link.cyberelf.whetstone/tools
up checked
Unclaimed · Unverified
Agent searches it appeared in, last 30 days: 0. Run this server? Claim the listing: verified label, uptime alerts and analytics.
Publisher-provided title
Whetstone
Publisher-provided description
Verifier-grounded AI promotion gates, disposable report cards, and signed PASS/HOLD/BLOCK receipts.
Summary by lookupd
Provides verifier-graded promotion gates, report cards, and signed PASS/HOLD/BLOCK receipts for comparing AI agent or model outputs.
Install
Claude Code, remote (streamable-http)
claude mcp add --transport http tools https://whetstone.cyberelf.link/mcp
Codex, remote (streamable-http)
codex mcp add tools --url https://whetstone.cyberelf.link/mcp
Cursor, remote (streamable-http) → .cursor/mcp.json
{
"mcpServers": {
"tools": {
"url": "https://whetstone.cyberelf.link/mcp"
}
}
}Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.
Tools (14 tools)
Publisher-provided text
inspect_promotionQuarantine declared exposure, compare paired baseline/candidate outcomes on the clean remainder, and issue a promotion receipt. Bring your own exam rows, exposuaudit_leakageExact declared-exposure audit over your exam rows: row identity, behavioral fingerprints for graph-DSL expressions, text-similarity review flags, and a clean expromotion_gatePASS, HOLD, or BLOCK from paired per-item results: gains, regressions, exact McNemar p-value, per-domain breakdown. Full example: GET /api/examples key 'gate'.bank_healthItem-lifecycle diagnostics over your grading history: discriminators, saturated and flaky items, frontier gaps. Full example: GET /api/examples key 'health'.safe_patchApply a section-scoped Markdown patch under conservation checks (untouched sections stay byte-identical; protected tokens preserved). Full example: GET /api/exacounterexample_huntBounded simulated-annealing search for a graph counterexample inside a DSL predicate class, with an exact certificate when found. CPU-bounded and strictly rate-memory_relevanceCompare query-free salience against objective-conditioned relevance for a set of memories under a token budget. Full example: GET /api/examples key 'memory'.replay_traceTurn reasoning-emulator control events into checkpoints, rewinds, notes, and a timeline. Full example: GET /api/examples key 'replay'.report_card_startTIER 1: start a disposable report-card session. Returns exam items (graph-repair prompts minted from the repository's public frontier) for THIS agent to answer.report_card_submitTIER 1: submit answers for a report-card session and receive the graded report (per-item verdicts, per-domain totals, SHA-256 commitments). Grading is by checkeopen_bench_startTIER 2: start a one-shot Open Promotion Bench session. Returns six fresh virtual-repository scope-integrity tasks. Run a baseline and candidate independently onopen_bench_submitTIER 2: grade paired baseline and candidate patches, count gains/regressions/ties, and issue PASS/HOLD/BLOCK. Set publish=true plus attestation=true to append oopen_bench_leaderboardTIER 2: list the self-attested public Open Promotion Bench receipts. Entries contain manifests, verdicts, item-level transitions, and commitments but never taskabout_whetstoneWhat this service is: the tool catalog, the tier boundaries, and where the source lives.
Details
- Version: 0.8.0
- Transports: streamable-http
- Uptime (7 days): 100%
- Median latency: 266 ms
- First indexed:
- Last seen in registry:
- Repository: https://github.com/CarlSR9001/whetstone
- Website: https://whetstone.cyberelf.link/
Badge for your README
Shows this live status and links here; updates hourly.
[](https://lookupd.com/servers/link.cyberelf.whetstone/tools)
- 62033 servers
- Last crawl: 2026-11-11T15:38:39.561Z
- API base:
https://api.lookupd.com - MCP URL:
https://api.lookupd.com/mcp