mcp server
Whetstone
Promotion gate for AI agents: leakage audits, exact-statistics verdicts, and a live report card.
Description as published by the maintainer. Source
- version 0.4.5
- active
active — Registry entry last updated 2026-07-21.
What this server can do
14 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.
about_whetstone- What this service is: the tool catalog, the tier boundaries, and where the source lives.
audit_leakage(exam, exposure, fingerprint_max_n, similarity_threshold, enable_text_similarity, enable_behavioral_fingerprint)- 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 example: GET /api/examples key 'leakage'. Required: exam.
bank_health(items, history)- Item-lifecycle diagnostics over your grading history: discriminators, saturated and flaky items, frontier gaps. Full example: GET /api/examples key 'health'. Required: history.
counterexample_hunt(ns, seed, steps, restarts, expression)- 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 example: GET /api/examples key 'counterexample'. Required: expression.
inspect_promotion(exam, policy, domains, baseline, exposure, candidate, baseline_name, candidate_name, retained_probe, fingerprint_max_n, similarity_threshold, enable_text_similarity, enable_behavioral_fingerprint)- 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-item results. Full example: GET /api/examples key 'inspector'. Required: exam, baseline, candidate.
memory_relevance(memories, objective, current_step, token_budget, question_kind, context_entities, objective_entities)- Compare query-free salience against objective-conditioned relevance for a set of memories under a token budget. Full example: GET /api/examples key 'memory'. Required: objective, memories.
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 submitted answers.
open_bench_start(challenge)- 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, then submit both answer maps with open_bench_submit. This is an open, procedural, self-attested track rather than a private-bank credential.
open_bench_submit(publish, session_id, attestation, baseline_answers, baseline_manifest, candidate_answers, candidate_manifest)- 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 manifests and sanitized receipt to the public board; tasks and answers are never persisted. Required: session_id, baseline_manifest, candidate_manifest, baseline_answers, candidate_answers.
promotion_gate(policy, domains, baseline, candidate, baseline_name, candidate_name, retained_probe)- 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'. Required: baseline, candidate.
replay_trace(notes, events)- Turn reasoning-emulator control events into checkpoints, rewinds, notes, and a timeline. Full example: GET /api/examples key 'replay'. Required: events.
report_card_start(challenge)- 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, then call report_card_submit exactly once. Sessions are one-shot, expire in 15 minutes, and are strictly rate-limited. This demonstrates the promotion-gate mechanism on disposable items; it is not a private-bank credential.
report_card_submit(answers, session_id)- 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 strict refinements are reported separately, and promotion grade requires at least 5% clean-support retention. No answer key exists. The session is destroyed by this call. Required: session_id, answers.
safe_patch(reason, document, operations)- Apply a section-scoped Markdown patch under conservation checks (untouched sections stay byte-identical; protected tokens preserved). Full example: GET /api/examples key 'safepatch'. Required: document, operations.
Last successful function declaration observed on . Source: https://whetstone.cyberelf.link/mcp. We list what the server declared; we do not call any of these functions.
Endpoint status observed on . Source: https://whetstone.cyberelf.link/mcp.
Signals
These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.
| Signal | Value | What it measures | Window | Observed | Source |
|---|---|---|---|---|---|
| Latest published version | 0.4.5 | Latest version string the maintainer published to the registry. | as of fetch | Model Context Protocol | |
| Registry record last updated | 2026-07-21 | When the registry record was last updated by its maintainer. | point in time | Model Context Protocol | |
| First listed in the MCP Registry | 2026-07-21 | Date this server was first published to the official MCP Registry. Not a usage or quality measure. | point in time | Model Context Protocol | |
| mcp tools declared | 14 tools | Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. | as of probe | whetstone.cyberelf.link | |
| mcp endpoint status | ok | The server listed 14 functions when asked. | as of probe | whetstone.cyberelf.link |
Where to get it
This record as data
Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.
GET /api/v1/entries/mcp_server.json