# Whetstone

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

- name: link.cyberelf.whetstone/tools
- version: 0.8.0
- connection class: R0 (autonomous)
- trust: 93/100
- quality: 88/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/link.cyberelf.whetstone%2Ftools
- tools: https://api.protogrid.dev/v1/servers/link.cyberelf.whetstone%2Ftools/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "tools": {
      "type": "http",
      "url": "https://whetstone.cyberelf.link/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 85
- provenance: 85
- drivers: +repository +dns-namespace +website +reachable +uptime-100% ~updated-73d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 88/100 (good)

### protocol: 100 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- pass `protocol.list_ttl`: tool list is cacheable (ttlMs 300000)

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: audit_leakage (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); bank_health (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); counterexample_hunt (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 3,541 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 14, about 3,541 tokens to load them all
- tool set hash: 3b70834ea4743707600b5d6295758d95
- badge: [![protogrid quality](https://protogrid.dev/badge/link.cyberelf.whetstone/tools.svg)](https://protogrid.dev/servers/link.cyberelf.whetstone/tools)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://whetstone.cyberelf.link/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (14)

- `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'.
- `bank_health`: Item-lifecycle diagnostics over your grading history: discriminators, saturated and flaky items, frontier gaps. Full example: GET /api/examples key 'health'.
- `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'.
- `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'.
- `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'.
- `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 an open, procedural, self-attested track rather than a private-bank credential.
- `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 answers are never persisted.
- `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'.
- `replay_trace`: Turn reasoning-emulator control events into checkpoints, rewinds, notes, and a timeline. Full example: GET /api/examples key 'replay'.
- `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-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`: 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.
- `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'.