Check website AI-readiness: Schema.org, llms.txt, E-E-A-T, robots.txt. Works in Cursor & Claude.
Dev & Codev1.0.0streamable-httpai-readiness.mingles.ai repository
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 708ms |
| protocol | 15 / 15 | valid JSON-RPC initialize result, protocolVersion 2024-11-05, serverInfo ai-site-scorer@1.0.0 |
| tooling | 35 / 35 | tools/list OK: 5 tools e.g. "analyze_url"; 5/5 described, 5/5 fully-typed schemas, median description 213 chars |
| latency | 7 / 10 | initialize round-trip 708ms |
| provenance | 15 / 15 | description present; repository linked; version 1.0.0; namespace io.github.MinglesAI matches endpoint/repo |
Score 97/100 · latency 708ms · 5 tools · auth: open
Claude Code:
claude mcp add --transport http ai-site-scorer https://ai-readiness.mingles.ai/api/mcp/
Generic MCP client config:
{ "mcpServers": { "ai-site-scorer": { "type": "http", "url": "https://ai-readiness.mingles.ai/api/mcp/" } } }
MCP Queen is a graded index, not a middleman — your agent connects directly to the server above. Check the grade and evidence first; that's the point.
Share this server: permalink https://mcpqueen.com/s/io.github.MinglesAI/ai-site-scorer · referral link https://mcpqueen.com/go/io.github.MinglesAI/ai-site-scorer (counts as “routed via the queen”).
Live badge, re-probed continuously — put it in your README:
[](https://mcpqueen.com/s/io.github.MinglesAI/ai-site-scorer)
Think the grade is wrong? Fix the finding the evidence shows, then the next probe cycle picks it up automatically (full cycle ≈ 3 days) — or open a dispute via the MCP endpoint.
Email alerts when the grade changes or the endpoint stops answering. Double-opt-in, one-click unwatch, free while in beta.
| When (UTC) | Grade | Score | Latency |
|---|---|---|---|
| 2026-07-13 17:47 | A | 97 | 708ms |