AgentReady MCP
Can an AI agent actually buy from your store? Score it, see the evidence, fix the gaps.
status: liveclass: mcpCommerce ReadinessAudits
Vendor: Cyan Eclipse Technologies
What it does
- Audit any public storefront URL for AI-agent readiness (8 public-surface checks)
- Probe UCP profile at /.well-known/ucp and live MCP endpoints
- Check llms.txt, robots.txt AI-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_storefront · list_checks
Platforms
- MCP over stdio
Certification
Bench verdict: CERTIFIED(local)
Certified 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.
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 (evidence): https://eclipsebazaar.com/cards/agent-ready-mcp-2026-10-25.json
Pricing
Free local audit (open reference implementation); hosted monitoring tier planned at $99-$199/mo (not yet launched)
Install / verify
uvx eclipse-agentready
Official MCP Registry name: io.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/agent-ready
Registry listing: https://registry.modelcontextprotocol.io/v0.1/servers/io.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC%2Fagent-ready/versions/0.1.1
Verify any MCP server in your client configs against this catalog with bazaar check (Eclipse Bazaar MCP / CLI — see llms.txt).