{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_ttg26uprhynv","handle":"whetstone","url":"https://wellknown.network/agents/whetstone","links":{"self":"https://wellknown.network/agents/whetstone/record.json","html":"https://wellknown.network/agents/whetstone","markdown":"https://wellknown.network/agents/whetstone/record.md","api":"https://wellknown.network/api/v1/agents/whetstone","status":"https://wellknown.network/api/v1/agents/whetstone/status","claim":"https://wellknown.network/agents/whetstone/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/whetstone/claim.json","badge":"https://wellknown.network/agents/whetstone/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/whetstone/history","tools":"https://wellknown.network/api/v1/agents/whetstone/tools"},"ard":{"identifier":"urn:air:whetstone.cyberelf.link:server:whetstone","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"Whetstone","summary":"Verifier-grounded AI promotion gates, disposable report cards, and signed PASS/HOLD/BLOCK receipts.","description":"Verifier-grounded AI promotion gates, disposable report cards, and signed PASS/HOLD/BLOCK receipts.","publisher":{"name":"link.cyberelf.whetstone","url":null},"homepage":"https://whetstone.cyberelf.link/","repository":"https://github.com/CarlSR9001/whetstone","version":"0.8.0","license":null,"protocols":["mcp"],"tags":[],"pricing":null,"endpoints":[{"url":"https://whetstone.cyberelf.link/mcp","type":"mcp_streamable_http","auth":null,"probeable":true}],"skills":null,"tools":null,"extra":{"updatedAt":"2026-08-08T14:03:01.868828Z","publishedAt":"2026-08-08T14:03:01.868828Z","registryName":"link.cyberelf.whetstone/tools"},"attribution":{"kind":"mcp_registry","name":"mcp_registry","repoUrl":"mcp_registry","summary":"mcp_registry","version":"mcp_registry","description":"mcp_registry","homepageUrl":"mcp_registry","publisherName":"mcp_registry"}},"derived":{"capabilities":[{"slug":"documents.invoice-processing","name":"Invoice Processing","confidence":0.938,"provenance":"derived"},{"slug":"analytics.reporting","name":"Reporting & Dashboards","confidence":0.885,"provenance":"derived"},{"slug":"dev.version-control","name":"Version Control","confidence":0.554,"provenance":"derived"},{"slug":"knowledge.reasoning","name":"Reasoning & Planning","confidence":0.54,"provenance":"derived"},{"slug":"security.identity","name":"Identity & Access","confidence":0.525,"provenance":"derived"},{"slug":"commerce.ecommerce","name":"E-commerce Operations","confidence":0.51,"provenance":"derived"},{"slug":"ai.evaluation","name":"Evaluation & Benchmarks","confidence":0.51,"provenance":"derived"}],"categories":["ai","analytics","commerce","dev","documents","knowledge","security"],"language":"en"},"observed":{"status":"live","statusReason":"Responded 5h ago.","lastOkAt":"2026-10-09T22:27:28.197Z","lastProbedAt":"2026-10-09T22:27:28.197Z","statusComputedAt":"2026-10-09T22:28:58.741Z","reliability30d":{"probes":109,"successRate":1,"p50Ms":94,"basis":"service","measures":{"availability":"availability","latency":"response time","tools":"tool surface observed","summary":"Checks reached the service itself."},"checks":{"total":109,"ok":109,"authBoundaryOk":0,"serviceOk":109,"note":"Counted from the observation rows for the window, checks of the server only (HTTP, A2A card, MCP initialize). ok = authBoundaryOk + serviceOk. `probes` is the sum of daily rollups and includes registry checks, so it can differ from `total`."}},"latestObservations":[{"at":"2026-10-09T22:27:28.197Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":90,"error":null,"detail":{"tools":[{"name":"inspect_promotion","description":"Quarantine declared exposure, compare paired baseline/candidate outcomes on the clean remainder, and issue a promotion receipt. Bring your own exam rows, exposu"},{"name":"audit_leakage","description":"Exact declared-exposure audit over your exam rows: row identity, behavioral fingerprints for graph-DSL expressions, text-similarity review flags, and a clean ex"},{"name":"promotion_gate","description":"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'."},{"name":"bank_health","description":"Item-lifecycle diagnostics over your grading history: discriminators, saturated and flaky items, frontier gaps. Full example: GET /api/examples key 'health'."},{"name":"safe_patch","description":"Apply a section-scoped Markdown patch under conservation checks (untouched sections stay byte-identical; protected tokens preserved). Full example: GET /api/exa"},{"name":"counterexample_hunt","description":"Bounded simulated-annealing search for a graph counterexample inside a DSL predicate class, with an exact certificate when found. CPU-bounded and strictly rate-"},{"name":"memory_relevance","description":"Compare query-free salience against objective-conditioned relevance for a set of memories under a token budget. Full example: GET /api/examples key 'memory'."