Whetstone is a remote MCP server that gives an AI agent 14 tools, among them about_whetstone, audit_leakage, bank_health. It answers at https://whetstone.cyberelf.link/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 12 September 2026; the last check, on 24 October 2026, succeeded.
Verifier-grounded AI promotion gates, disposable report cards, and signed PASS/HOLD/BLOCK receipts.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
about_whetstone | What this service is: the tool catalog, the tier boundaries, and where the source lives. |
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 example: GET /api/examples key 'leakage'. Inputs: enable_behavioral_fingerprint, enable_text_similarity, exam, exposure, fingerprint_max_n, similarity_threshold |
bank_health | Item-lifecycle diagnostics over your grading history: discriminators, saturated and flaky items, frontier gaps. Full example: GET /api/examples key 'health'. Inputs: history, items |
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 example: GET /api/examples key 'counterexample'. Inputs: expression, ns, restarts, seed, steps |
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-item results. Full example: GET /api/examples key 'inspector Inputs: baseline, baseline_name, candidate, candidate_name, domains, enable_behavioral_fingerprint |
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'. Inputs: context_entities, current_step, memories, objective, objective_entities, question_kind |
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 | 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 a Inputs: challenge |
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 manifests and sanitized receipt to the public board; tasks and answ Inputs: attestation, baseline_answers, baseline_manifest, candidate_answers, candidate_manifest, publish |
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'. Inputs: baseline, baseline_name, candidate, candidate_name, domains, policy |
replay_trace | Turn reasoning-emulator control events into checkpoints, rewinds, notes, and a timeline. Full example: GET /api/examples key 'replay'. Inputs: events, notes |
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, then call report_card_submit exactly once. Sessions are one- Inputs: challenge |
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 strict refinements are reported separately, and promotion grade Inputs: answers, session_id |
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'. Inputs: document, operations, reason |
Every block below points at https://whetstone.cyberelf.link/mcp. Pick your client and copy.
claude mcp add --transport http whetstone https://whetstone.cyberelf.link/mcp
{
"mcpServers": {
"whetstone": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://whetstone.cyberelf.link/mcp"]
}
}
}{
"mcpServers": {
"whetstone": {
"url": "https://whetstone.cyberelf.link/mcp"
}
}
}{
"servers": {
"whetstone": {
"type": "http",
"url": "https://whetstone.cyberelf.link/mcp"
}
}
}{
"context_servers": {
"whetstone": {
"url": "https://whetstone.cyberelf.link/mcp"
}
}
}{
"mcpServers": {
"whetstone": {
"serverUrl": "https://whetstone.cyberelf.link/mcp"
}
}
}{
"mcpServers": {
"whetstone": {
"url": "https://whetstone.cyberelf.link/mcp"
}
}
}name: Whetstone
version: 0.0.1
schema: v1
mcpServers:
- name: Whetstone
type: streamable-http
url: https://whetstone.cyberelf.link/mcp{
"mcpServers": {
"whetstone": {
"httpUrl": "https://whetstone.cyberelf.link/mcp"
}
}
}{
"mcpServers": {
"whetstone": {
"type": "http",
"url": "https://whetstone.cyberelf.link/mcp"
}
}
}{
"mcpServers": {
"whetstone": {
"url": "https://whetstone.cyberelf.link/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fwhetstone.cyberelf.link%2Fmcp&type=streamable_http&id=whetstone&name=Whetstone
It answered our last check on 24 October 2026 in 373 ms. Over 6 checks since 12 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by cyberelf.link and served from whetstone.cyberelf.link, the vendor's own domain: https://whetstone.cyberelf.link/mcp.
14, as returned by the server's own tools/list on 22 September 2026: about_whetstone, audit_leakage, bank_health, counterexample_hunt, inspect_promotion, memory_relevance, open_bench_leaderboard, open_bench_start, and 6 more.
It answered our last check on 24 October 2026 in 373 ms. Over 6 checks since 12 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://whetstone.cyberelf.link/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: link.cyberelf.whetstone. Endpoint host: whetstone.cyberelf.link. ARD identifier: urn:air:link.cyberelf.whetstone:mcp:tools.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.