# Whetstone (remote · whetstone.cyberelf.link)

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

- Trust score: 59/100 (low)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `whetstone.cyberelf.link`: 59/100 (this document), [markdown](https://verifymcp.io/servers/link-cyberelf-whetstone-tools/whetstone.md), [page](https://verifymcp.io/servers/link-cyberelf-whetstone-tools/whetstone)

## Channel facts

- Endpoint: `https://whetstone.cyberelf.link/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.4.5`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 14 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 61/100
  - AI-judged instruction clarity (good).
  - 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.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability check failed: schema churn in the 8 days we've observed: 0 tool removals, 8 breaking changes, 0 auth/transport breaks, 3 additions.
- **Tool Coverage**: 82/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 46% of tool parameters carry a description.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### Claude

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

### Codex

```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
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add link-cyberelf-whetstone-tools --url https://whetstone.cyberelf.link/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  link-cyberelf-whetstone-tools:
    url: "https://whetstone.cyberelf.link/mcp"
```

### Other

```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 recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 59, +2)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 1385 → 1693
- [functional regression] 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”

### 2026-07-31 (score 57, +2)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 55, −2)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-28 (score 57, +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.

### 2026-07-27 (score 56, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 55)

First indexed and scored.

## MCP tools (14)

### `inspect_promotion` (~246 tokens)

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'.

Input parameters:

- `baseline` (object, required): item_id -> boolean pass/fail result for the baseline system.
- `baseline_name` (string)
- `candidate` (object, required): item_id -> boolean pass/fail result for the candidate system.
- `candidate_name` (string)
- `domains` (object): Optional item_id -> domain label mapping.
- `enable_behavioral_fingerprint` (boolean)
- `enable_text_similarity` (boolean)
- `exam` (array, required): Exam rows. Each row needs item_id (or id) plus prompt/content/input/task/question/expression.
- `exposure` (array): Declared exposure rows carrying identity/content fields and an optional source or path.
- `fingerprint_max_n` (integer)
- `policy` (object): Explicit promotion policy. Omitted fields use the documented defaults.
- `retained_probe` (object): Optional retained-capability result checked alongside the paired cohort.
- `similarity_threshold` (number)

### `audit_leakage` (~142 tokens)

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'.

Input parameters:

- `enable_behavioral_fingerprint` (boolean)
- `enable_text_similarity` (boolean)
- `exam` (array, required): Exam rows. Each row needs item_id (or id) plus prompt/content/input/task/question/expression.
- `exposure` (array): Declared exposure rows carrying identity/content fields and an optional source or path.
- `fingerprint_max_n` (integer)
- `similarity_threshold` (number)

### `promotion_gate` (~151 tokens)

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'.

Input parameters:

- `baseline` (object, required): item_id -> boolean pass/fail result for the baseline system.
- `baseline_name` (string)
- `candidate` (object, required): item_id -> boolean pass/fail result for the candidate system.
- `candidate_name` (string)
- `domains` (object): Optional item_id -> domain label mapping.
- `policy` (object): Explicit promotion policy. Omitted fields use the documented defaults.
- `retained_probe` (object): Optional retained-capability result checked alongside the paired cohort.

### `bank_health` (~61 tokens)

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

Input parameters:

- `history` (array, required): Observed item/system outcomes.
- `items` (array): Optional item definitions.

### `safe_patch` (~71 tokens)

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

Input parameters:

- `document` (string, required): Complete Markdown document to patch.
- `operations` (array, required)
- `reason` (string)

### `counterexample_hunt` (~120 tokens)

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'.

Input parameters:

- `expression` (string, required): Graph predicate in the Whetstone DSL, for example: is_connected and is_triangle_free and not is_bipartite
- `ns` (array): Graph sizes searched.
- `restarts` (integer)
- `seed` (integer)
- `steps` (integer)

### `memory_relevance` (~113 tokens)

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

Input parameters:

- `context_entities` (array): Entities already active in context.
- `current_step` (integer)
- `memories` (array, required): Memories to rank.
- `objective` (string, required)
- `objective_entities` (array): Optional explicit entities when the objective text is not self-describing.
- `question_kind` (string)
- `token_budget` (integer)

### `replay_trace` (~60 tokens)

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

Input parameters:

- `events` (array, required): Ordered reasoning-emulator events.
- `notes` (array): Optional analyst notes.

### `report_card_start` (~92 tokens)

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` (~103 tokens)

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.

Input parameters:

- `answers` (object, required): item_id -> answer (a DSL predicate, or the JSON reply the prompt asked for)
- `session_id` (string, required)

### `open_bench_start` (~75 tokens)

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` (~121 tokens)

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.

Input parameters:

- `attestation` (boolean)
- `baseline_answers` (object, required)
- `baseline_manifest` (object, required)
- `candidate_answers` (object, required)
- `candidate_manifest` (object, required)
- `publish` (boolean)
- `session_id` (string, required)

### `open_bench_leaderboard` (~49 tokens)

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` (~29 tokens)

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

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/link-cyberelf-whetstone-tools/whetstone#diagnostics

## Score history

- 2026-08-03: 59
- 2026-08-02: 59
- 2026-08-01: 57
- 2026-07-31: 57
- 2026-07-30: 55
- 2026-07-29: 57
- 2026-07-28: 57
- 2026-07-27: 56
- 2026-07-26: 55

## Links

- Remote endpoint: https://whetstone.cyberelf.link/mcp
- Repository: https://github.com/CarlSR9001/whetstone
- Website: https://whetstone.cyberelf.link/
- Changelog RSS feed: https://verifymcp.io/servers/link-cyberelf-whetstone-tools/whetstone/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/link-cyberelf-whetstone-tools/whetstone/changelog.json
- HTML version of this page: https://verifymcp.io/servers/link-cyberelf-whetstone-tools/whetstone