},{"name":"replay_trace","description":"Turn reasoning-emulator control events into checkpoints, rewinds, notes, and a timeline. Full example: GET /api/examples key 'replay'."},{"name":"report_card_start","description":"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."},{"name":"report_card_submit","description":"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"},{"name":"open_bench_start","description":"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"},{"name":"open_bench_submit","description":"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"},{"name":"open_bench_leaderboard","description":"TIER 2: list the self-attested public Open Promotion Bench receipts. Entries contain manifests, verdicts, item-level transitions, and commitments but never task"},{"name":"about_whetstone","description":"What this service is: the tool catalog, the tier boundaries, and where the source lives."}],"toolCount":14,"toolsHash":"0352dd0877837104e6ff843149c19ed6c6f4cf369eb8b766f7bdbdb25e7ad12e","serverName":"whetstone-tools","capabilities":["tools"],"serverVersion":"0.8.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-09T15:31:51.578Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":91,"error":null,"detail":{"tools":[{"name":"inspect_promotion","description":"Quarantine declared exposure, compare paired baseline/candidate outcomes on the clean remainder, and issue a promotion receipt. Bring your own exam rows, exposu"},{"name":"audit_leakage","description":"Exact declared-exposure audit over your exam rows: row identity, behavioral fingerprints for graph-DSL expressions, text-similarity review flags, and a clean ex"},{"name":"promotion_gate","description":"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'."},{"name":"bank_health","description":"Item-lifecycle diagnostics over your grading history: discriminators, saturated and flaky items, frontier gaps. Full example: GET /api/examples key 'health'."},{"name":"safe_patch","description":"Apply a section-scoped Markdown patch under conservation checks (untouched sections stay byte-identical; protected tokens preserved). Full example: GET /api/exa"},{"name":"counterexample_hunt","description":"Bounded simulated-annealing search for a graph counterexample inside a DSL predicate class, with an exact certificate when found. CPU-bounded and strictly rate-"},{"name":"memory_relevance","description":"Compare query-free salience against objective-conditioned relevance for a set of memories under a token budget. Full example: GET /api/examples key 'memory'."},{"name":"replay_trace","description":"Turn reasoning-emulator control events into checkpoints, rewinds, notes, and a timeline. Full example: GET /api/examples key 'replay'."},{"name":"report_card_start","description":"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."},{"name":"report_card_submit","description":"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"},{"name":"open_bench_start","description":"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"},{"name":"open_bench_submit","description":"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"},{"name":"open_bench_leaderboard","description":"TIER 2: list the self-attested public Open Promotion Bench receipts. Entries contain manifests, verdicts, item-level transitions, and commitments but never task"},{"name":"about_whetstone","description":"What this service is: the tool catalog, the tier boundaries, and where the source lives."}],"toolCount":14,"toolsHash":"0352dd0877837104e6ff843149c19ed6c6f4cf369eb8b766f7bdbdb25e7ad12e","serverName":"whetstone-tools","capabilities":["tools"],"serverVersion":"0.8.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-09T08:28:54.083Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":96,"error":null,"detail":{"tools":[{"name":"inspect_promotion","description":"Quarantine declared exposure, compare paired baseline/candidate outcomes on the clean remainder, and issue a promotion receipt. Bring your own exam rows, exposu"},{"name":"audit_leakage","description":"Exact declared-exposure audit over your exam rows: row identity, behavioral fingerprints for graph-DSL expressions, text-similarity review flags, and a clean ex"},{"name":"promotion_gate","description":"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'."},{"name":"bank_health","description":"Item-lifecycle diagnostics over your grading history: discriminators, saturated and flaky items, frontier gaps. Full example: GET /api/examples key 'health'."