# Cyberelf Whetstone Tools MCP server

Source: https://glimind.com/server/mcp-registry%2Flink.cyberelf.whetstone%2Ftools
Registry id: `mcp-registry/link.cyberelf.whetstone/tools`
Status: live (checked 2026-10-26T23:20:43.123Z)

## Measurements (30 days)

- Uptime: 99.97%
- Checks: 4924
- Outages (90 days): 4

## Install

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

Claude Code:

```sh
claude mcp add --transport http cyberelf-whetstone-tools-mcp-server https://whetstone.cyberelf.link/mcp
```

## 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 ex
- `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-
- `inspect_promotion`: Quarantine declared exposure, compare paired baseline/candidate outcomes on the clean remainder, and issue a promotion receipt. Bring your own exam rows, exposu
- `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
- `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
- `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 o
- `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.
- `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 checke
- `safe_patch`: Apply a section-scoped Markdown patch under conservation checks (untouched sections stay byte-identical; protected tokens preserved). Full example: GET /api/exa

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.