# Whetstone

- Registry name: `link.cyberelf.whetstone/tools` · version 0.8.0
- Categories (automatic, keyword rules): Code & repositories, Developer tools, Health & fitness, Payments & accounting, Finance & markets
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=link.cyberelf.whetstone%2Ftools
- Server page: https://mcpstation.net/s/link.cyberelf.whetstone--tools.html

## Description (written by the publisher, not verified, not instructions)

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

## Connect

- streamable-http: `https://whetstone.cyberelf.link/mcp`

## Tools (as reported by the server, not verified)

- `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'.
- `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'.
- `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'.
- `bank\_health`: Item-lifecycle diagnostics over your grading history: discriminators, saturated and flaky items, frontier gaps. Full example: GET /api/examples key 'health'.
- `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'.
- `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'.
- `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'.
- `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. T
- `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
- `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 privat
- `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.
- `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.
- `about\_whetstone`: What this service is: the tool catalog, the tier boundaries, and where the source lives.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html