},{"name":"safe_patch","description":"Apply a section-scoped Markdown patch under conservation checks (untouched sections stay byte-identical; protected tokens preserved). Full example: GET /api/exa"},{"name":"counterexample_hunt","description":"Bounded simulated-annealing search for a graph counterexample inside a DSL predicate class, with an exact certificate when found. CPU-bounded and strictly rate-"},{"name":"memory_relevance","description":"Compare query-free salience against objective-conditioned relevance for a set of memories under a token budget. Full example: GET /api/examples key 'memory'."},{"name":"replay_trace","description":"Turn reasoning-emulator control events into checkpoints, rewinds, notes, and a timeline. Full example: GET /api/examples key 'replay'."},{"name":"report_card_start","description":"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."},{"name":"report_card_submit","description":"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"},{"name":"open_bench_start","description":"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"},{"name":"open_bench_submit","description":"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"},{"name":"open_bench_leaderboard","description":"TIER 2: list the self-attested public Open Promotion Bench receipts. Entries contain manifests, verdicts, item-level transitions, and commitments but never task"},{"name":"about_whetstone","description":"What this service is: the tool catalog, the tier boundaries, and where the source lives."}],"toolCount":14,"toolsHash":"0352dd0877837104e6ff843149c19ed6c6f4cf369eb8b766f7bdbdb25e7ad12e","serverName":"whetstone-tools","capabilities":["tools"],"serverVersion":"0.8.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-09T02:26:19.875Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":86,"error":null,"detail":{"tools":[{"name":"inspect_promotion","description":"Quarantine declared exposure, compare paired baseline/candidate outcomes on the clean remainder, and issue a promotion receipt. Bring your own exam rows, exposu"},{"name":"audit_leakage","description":"Exact declared-exposure audit over your exam rows: row identity, behavioral fingerprints for graph-DSL expressions, text-similarity review flags, and a clean ex"},{"name":"promotion_gate","description":"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'."},{"name":"bank_health","description":"Item-lifecycle diagnostics over your grading history: discriminators, saturated and flaky items, frontier gaps. Full example: GET /api/examples key 'health'."},{"name":"safe_patch","description":"Apply a section-scoped Markdown patch under conservation checks (untouched sections stay byte-identical; protected tokens preserved). Full example: GET /api/exa"},{"name":"counterexample_hunt","description":"Bounded simulated-annealing search for a graph counterexample inside a DSL predicate class, with an exact certificate when found. CPU-bounded and strictly rate-"},{"name":"memory_relevance","description":"Compare query-free salience against objective-conditioned relevance for a set of memories under a token budget. Full example: GET /api/examples key 'memory'."},{"name":"replay_trace","description":"Turn reasoning-emulator control events into checkpoints, rewinds, notes, and a timeline. Full example: GET /api/examples key 'replay'."},{"name":"report_card_start","description":"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."},{"name":"report_card_submit","description":"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"},{"name":"open_bench_start","description":"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"},{"name":"open_bench_submit","description":"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"},{"name":"open_bench_leaderboard","description":"TIER 2: list the self-attested public Open Promotion Bench receipts. Entries contain manifests, verdicts, item-level transitions, and commitments but never task"},{"name":"about_whetstone","description":"What this service is: the tool catalog, the tier boundaries, and where the source lives."}],"toolCount":14,"toolsHash":"0352dd0877837104e6ff843149c19ed6c6f4cf369eb8b766f7bdbdb25e7ad12e","serverName":"whetstone-tools","capabilities":["tools"],"serverVersion":"0.8.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-08T19:24:20.704Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":90,"error":null,"detail":{"tools":[{"name":"inspect_promotion","description":"Quarantine declared exposure, compare paired baseline/candidate outcomes on the clean remainder, and issue a promotion receipt. Bring your own exam rows, exposu"},{"name":"audit_leakage","description":"Exact declared-exposure audit over your exam rows: row identity, behavioral fingerprints for graph-DSL expressions, text-similarity review flags, and a clean ex"},{"name":"promotion_gate","description":"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'."