Server definition

Hash: sha256:402242c1c6701ac15a824145d427817607bac39e5c2299ed128625711bbd3028
What it is: What a remote MCP server returned when asked what it offers: 14 tools

The blob, as servednamed by its sha256

{
  "instructions": "Whetstone's public verifier toolbox as MCP tools. Three tiers. Tier 0 is stateless: you supply the data (exam rows, paired results, documents, event logs) and get back audits, promotion verdicts, patches, or counterexamples; payloads and results are not persisted, while operational counters and standard access logs are retained. Tier 1 is the disposable report card: report_card_start hands your agent a small graph-repair exam minted from the repository's public frontier, report_card_submit grades it by checker spec and requires a verified repair to retain at least 5% of clean support for promotion grade (no answer key exists), then destroys the session. Tier 2 is Open Promotion Bench: open_bench_start gives a paired baseline/candidate scope-integrity cohort, open_bench_submit grades both answer maps, and open_bench_leaderboard returns opt-in public receipts. Published entries retain only the self-attested manifests and sanitized receipts, never tasks or answers. No private exam bank is loaded in this service, so no tool can leak one. Complete request/response examples for every Tier 0 tool: GET /api/examples. Full agent documentation: https://whetstone.cyberelf.link/for-agents — installable skill file: https://whetstone.cyberelf.link/skill.md",
  "tools": [
    {
      "description": "What this service is: the tool catalog, the tier boundaries, and where the source lives.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {},
        "type": "object"
      },
      "name": "about_whetstone",
      "outputSchema": null
    },
    {
      "description": "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'.",
      "inputSchema": {
        "additionalProperties": false,
        "description": "Audit declared exposure against an exam and export the clean remainder.",
        "properties": {
          "enable_behavioral_fingerprint": {
            "default": true,
            "type": "boolean"
          },
          "enable_text_similarity": {
            "default": true,
            "type": "boolean"
          },
          "exam": {
            "description": "Exam rows. Each row needs item_id (or id) plus prompt/content/input/task/question/expression.",
            "items": {
              "additionalProperties": true,
              "properties": {},
              "type": "object"
            },
            "maxItems": 5000,
            "minItems": 1,
            "type": "array"
          },
          "exposure": {
            "description": "Declared exposure rows carrying identity/content fields and an optional source or path.",
            "items": {
              "additionalProperties": true,
              "properties": {},
              "type": "object"
            },
            "maxItems": 5000,
            "minItems": 0,
            "type": "array"
          },
          "fingerprint_max_n": {
            "default": 4,
            "maximum": 5,
            "minimum": 3,
            "type": "integer"
          },
          "similarity_threshold": {
            "default": 0.6,
            "maximum": 1,
            "minimum": 0.5,
            "type": "number"
          }
        },
        "required": [
          "exam"
        ],
        "type": "object"
      },
      "name": "audit_leakage",
      "outputSchema": null
    },
    {
      "description": "Item-lifecycle diagnostics over your grading history: discriminators, saturated and flaky items, frontier gaps. Full example: GET /api/examples key 'health'.",
      "inputSchema": {
        "additionalProperties": false,
        "description": "Diagnose item lifecycle health from one or more grading-history rows.",
        "properties": {
          "history": {
            "description": "Observed item/system outcomes.",
            "items": {
              "additionalProperties": true,
              "properties": {
                "domain": {
                  "type": "string"
                },
                "item_id": {
                  "minLength": 1,
                  "type": "string"
                },
                "passed": {
                  "type": "boolean"
                },
                "system": {
                  "minLength": 1,
                  "type": "string"
                }
              },
              "required": [
                "item_id",
                "system",
                "passed"
              ],
              "type": "object"
            },
            "maxItems": 5000,
            "minItems": 1,
            "type": "array"
          },
          "items": {
            "description": "Optional item definitions.",
            "items": {
              "additionalProperties": true,
              "properties": {
                "domain": {
                  "type": "string"
                },
                "item_id": {
                  "minLength": 1,
                  "type": "string"
                }
              },
              "required": [
                "item_id"
              ],
              "type": "object"
            },
            "maxItems": 5000,
            "minItems": 0,
            "type": "array"
          }
        },
        "required": [
          "history"
        ],
        "type": "object"
      },
      "name": "bank_health",
      "outputSchema": null
    },
    {
      "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-limited. Full example: GET /api/examples key 'counterexample'.",
      "inputSchema": {
        "additionalProperties": false,
        "description": "Run a bounded graph search against one Whetstone predicate expression.",
        "properties": {
          "expression": {
            "description": "Graph predicate in the Whetstone DSL, for example: is_connected and is_triangle_free and not is_bipartite",
            "maxLength": 500,
            "minLength": 1,
            "type": "string"
          },
          "ns": {
            "default": [
              8,
              9,
              10,
              11
            ],
            "description": "Graph sizes searched.",
