Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, email [email protected] and we’ll put it right.

Whetstone

REMOTE · WHETSTONE.CYBERELF.LINK · SCANNED AUG 3

Promotion gate for AI agents: leakage audits, exact-statistics verdicts, and a live report card.

+3 this week 59 Trust /100
Trust breakdown (6 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability61
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1693 tokens (~120/item across 14 items; 14 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
  • Stability check failed: schema churn in the 8 days we've observed: 0 tool removals, 8 breaking changes, 0 auth/transport breaks, 3 additions. See how to fix → Fail
Tool Coverage82
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 46% of tool parameters carry a description.Partial
Capabilities60
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

remote · whetstone.cyberelf.link

# add to Claude Code
claude mcp add --transport http link-cyberelf-whetstone-tools https://whetstone.cyberelf.link/mcp
# ~/.codex/config.toml
[mcp_servers.link-cyberelf-whetstone-tools]
url = "https://whetstone.cyberelf.link/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "link-cyberelf-whetstone-tools": {
      "type": "remote",
      "url": "https://whetstone.cyberelf.link/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add link-cyberelf-whetstone-tools --url https://whetstone.cyberelf.link/mcp --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  link-cyberelf-whetstone-tools:
    url: "https://whetstone.cyberelf.link/mcp"
// mcp.json
{
  "mcpServers": {
    "link-cyberelf-whetstone-tools": {
      "type": "http",
      "url": "https://whetstone.cyberelf.link/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 2 Aug 26 +2
    • The server rewrote its instructions, which are the text every model session reads security
    • Schema quality: 1385 → 1693 functional
    • Tool coverage: 53% → 46% functional
    • Schema quality: fair → good functional
    • Server version: 0.5.3 → 0.6.0 functional
    • New tool “open_bench_leaderboard” functional
    • New tool “open_bench_start” functional
    • New tool “open_bench_submit” functional
  • 31 Jul 26 +2
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 30 Jul 26 −2
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 28 Jul 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

  • 27 Jul 26 +1
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 26 Jul 26 55

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 3 Aug 2026 · Probed https://whetstone.cyberelf.link/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=whetstone.cyberelf.link CN=YE2,O=Let's Encrypt,C=US 12 Jul 2026 10 Oct 2026 ECDSA 256 ECDSA-SHA384 50fd1fff6c4011b326fb07f21caae099aec
SANs: whetstone.cyberelf.link
CN=YE2,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 4df3b15dd6c0784c507cd37b58e6f115
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd
DNSSEC insecure

Validation of whetstone.cyberelf.link. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
link. present 16766 13 Verified
cyberelf.link. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=31536000
content-security-policy default-src 'self'; script-src 'self'; style-src 'self' 'unsafe-inline'; img-src 'self' data:; connect-src 'self'; object-src 'none'; base-uri 'none'; form-action 'self'; frame-ancestors 'none'
x-content-type-options nosniff
x-frame-options DENY
referrer-policy no-referrer
permissions-policy camera=(), microphone=(), geolocation=(), payment=()
Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://whetstone.cyberelf.link/mcp Verified 200
http (plaintext) http://whetstone.cyberelf.link/mcp HTTPS enforced 301 https://whetstone.cyberelf.link/mcp
MCP tools — 14 exposed · ~1,433 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability.

Tool Tokens
about_whetstone ~29

What this service is: the tool catalog, the tier boundaries, and where the source lives.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

audit_leakage ~142

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'.

NameTypeReqDescription
enable_behavioral_fingerprintboolean
enable_text_similarityboolean
examarrayyesExam rows. Each row needs item_id (or id) plus prompt/content/input/task/question/expression.
exposurearrayDeclared exposure rows carrying identity/content fields and an optional source or path.
fingerprint_max_ninteger
similarity_thresholdnumber

No output schema declared.

No examples provided.

bank_health ~61

Item-lifecycle diagnostics over your grading history: discriminators, saturated and flaky items, frontier gaps. Full example: GET /api/examples key 'health'.

NameTypeReqDescription
historyarrayyesObserved item/system outcomes.
itemsarrayOptional item definitions.

No output schema declared.

No examples provided.

counterexample_hunt ~120

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'.

NameTypeReqDescription
expressionstringyesGraph predicate in the Whetstone DSL, for example: is_connected and is_triangle_free and not is_bipartite
nsarrayGraph sizes searched.
restartsinteger
seedinteger
stepsinteger

No output schema declared.

No examples provided.

inspect_promotion ~246

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'.

NameTypeReqDescription
baselineobjectyesitem_id -> boolean pass/fail result for the baseline system.
baseline_namestring
candidateobjectyesitem_id -> boolean pass/fail result for the candidate system.
candidate_namestring
domainsobjectOptional item_id -> domain label mapping.
enable_behavioral_fingerprintboolean
enable_text_similarityboolean
examarrayyesExam rows. Each row needs item_id (or id) plus prompt/content/input/task/question/expression.
exposurearrayDeclared exposure rows carrying identity/content fields and an optional source or path.
fingerprint_max_ninteger
policyobjectExplicit promotion policy. Omitted fields use the documented defaults.
retained_probeobjectOptional retained-capability result checked alongside the paired cohort.
similarity_thresholdnumber

No output schema declared.

No examples provided.

memory_relevance ~113

Compare query-free salience against objective-conditioned relevance for a set of memories under a token budget. Full example: GET /api/examples key 'memory'.

NameTypeReqDescription
context_entitiesarrayEntities already active in context.
current_stepinteger
memoriesarrayyesMemories to rank.
objectivestringyes
objective_entitiesarrayOptional explicit entities when the objective text is not self-describing.
question_kindstring
token_budgetinteger

No output schema declared.

No examples provided.

open_bench_leaderboard ~49

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.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

open_bench_start ~75

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.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

open_bench_submit ~121

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.

NameTypeReqDescription
attestationboolean
baseline_answersobjectyes
baseline_manifestobjectyes
candidate_answersobjectyes
candidate_manifestobjectyes
publishboolean
session_idstringyes

No output schema declared.

No examples provided.

promotion_gate ~151

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'.

NameTypeReqDescription
baselineobjectyesitem_id -> boolean pass/fail result for the baseline system.
baseline_namestring
candidateobjectyesitem_id -> boolean pass/fail result for the candidate system.
candidate_namestring
domainsobjectOptional item_id -> domain label mapping.
policyobjectExplicit promotion policy. Omitted fields use the documented defaults.
retained_probeobjectOptional retained-capability result checked alongside the paired cohort.

No output schema declared.

No examples provided.

replay_trace ~60

Turn reasoning-emulator control events into checkpoints, rewinds, notes, and a timeline. Full example: GET /api/examples key 'replay'.

NameTypeReqDescription
eventsarrayyesOrdered reasoning-emulator events.
notesarrayOptional analyst notes.

No output schema declared.

No examples provided.

report_card_start ~92

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.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

report_card_submit ~103

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: any verified strict refinement of the item's predicate passes; no answer key exists. The session is destroyed by this call.

NameTypeReqDescription
answersobjectyesitem_id -> answer (a DSL predicate, or the JSON reply the prompt asked for)
session_idstringyes

No output schema declared.

No examples provided.

safe_patch ~71

Apply a section-scoped Markdown patch under conservation checks (untouched sections stay byte-identical; protected tokens preserved). Full example: GET /api/examples key 'safepatch'.

NameTypeReqDescription
documentstringyesComplete Markdown document to patch.
operationsarrayyes
reasonstring

No output schema declared.

No examples provided.