},{"name":"bank_health","description":"Item-lifecycle diagnostics over your grading history: discriminators, saturated and flaky items, frontier gaps. Full example: GET /api/examples key 'health'."},{"name":"safe_patch","description":"Apply a section-scoped Markdown patch under conservation checks (untouched sections stay byte-identical; protected tokens preserved). Full example: GET /api/exa"},{"name":"counterexample_hunt","description":"Bounded simulated-annealing search for a graph counterexample inside a DSL predicate class, with an exact certificate when found. CPU-bounded and strictly rate-"},{"name":"memory_relevance","description":"Compare query-free salience against objective-conditioned relevance for a set of memories under a token budget. Full example: GET /api/examples key 'memory'."},{"name":"replay_trace","description":"Turn reasoning-emulator control events into checkpoints, rewinds, notes, and a timeline. Full example: GET /api/examples key 'replay'."},{"name":"report_card_start","description":"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."},{"name":"report_card_submit","description":"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"},{"name":"open_bench_start","description":"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"},{"name":"open_bench_submit","description":"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"},{"name":"open_bench_leaderboard","description":"TIER 2: list the self-attested public Open Promotion Bench receipts. Entries contain manifests, verdicts, item-level transitions, and commitments but never task"},{"name":"about_whetstone","description":"What this service is: the tool catalog, the tier boundaries, and where the source lives."}],"toolCount":14,"toolsHash":"0352dd0877837104e6ff843149c19ed6c6f4cf369eb8b766f7bdbdb25e7ad12e","serverName":"whetstone-tools","capabilities":["tools"],"serverVersion":"0.8.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-08T13:23:06.504Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":85,"error":null,"detail":{"tools":[{"name":"inspect_promotion","description":"Quarantine declared exposure, compare paired baseline/candidate outcomes on the clean remainder, and issue a promotion receipt. Bring your own exam rows, exposu"},{"name":"audit_leakage","description":"Exact declared-exposure audit over your exam rows: row identity, behavioral fingerprints for graph-DSL expressions, text-similarity review flags, and a clean ex"},{"name":"promotion_gate","description":"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'."},{"name":"bank_health","description":"Item-lifecycle diagnostics over your grading history: discriminators, saturated and flaky items, frontier gaps. Full example: GET /api/examples key 'health'."},{"name":"safe_patch","description":"Apply a section-scoped Markdown patch under conservation checks (untouched sections stay byte-identical; protected tokens preserved). Full example: GET /api/exa"},{"name":"counterexample_hunt","description":"Bounded simulated-annealing search for a graph counterexample inside a DSL predicate class, with an exact certificate when found. CPU-bounded and strictly rate-"},{"name":"memory_relevance","description":"Compare query-free salience against objective-conditioned relevance for a set of memories under a token budget. Full example: GET /api/examples key 'memory'."},{"name":"replay_trace","description":"Turn reasoning-emulator control events into checkpoints, rewinds, notes, and a timeline. Full example: GET /api/examples key 'replay'."},{"name":"report_card_start","description":"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."},{"name":"report_card_submit","description":"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"},{"name":"open_bench_start","description":"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"},{"name":"open_bench_submit","description":"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"},{"name":"open_bench_leaderboard","description":"TIER 2: list the self-attested public Open Promotion Bench receipts. Entries contain manifests, verdicts, item-level transitions, and commitments but never task"},{"name":"about_whetstone","description":"What this service is: the tool catalog, the tier boundaries, and where the source lives."}],"toolCount":14,"toolsHash":"0352dd0877837104e6ff843149c19ed6c6f4cf369eb8b766f7bdbdb25e7ad12e","serverName":"whetstone-tools","capabilities":["tools"],"serverVersion":"0.8.