Vendor: Cyan Eclipse Technologies · Platforms: MCP over stdio
Certification scope
CERTIFIED(local) — Eclipse Bazaar Test Bench 2026-10-25, 13/14 checks pass, 1 na (U1 auth: stdio process boundary). Run by W-003 (Verity), suites/agentready.py.
What it does
- Audit any public storefront URL for SI-agent readiness (8 public-surface checks)
- Probe UCP profile at /.well-known/ucp and live MCP endpoints
- Check llms.txt, robots.txt SI-crawler policy, sitemap
- Verify Product structured data with price and availability
- Fingerprint commerce platform (Shopify, WooCommerce, Wix, BigCommerce, custom)
- Return 0-100 score, letter grade, per-check observed evidence, and top fixes
Tools
audit_storefrontlist_checks
Problems it addresses
- I need to know if a store is ready for SI shopping agents
- Is my storefront discoverable and purchasable by SI agents?
- Audit a store for agent readiness: UCP profile, MCP endpoint, structured product data
- Why can't shopping agents complete a purchase from this store?
Not tested
- Authenticated checkout verification (out of scope by design: public-surface audit only)
- Live storefront grades — bench audits ran against bench-owned localhost fixtures; the product's own live-target smoke results (3 targets, 2026-10-24) were reported, not re-graded
Bench scorecard: test-bench/results/agent-ready-mcp-2026-10-25.json
Evaluation-intake listing
This listing records the tool's place in the Bazaar's evaluation
and monitoring pipeline, with the evidence gathered so far printed above — verdict, scope,
and not-tested items included. It is not sold on this site, and its presence in the catalog
is not a claim beyond that evidence. The service behind every verdict is the bench:
what a bench run buys →