            "items": {
              "maximum": 12,
              "minimum": 4,
              "type": "integer"
            },
            "maxItems": 5,
            "minItems": 1,
            "type": "array"
          },
          "restarts": {
            "default": 4,
            "maximum": 6,
            "minimum": 1,
            "type": "integer"
          },
          "seed": {
            "default": 0,
            "type": "integer"
          },
          "steps": {
            "default": 800,
            "maximum": 1500,
            "minimum": 50,
            "type": "integer"
          }
        },
        "required": [
          "expression"
        ],
        "type": "object"
      },
      "name": "counterexample_hunt",
      "outputSchema": null
    },
    {
      "description": "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'.",
      "inputSchema": {
        "additionalProperties": false,
        "description": "Audit exposure, prove a complete clean cohort, then gate baseline versus candidate.",
        "properties": {
          "baseline": {
            "additionalProperties": {
              "type": "boolean"
            },
            "description": "item_id -> boolean pass/fail result for the baseline system.",
            "maxProperties": 5000,
            "minProperties": 1,
            "type": "object"
          },
          "baseline_name": {
            "default": "baseline",
            "type": "string"
          },
          "candidate": {
            "additionalProperties": {
              "type": "boolean"
            },
            "description": "item_id -> boolean pass/fail result for the candidate system.",
            "maxProperties": 5000,
            "minProperties": 1,
            "type": "object"
          },
          "candidate_name": {
            "default": "candidate",
            "type": "string"
          },
          "domains": {
            "additionalProperties": {
              "type": "string"
            },
            "description": "Optional item_id -> domain label mapping.",
            "type": "object"
          },
          "enable_behavioral_fingerprint": {
            "default": true,
            "type": "boolean"
          },
          "enable_text_similarity": {
            "default": true,
            "type": "boolean"
          },
          "exam": {
            "description": "Exam rows. Each row needs item_id (or id) plus prompt/content/input/task/question/expression.",
            "items": {
              "additionalProperties": true,
              "properties": {},
              "type": "object"
            },
            "maxItems": 5000,
            "minItems": 1,
            "type": "array"
          },
          "exposure": {
            "description": "Declared exposure rows carrying identity/content fields and an optional source or path.",
            "items": {
              "additionalProperties": true,
              "properties": {},
              "type": "object"
            },
            "maxItems": 5000,
            "minItems": 0,
            "type": "array"
          },
          "fingerprint_max_n": {
            "default": 4,
            "maximum": 5,
            "minimum": 3,
            "type": "integer"
          },
          "policy": {
            "additionalProperties": false,
            "description": "Explicit promotion policy. Omitted fields use the documented defaults.",
            "properties": {
              "confidence_alpha": {
                "default": 0.05,
                "exclusiveMinimum": 0,
                "maximum": 1,
                "type": "number"
              },
              "max_regressions": {
                "default": 0,
                "minimum": 0,
                "type": "integer"
              },
              "min_gains": {
                "default": 1,
                "minimum": 0,
                "type": "integer"
              },
              "require_retained_probe": {
                "default": false,
                "type": "boolean"
              }
            },
            "type": "object"
          },
          "retained_probe": {
            "additionalProperties": false,
            "description": "Optional retained-capability result checked alongside the paired cohort.",
            "properties": {
              "base_verified": {
                "minimum": 0,
                "type": "integer"
              },
              "candidate_verified": {
                "minimum": 0,
                "type": "integer"
              },
              "items": {
                "minimum": 0,
                "type": "integer"
              }
            },
            "required": [
              "base_verified",
              "candidate_verified",
              "items"
            ],
            "type": "object"
          },
          "similarity_threshold": {
            "default": 0.6,
            "maximum": 1,
            "minimum": 0.5,
            "type": "number"
          }
        },
        "required": [
          "exam",
          "baseline",
          "candidate"
        ],
        "type": "object"
      },
      "name": "inspect_promotion",
      "outputSchema": null
    },
    {
      "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'.",
      "inputSchema": {
        "additionalProperties": false,
        "description": "Rank caller-supplied memories against a concrete objective under a token budget.",
        "properties": {
          "context_entities": {
            "description": "Entities already active in context.",
            "items": {
              "type": "string"
            },
            "maxItems": 100,
            "type": "array"
          },
          "current_step": {
            "minimum": 0,
            "type": "integer"
          },
          "memories": {
            "description": "Memories to rank.",
            "items": {
              "additionalProperties": false,
              "properties": {
                "age": {
                  "default": 0,
                  "minimum": 0,
                  "type": "integer"
                },
                "confidence": {
                  "default": 0.8,
                  "maximum": 1,
                  "minimum": 0,
