require client-side JavaScript execution to render

●text-density-ratio
access

Text density ratio: 3%

●mcp-tools-breadth
usability

Product MCP lacks tool breadth (2 < 3 tools)

●mcp-tools-schema-dialect
usability

2/2 tools declare an older JSON Schema dialect (web_search_exa, web_fetch_exa)

●mcp-transport-sse
usability

No legacy SSE stream served on GET

●mcp-logging-notifications
usability

Server does not declare the logging capability (deprecated in MCP 2026-07-28; not scored)

●mcp-protocol-modern
usability

Does not answer server/discover; speaks only initialize-based (pre-2026-07-28) revisions

●mcp-wire-compatibility
usability

Answers only the legacy initialize handshake

●auth-md-stage-exchange
usability

auth.md missing Stage 5 (Token Exchange)

●api-error-schemas
usability

Only 25/64 operations declare typed 4xx/5xx/default responses

●api-idempotency-keys
usability

No Idempotency-Key header parameter declared

●api-rate-limit-headers
usability

No RateLimit or Retry-After headers documented

●api-curl-examples
usability

No cURL examples in the spec

●api-code-samples
usability

No x-codeSamples declared

●api-rfc7807-problem-details
usability

No RFC 7807 problem+json responses declared

●api-webhook-declarations
usability

No webhooks or callbacks declared

Solutions

4 available
●Configure API Reference Link
surfaces
Publish a dedicated API Reference link to describe raw endpoints clearly.
●Bridge Developer Authentication Link
surfaces
Ensure login and API key provisioning screens are discoverable for automated credential setups.
●Add Developer Dashboard Link
surfaces
Ensure a links dashboard is provided for developer keys and workspace management.
●Add SDK Integration Guides
surfaces
Publish SDK install guides (npm/pip) linked from docs or homepage.

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

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

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, 202680BARS 3.3.1View →
Nov 2, 202680BARS 3.3.1Viewing
Oct 26, 202679BARS 3.3.1View →
Oct 25, 202684BARS 3.3.1View →
Oct 23, 202679BARS 3.3View →
Oct 19, 202682BARS 3.2View →
Oct 12, 202678BARS 3.2View →
Oct 12, 202678BARS 3.2View →
Sep 18, 202660CARS 3.0View →
Aug 5, 202677—ARS 1.0View →
Share your scorecard