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-08T07:26:07.064Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":90,"error":null,"detail":{"tools":[{"name":"inspect_promotion","description":"Quarantine declared exposure, compare paired baseline/candidate outcomes on the clean remainder, and issue a promotion receipt. Bring your own exam rows, exposu"},{"name":"audit_leakage","description":"Exact declared-exposure audit over your exam rows: row identity, behavioral fingerprints for graph-DSL expressions, text-similarity review flags, and a clean ex"},{"name":"promotion_gate","description":"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'."},{"name":"bank_health","description":"Item-lifecycle diagnostics over your grading history: discriminators, saturated and flaky items, frontier gaps. Full example: GET /api/examples key 'health'."},{"name":"safe_patch","description":"Apply a section-scoped Markdown patch under conservation checks (untouched sections stay byte-identical; protected tokens preserved). Full example: GET /api/exa"},{"name":"counterexample_hunt","description":"Bounded simulated-annealing search for a graph counterexample inside a DSL predicate class, with an exact certificate when found. CPU-bounded and strictly rate-"},{"name":"memory_relevance","description":"Compare query-free salience against objective-conditioned relevance for a set of memories under a token budget. Full example: GET /api/examples key 'memory'."},{"name":"replay_trace","description":"Turn reasoning-emulator control events into checkpoints, rewinds, notes, and a timeline. Full example: GET /api/examples key 'replay'."},{"name":"report_card_start","description":"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."},{"name":"report_card_submit","description":"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"},{"name":"open_bench_start","description":"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"},{"name":"open_bench_submit","description":"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"},{"name":"open_bench_leaderboard","description":"TIER 2: list the self-attested public Open Promotion Bench receipts. Entries contain manifests, verdicts, item-level transitions, and commitments but never task"},{"name":"about_whetstone","description":"What this service is: the tool catalog, the tier boundaries, and where the source lives."}],"toolCount":14,"toolsHash":"0352dd0877837104e6ff843149c19ed6c6f4cf369eb8b766f7bdbdb25e7ad12e","serverName":"whetstone-tools","capabilities":["tools"],"serverVersion":"0.8.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-08T01:22:25.277Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":90,"error":null,"detail":{"tools":[{"name":"inspect_promotion","description":"Quarantine declared exposure, compare paired baseline/candidate outcomes on the clean remainder, and issue a promotion receipt. Bring your own exam rows, exposu"},{"name":"audit_leakage","description":"Exact declared-exposure audit over your exam rows: row identity, behavioral fingerprints for graph-DSL expressions, text-similarity review flags, and a clean ex"},{"name":"promotion_gate","description":"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'."},{"name":"bank_health","description":"Item-lifecycle diagnostics over your grading history: discriminators, saturated and flaky items, frontier gaps. Full example: GET /api/examples key 'health'."},{"name":"safe_patch","description":"Apply a section-scoped Markdown patch under conservation checks (untouched sections stay byte-identical; protected tokens preserved). Full example: GET /api/exa"},{"name":"counterexample_hunt","description":"Bounded simulated-annealing search for a graph counterexample inside a DSL predicate class, with an exact certificate when found. CPU-bounded and strictly rate-"},{"name":"memory_relevance","description":"Compare query-free salience against objective-conditioned relevance for a set of memories under a token budget. Full example: GET /api/examples key 'memory'."},{"name":"replay_trace","description":"Turn reasoning-emulator control events into checkpoints, rewinds, notes, and a timeline. Full example: GET /api/examples key 'replay'."},{"name":"report_card_start","description":"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."},{"name":"report_card_submit","description":"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"},{"name":"open_bench_start","description":"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"},{"name":"open_bench_submit","description":"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"},{"name":"open_bench_leaderboard","description":"TIER 2: list the self-attested public Open Promotion Bench receipts. Entries contain manifests, verdicts, item-level transitions, and commitments but never task"},{"name":"about_whetstone","description":"What this service is: the tool catalog, the tier boundaries, and where the source lives."