                  "type": "number"
                },
                "content": {
                  "minLength": 1,
                  "type": "string"
                },
                "entities": {
                  "description": "Entities explicitly present in this memory.",
                  "items": {
                    "type": "string"
                  },
                  "maxItems": 100,
                  "type": "array"
                },
                "kind": {
                  "default": "episodic",
                  "type": "string"
                },
                "source": {
                  "default": "uploaded",
                  "type": "string"
                },
                "use_count": {
                  "default": 0,
                  "minimum": 0,
                  "type": "integer"
                }
              },
              "required": [
                "content"
              ],
              "type": "object"
            },
            "maxItems": 1000,
            "minItems": 1,
            "type": "array"
          },
          "objective": {
            "minLength": 1,
            "type": "string"
          },
          "objective_entities": {
            "description": "Optional explicit entities when the objective text is not self-describing.",
            "items": {
              "type": "string"
            },
            "maxItems": 100,
            "type": "array"
          },
          "question_kind": {
            "default": "generic",
            "type": "string"
          },
          "token_budget": {
            "default": 90,
            "maximum": 10000,
            "minimum": 1,
            "type": "integer"
          }
        },
        "required": [
          "objective",
          "memories"
        ],
        "type": "object"
      },
      "name": "memory_relevance",
      "outputSchema": null
    },
    {
      "description": "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.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {},
        "type": "object"
      },
      "name": "open_bench_leaderboard",
      "outputSchema": null
    },
    {
      "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 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.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "challenge": {
            "description": "Caller nonce bound into the signed receipt for replay detection.",
            "maxLength": 128,
            "minLength": 8,
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "open_bench_start",
      "outputSchema": null
    },
    {
      "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 only the safe manifests and sanitized receipt to the public board; tasks and answers are never persisted.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "attestation": {
            "type": "boolean"
          },
          "baseline_answers": {
            "type": "object"
          },
          "baseline_manifest": {
            "additionalProperties": false,
            "properties": {
              "harness": {
                "type": "string"
              },
              "model": {
                "type": "string"
              },
              "name": {
                "type": "string"
              },
              "version": {
                "type": "string"
              }
            },
            "required": [
              "name"
            ],
            "type": "object"
          },
          "candidate_answers": {
            "type": "object"
          },
          "candidate_manifest": {
            "additionalProperties": false,
            "properties": {
              "harness": {
                "type": "string"
              },
              "model": {
                "type": "string"
              },
              "name": {
                "type": "string"
              },
              "version": {
                "type": "string"
              }
            },
            "required": [
              "name"
            ],
            "type": "object"
          },
          "publish": {
            "type": "boolean"
          },
          "session_id": {
            "type": "string"
          }
        },
        "required": [
          "session_id",
          "baseline_manifest",
          "candidate_manifest",
          "baseline_answers",
          "candidate_answers"
        ],
        "type": "object"
      },
      "name": "open_bench_submit",
      "outputSchema": null
    },
    {
      "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'.",
      "inputSchema": {
        "additionalProperties": false,
        "description": "Compare identical baseline and candidate item cohorts under an explicit policy.",
        "properties": {
          "baseline": {
            "additionalProperties": {
              "type": "boolean"
            },
            "description": "item_id -> boolean pass/fail result for the baseline system.",
            "maxProperties": 5000,
            "minProperties": 1,
            "type": "object"
          },
          "baseline_name": {
            "default": "baseline",
            "type": "string"
          },
          "candidate": {
            "additionalProperties": {
              "type": "boolean"
            },
            "description": "item_id -> boolean pass/fail result for the candidate system.",
            "maxProperties": 5000,
            "minProperties": 1,
            "type": "object"
          },
          "candidate_name": {
            "default": "candidate",
            "type": "string"
          },
          "domains": {
            "additionalProperties": {
              "type": "string"
            },
            "description": "Optional item_id -> domain label mapping.",
            "type": "object"
          },
          "policy": {
            "additionalProperties": false,
            "description": "Explicit promotion policy. Omitted fields use the documented defaults.",
            "properties": {
              "confidence_alpha": {
                "default": 0.05,
                "exclusiveMinimum": 0,
                "maximum": 1,
                "type": "number"
              },
              "max_regressions": {
