Skip to main content
Glama

Server Details

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

If you are the author of this connector, you can claim ownership. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-06-18
URL
Repository
CarlSR9001/whetstone
GitHub Stars
0
Server Listing
link.cyberelf.whetstone/tools
ChatGPT
–
Claude
–

TDQS

B3.4/5.0

Scored across 14 tools

Disambiguation3/5

Most tools have distinct targets, but promotion_gate, open_bench_submit, and inspect_promotion all involve grading paired baseline/candidate outcomes and issuing promotion decisions. The descriptions clarify the context, yet an agent could still misselect among them. The tiered report_card vs open_bench tools are otherwise well-differentiated.

Naming Consistency3/5

The set mostly uses snake_case and the report_card_* and open_bench_* prefixes add structure, but conventions are mixed: verb_noun names like audit_leakage coexist with noun phrases like bank_health and memory_relevance, plus compound forms like counterexample_hunt and report_card_start. The names are readable but not consistently patterned.

Tool Count4/5

14 tools is within a reasonable range, and the set covers multiple workflows: report-card demos, open-bench sessions, promotion gating, diagnostics, and utilities. However, tools like memory_relevance, replay_trace, and safe_patch feel tangential to the core promotion/benchmark purpose, making the overall scope slightly broad.

Completeness4/5

The core promotion lifecycle is well covered: report_card_start/submit, open_bench_start/submit/leaderboard, promotion_gate, inspection, audit, and bank health diagnostics form a coherent workflow from session start through publication. Minor gaps exist, such as no explicit session cancellation or deeper per-item drilldown, but the one-shot session model reduces the need for full CRUD coverage.

Available Tools

14 tools
about_whetstoneAInspect

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

Inputs: no named parameters.

audit_leakageBInspect

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'.

Inputs: exam (required), exposure, fingerprint_max_n, similarity_threshold, +2 more.

bank_healthBInspect

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

Inputs: history (required), items.

counterexample_huntAInspect

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'.

Inputs: expression (required), ns, seed, steps, +1 more.

inspect_promotionBInspect

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'.

Inputs: exam (required), baseline (required), candidate (required), policy, +9 more.

memory_relevanceCInspect

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

Inputs: memories (required), objective (required), current_step, token_budget, +3 more.

open_bench_leaderboardAInspect

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.

Inputs: no named parameters.

open_bench_startAInspect

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.

Inputs: challenge.

open_bench_submitAInspect

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.

Inputs: session_id (required), baseline_answers (required), baseline_manifest (required), candidate_answers (required), +3 more.

promotion_gateAInspect

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'.

Inputs: baseline (required), candidate (required), policy, domains, +3 more.

replay_traceAInspect

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

Inputs: events (required), notes.

report_card_startAInspect

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.

Inputs: challenge.

report_card_submitAInspect

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.

Inputs: answers (required), session_id (required).

safe_patchAInspect

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

Inputs: document (required), operations (required), reason.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      B
      maintenance
      Signed receipts for agent actions and a read-only-allowlist decision gate, as an MCP server. Ed25519, plus ML-DSA-65 when the post-quantum backend is available. gate_decision returns ALLOW, DENY or ESCALATE from action names and does not observe or block anything. verify_receipt takes expected_kid to pin which key signed. Seven tools.
      16
      50 PyPI
      1
      Apache 2.0
    • A
      license
      Not graded
      quality
      D
      maintenance
      Provides cryptographic governance receipts for AI agents, enabling pre-execution evaluation and signed verdicts (EXECUTE/BLOCK/REVIEW/SHADOW) with offline-verifiable audit trails.
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Verifiable action receipts for AI agents — agents sign claims locally, an independent witness countersigns and timestamps, anyone can verify offline.
      9 npm
      MIT
    • A
      license
      A
      quality
      A
      maintenance
      The accountability layer for AI agents — a named human's signed yes before an agent does anything irreversible (payment, record change, deploy), then an offline-verifiable Trust Receipt. Apache-2.0, formally verified.
      3
      550
      Apache 2.0
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.