INDIVIDUAL MCP TOOL
memory_relevance
Compare query-free salience against objective-conditioned relevance for a set of memories under a token budget.
LIVE ENDPOINT
https://whetstone.cyberelf.link/mcp
Connect to this endpoint to inspect the live schema for memory_relevance and invoke it with your own arguments.
Indexed input schema
{}Risk classification
Inferred read-only · medium confidence · heuristic, not a guarantee.
- A tool name, description or schema mentions credentials.
Parent server
CONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.whetstone-tools]
url = "https://whetstone.cyberelf.link/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"whetstone-tools": {
"type": "http",
"url": "https://whetstone.cyberelf.link/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: whetstone-tools
Remote MCP URL: https://whetstone.cyberelf.link/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"whetstone-tools": {
"url": "https://whetstone.cyberelf.link/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"whetstone-tools": {
"type": "http",
"url": "https://whetstone.cyberelf.link/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "whetstone-tools",
"transport": "streamable-http",
"url": "https://whetstone.cyberelf.link/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
Related tools
inspect_promotion— Quarantine declared exposure, compare paired baseline/candidate outcomes on the clean remainder, and issue a promotion receipt.audit_leakage— Exact declared-exposure audit over your exam rows: row identity, behavioral fingerprints for graph-DSL expressions, text-similarity review flags, and a clean exam export.promotion_gate— PASS, HOLD, or BLOCK from paired per-item results: gains, regressions, exact McNemar p-value, per-domain breakdown.bank_health— Item-lifecycle diagnostics over your grading history: discriminators, saturated and flaky items, frontier gaps.safe_patch— Apply a section-scoped Markdown patch under conservation checks (untouched sections stay byte-identical; protected tokens preserved).counterexample_hunt— Bounded simulated-annealing search for a graph counterexample inside a DSL predicate class, with an exact certificate when found.replay_trace— Turn reasoning-emulator control events into checkpoints, rewinds, notes, and a timeline.report_card_start— TIER 1: start a disposable report-card session.