                "default": 0,
                "minimum": 0,
                "type": "integer"
              },
              "min_gains": {
                "default": 1,
                "minimum": 0,
                "type": "integer"
              },
              "require_retained_probe": {
                "default": false,
                "type": "boolean"
              }
            },
            "type": "object"
          },
          "retained_probe": {
            "additionalProperties": false,
            "description": "Optional retained-capability result checked alongside the paired cohort.",
            "properties": {
              "base_verified": {
                "minimum": 0,
                "type": "integer"
              },
              "candidate_verified": {
                "minimum": 0,
                "type": "integer"
              },
              "items": {
                "minimum": 0,
                "type": "integer"
              }
            },
            "required": [
              "base_verified",
              "candidate_verified",
              "items"
            ],
            "type": "object"
          }
        },
        "required": [
          "baseline",
          "candidate"
        ],
        "type": "object"
      },
      "name": "promotion_gate",
      "outputSchema": null
    },
    {
      "description": "Turn reasoning-emulator control events into checkpoints, rewinds, notes, and a timeline. Full example: GET /api/examples key 'replay'.",
      "inputSchema": {
        "additionalProperties": false,
        "description": "Reconstruct checkpoints, rewinds, branches, and verifier outcomes from control events.",
        "properties": {
          "events": {
            "description": "Ordered reasoning-emulator events.",
            "items": {
              "additionalProperties": false,
              "properties": {
                "detail": {
                  "type": "string"
                },
                "kind": {
                  "description": "Event class such as control, verifier, model, or observation.",
                  "type": "string"
                },
                "source": {
                  "default": "native",
                  "type": "string"
                },
                "step": {
                  "minimum": 0,
                  "type": "integer"
                }
              },
              "required": [
                "kind",
                "detail"
              ],
              "type": "object"
            },
            "maxItems": 5000,
            "minItems": 1,
            "type": "array"
          },
          "notes": {
            "description": "Optional analyst notes.",
            "items": {
              "type": "string"
            },
            "maxItems": 5000,
            "type": "array"
          }
        },
        "required": [
          "events"
        ],
        "type": "object"
      },
      "name": "replay_trace",
      "outputSchema": null
    },
    {
      "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. 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.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "challenge": {
            "description": "Caller nonce bound into the signed receipt for replay detection.",
            "maxLength": 128,
            "minLength": 8,
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "report_card_start",
      "outputSchema": null
    },
    {
      "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 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.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "answers": {
            "additionalProperties": {
              "type": "string"
            },
            "description": "item_id -> answer (a DSL predicate, or the JSON reply the prompt asked for)",
            "type": "object"
          },
          "session_id": {
            "type": "string"
          }
        },
        "required": [
          "session_id",
          "answers"
        ],
        "type": "object"
      },
      "name": "report_card_submit",
      "outputSchema": null
    },
    {
      "description": "Apply a section-scoped Markdown patch under conservation checks (untouched sections stay byte-identical; protected tokens preserved). Full example: GET /api/examples key 'safepatch'.",
      "inputSchema": {
        "additionalProperties": false,
        "description": "Apply deterministic, section-scoped Markdown replacements under conservation checks.",
        "properties": {
          "document": {
            "description": "Complete Markdown document to patch.",
            "maxLength": 200000,
            "minLength": 1,
            "type": "string"
          },
          "operations": {
            "items": {
              "additionalProperties": false,
              "properties": {
                "allow_token_changes": {
                  "description": "Protected literal tokens that this operation may intentionally change.",
                  "items": {
                    "type": "string"
                  },
                  "maxItems": 100,
                  "type": "array"
                },
                "find": {
                  "minLength": 1,
                  "type": "string"
                },
                "replace": {
                  "type": "string"
                },
                "target_heading": {
                  "description": "Markdown heading text without the leading # characters.",
                  "minLength": 1,
                  "type": "string"
                }
              },
              "required": [
                "target_heading",
                "find",
                "replace"
              ],
              "type": "object"
            },
            "maxItems": 50,
            "minItems": 1,
            "type": "array"
          },
          "reason": {
            "type": "string"
          }
        },
        "required": [
          "document",
          "operations"
        ],
        "type": "object"
      },
      "name": "safe_patch",
      "outputSchema": null
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:402242c1c6701ac15a824145d427817607bac39e5c2299ed128625711bbd3028 | sha256sum