VaultCrux Memory Core — 32 tools: knowledge, decisions, constraints, signals, coverage
Dev & Codev0.2.0streamable-httpapi.vaultcrux.com repository
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 1080ms |
| protocol | 15 / 15 | valid JSON-RPC initialize result, protocolVersion 2025-06-18, serverInfo vaultcrux-memory-core@v0.3.4+sha.2591acf0119c |
| tooling | 35 / 35 | tools/list OK: 75 tools e.g. "query_memory"; 75/75 described, 75/75 fully-typed schemas, median description 253 chars |
| latency | 7 / 10 | initialize round-trip 1080ms |
| provenance | 15 / 15 | description present; repository linked; version 0.2.0; namespace io.github.CueCrux matches endpoint/repo |
Score 97/100 · latency 1080ms · 75 tools · auth: open
Claude Code:
claude mcp add --transport http vaultcrux-memory-core https://api.vaultcrux.com/memory-core/mcp
Generic MCP client config:
{ "mcpServers": { "vaultcrux-memory-core": { "type": "http", "url": "https://api.vaultcrux.com/memory-core/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.CueCrux/vaultcrux-memory-core · referral link https://mcpqueen.com/go/io.github.CueCrux/vaultcrux-memory-core (counts as “routed via the queen”).
Live badge, re-probed continuously — put it in your README:
[](https://mcpqueen.com/s/io.github.CueCrux/vaultcrux-memory-core)
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 15:01 | A | 97 | 1080ms |