}],"toolCount":14,"toolsHash":"0352dd0877837104e6ff843149c19ed6c6f4cf369eb8b766f7bdbdb25e7ad12e","serverName":"whetstone-tools","capabilities":["tools"],"serverVersion":"0.8.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-07T19:24:04.189Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":118,"error":null,"detail":{"tools":[{"name":"inspect_promotion","description":"Quarantine declared exposure, compare paired baseline/candidate outcomes on the clean remainder, and issue a promotion receipt. Bring your own exam rows, exposu"},{"name":"audit_leakage","description":"Exact declared-exposure audit over your exam rows: row identity, behavioral fingerprints for graph-DSL expressions, text-similarity review flags, and a clean ex"},{"name":"promotion_gate","description":"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'."},{"name":"bank_health","description":"Item-lifecycle diagnostics over your grading history: discriminators, saturated and flaky items, frontier gaps. Full example: GET /api/examples key 'health'."},{"name":"safe_patch","description":"Apply a section-scoped Markdown patch under conservation checks (untouched sections stay byte-identical; protected tokens preserved). Full example: GET /api/exa"},{"name":"counterexample_hunt","description":"Bounded simulated-annealing search for a graph counterexample inside a DSL predicate class, with an exact certificate when found. CPU-bounded and strictly rate-"},{"name":"memory_relevance","description":"Compare query-free salience against objective-conditioned relevance for a set of memories under a token budget. Full example: GET /api/examples key 'memory'."},{"name":"replay_trace","description":"Turn reasoning-emulator control events into checkpoints, rewinds, notes, and a timeline. Full example: GET /api/examples key 'replay'."},{"name":"report_card_start","description":"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."},{"name":"report_card_submit","description":"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"},{"name":"open_bench_start","description":"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"},{"name":"open_bench_submit","description":"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"},{"name":"open_bench_leaderboard","description":"TIER 2: list the self-attested public Open Promotion Bench receipts. Entries contain manifests, verdicts, item-level transitions, and commitments but never task"},{"name":"about_whetstone","description":"What this service is: the tool catalog, the tier boundaries, and where the source lives."}],"toolCount":14,"toolsHash":"0352dd0877837104e6ff843149c19ed6c6f4cf369eb8b766f7bdbdb25e7ad12e","serverName":"whetstone-tools","capabilities":["tools"],"serverVersion":"0.8.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-07T12:29:45.259Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":94,"error":null,"detail":{"tools":[{"name":"inspect_promotion","description":"Quarantine declared exposure, compare paired baseline/candidate outcomes on the clean remainder, and issue a promotion receipt. Bring your own exam rows, exposu"},{"name":"audit_leakage","description":"Exact declared-exposure audit over your exam rows: row identity, behavioral fingerprints for graph-DSL expressions, text-similarity review flags, and a clean ex"},{"name":"promotion_gate","description":"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'."},{"name":"bank_health","description":"Item-lifecycle diagnostics over your grading history: discriminators, saturated and flaky items, frontier gaps. Full example: GET /api/examples key 'health'."},{"name":"safe_patch","description":"Apply a section-scoped Markdown patch under conservation checks (untouched sections stay byte-identical; protected tokens preserved). Full example: GET /api/exa"},{"name":"counterexample_hunt","description":"Bounded simulated-annealing search for a graph counterexample inside a DSL predicate class, with an exact certificate when found. CPU-bounded and strictly rate-"},{"name":"memory_relevance","description":"Compare query-free salience against objective-conditioned relevance for a set of memories under a token budget. Full example: GET /api/examples key 'memory'."},{"name":"replay_trace","description":"Turn reasoning-emulator control events into checkpoints, rewinds, notes, and a timeline. Full example: GET /api/examples key 'replay'."},{"name":"report_card_start","description":"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."