MCP serverlink.cyberelf.whetstone/tools

Verifier-grounded AI promotion gates, disposable report cards, and signed PASS/HOLD/BLOCK receipts.

UNRATEDActivestreamable-httpwhetstone.cyberelf.link

Overview

Score?

UNRATED 0.691

of what a free look can see, on 30 looks

Looks

last 10 hr ago

Tools

More info

URL

whetstone.cyberelf.link/mcp

streamable-http

Says it is

whetstone-tools 0.8.0

protocol 2025-06-18

In the record since

32 days ago

Among servers18,413 with a card

0median 0.606 · this server 0.691 · highest on record 0.8561

Toolsfrom sha256:402242c1c6…bd3028

The tools this server lists, read out of the definition it returned
Tool	Schema
about_whetstone What this service is: the tool catalog, the tier boundaries, and where the source lives.	input · no output
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. Full exam	input · no output
bank_health Item-lifecycle diagnostics over your grading history: discriminators, saturated and flaky items, frontier gaps. Full example: GET /api/examples key 'health'.	input · no output
counterexample_hunt Bounded simulated-annealing search for a graph counterexample inside a DSL predicate class, with an exact certificate when found. CPU-bounded and strictly rate-limited. Full exampl	input · no output
inspect_promotion Quarantine declared exposure, compare paired baseline/candidate outcomes on the clean remainder, and issue a promotion receipt. Bring your own exam rows, exposure records, and per-	input · no output
memory_relevance Compare query-free salience against objective-conditioned relevance for a set of memories under a token budget. Full example: GET /api/examples key 'memory'.	input · no output
open_bench_leaderboard TIER 2: list the self-attested public Open Promotion Bench receipts. Entries contain manifests, verdicts, item-level transitions, and commitments but never task contents or submitt	input · no output
open_bench_start TIER 2: start a one-shot Open Promotion Bench session. Returns six fresh virtual-repository scope-integrity tasks. Run a baseline and candidate independently on the same cohort, th	input · no output
open_bench_submit TIER 2: grade paired baseline and candidate patches, count gains/regressions/ties, and issue PASS/HOLD/BLOCK. Set publish=true plus attestation=true to append only the safe manifes	input · no output
promotion_gate PASS, HOLD, or BLOCK from paired per-item results: gains, regressions, exact McNemar p-value, per-domain breakdown. Full example: GET /api/examples key 'gate'.	input · no output
replay_trace Turn reasoning-emulator control events into checkpoints, rewinds, notes, and a timeline. Full example: GET /api/examples key 'replay'.	input · no output
report_card_start TIER 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. Answer every item,	input · no output
report_card_submit TIER 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 checker spec: verified str	input · no output
safe_patch Apply a section-scoped Markdown patch under conservation checks (untouched sections stay byte-identical; protected tokens preserved). Full example: GET /api/examples key 'safepatch	input · no output

Verify it yourselfnpx teppi-check https://whetstone.cyberelf.link/mcpcurl -s https://api.teppi.xyz/v1/trust/mcp/mcs_01M1FZ2PRTKK4JAFHENX9ENCRF