A secret store for AI agents: the agent never sees the plaintext.
AI & Agentsv1.3.0streamable-httproyashbrook.com repository
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 515ms |
| protocol | 15 / 15 | valid JSON-RPC initialize result, protocolVersion 2025-06-18, serverInfo hush@1.0.0 |
| tooling | 35 / 35 | tools/list OK: 1 tools e.g. "get_skill"; 1/1 described, 1/1 fully-typed schemas, median description 68 chars |
| latency | 7 / 10 | initialize round-trip 515ms |
| provenance | 15 / 15 | description present; repository linked; version 1.3.0; namespace com.royashbrook matches endpoint/repo |
Score 97/100 · latency 515ms · 1 tools · auth: open
Claude Code:
claude mcp add --transport http hush https://royashbrook.com/hush
Generic MCP client config:
{ "mcpServers": { "hush": { "type": "http", "url": "https://royashbrook.com/hush" } } }
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/com.royashbrook/hush · referral link https://mcpqueen.com/go/com.royashbrook/hush (counts as “routed via the queen”).
Live badge, re-probed continuously — put it in your README:
[](https://mcpqueen.com/s/com.royashbrook/hush)
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 06:30 | A | 97 | 515ms |