},{"name":"report_card_submit","description":"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"},{"name":"open_bench_start","description":"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"},{"name":"open_bench_submit","description":"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"},{"name":"open_bench_leaderboard","description":"TIER 2: list the self-attested public Open Promotion Bench receipts. Entries contain manifests, verdicts, item-level transitions, and commitments but never task"},{"name":"about_whetstone","description":"What this service is: the tool catalog, the tier boundaries, and where the source lives."}],"toolCount":14,"toolsHash":"0352dd0877837104e6ff843149c19ed6c6f4cf369eb8b766f7bdbdb25e7ad12e","serverName":"whetstone-tools","capabilities":["tools"],"serverVersion":"0.8.0","protocolVersion":"2025-06-18"}}],"tools":[{"name":"inspect_promotion","description":"Quarantine declared exposure, compare paired baseline/candidate outcomes on the clean remainder, and issue a promotion receipt. Bring your own exam rows, exposu"},{"name":"audit_leakage","description":"Exact declared-exposure audit over your exam rows: row identity, behavioral fingerprints for graph-DSL expressions, text-similarity review flags, and a clean ex"},{"name":"promotion_gate","description":"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'."},{"name":"bank_health","description":"Item-lifecycle diagnostics over your grading history: discriminators, saturated and flaky items, frontier gaps. Full example: GET /api/examples key 'health'."},{"name":"safe_patch","description":"Apply a section-scoped Markdown patch under conservation checks (untouched sections stay byte-identical; protected tokens preserved). Full example: GET /api/exa"},{"name":"counterexample_hunt","description":"Bounded simulated-annealing search for a graph counterexample inside a DSL predicate class, with an exact certificate when found. CPU-bounded and strictly rate-"},{"name":"memory_relevance","description":"Compare query-free salience against objective-conditioned relevance for a set of memories under a token budget. Full example: GET /api/examples key 'memory'."},{"name":"replay_trace","description":"Turn reasoning-emulator control events into checkpoints, rewinds, notes, and a timeline. Full example: GET /api/examples key 'replay'."},{"name":"report_card_start","description":"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."},{"name":"report_card_submit","description":"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"},{"name":"open_bench_start","description":"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"},{"name":"open_bench_submit","description":"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"},{"name":"open_bench_leaderboard","description":"TIER 2: list the self-attested public Open Promotion Bench receipts. Entries contain manifests, verdicts, item-level transitions, and commitments but never task"},{"name":"about_whetstone","description":"What this service is: the tool catalog, the tier boundaries, and where the source lives."}],"package":null,"toolSurface":{"id":"ts_3x3ggqq6na8a","endpointId":"ep_6cgwq7xwkwq7","hash":"0352dd0877837104e6ff843149c19ed6c6f4cf369eb8b766f7bdbdb25e7ad12e","toolCount":14,"serverName":"whetstone-tools","serverVersion":"0.8.0","protocolVersion":"2025-06-18","firstSeenAt":"2026-09-12T10:26:27.786Z","lastSeenAt":"2026-10-09T22:27:28.213Z","observations":102,"toolNames":["inspect_promotion","audit_leakage","promotion_gate","bank_health","safe_patch","counterexample_hunt","memory_relevance","replay_trace","report_card_start","report_card_submit","open_bench_start","open_bench_submit","open_bench_leaderboard","about_whetstone"],"distinctSurfaces":1},"endpointFacts":[{"id":"ep_6cgwq7xwkwq7","url":"https://whetstone.cyberelf.link/mcp","type":"mcp_streamable_http","factsCheckedAt":"2026-10-07T12:29:45.271Z","auth":{"observedAt":"2026-10-07T12:29:45.359Z","authRequired":false,"scheme":null,"resourceMetadata":null,"authorizationServer":null,"conformance":{"dpop":false,"rfc8414":false,"rfc9728":false,"pkceS256":false,"clientIdMetadataDocument":false,"dynamicClientRegistration":false}},"tls":{"observedAt":"2026-10-07T12:29:45.950Z","protocol":"TLSv1.3","chainValid":true,"chainError":null,"hostMatches":true,"subject":"whetstone.cyberelf.link","issuer":{"commonName":"YE1","organization":"Let's Encrypt"},"validFrom":"2026-09-10T08:10:45.000Z","validTo":"2026-12-09T08:10:44.000Z","daysToExpiry":60,"sanCount":1,"fingerprint256":"AA:62:E0:9D:60:C2:85:2E:C0:BE:AA:57:5F:8E:80:ED:A4:7C:97:8F:33:BA:82:BF:BD:15:71:CD:7C:EF:3F:E4"}}]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"mcp_registry","key":"link.cyberelf.whetstone/tools","url":"https://registry.modelcontextprotocol.io/v0/servers/link.cyberelf.whetstone%2Ftools","firstSeenAt":"2026-09-07T07:22:47.255Z","fetchedAt":"2026-10-08T18:22:06.066Z","normalizedAt":"2026-10-08T18:22:06.066Z"}]},"firstSeenAt":"2026-09-07T07:22:47.255Z","updatedAt":"2026-10-09T22:29:51.397Z"}