Evidence row 309092

What was observed

{
  "count": 3,
  "tools": [
    {
      "description": "Check the remaining credit balance for this API key — free to call, no credits charged and no usage logged.\n\nReturns the same fields as the REST GET /v1/account/balance endpoint: `balance`\n(total remaining credits, 2 decimal places), `permanent` (recharge/bonus credits that\nnever expire), `expiring` (subscription credits, valid 30 days), `upcoming` (renewal\ncredits already granted but not active until the next cycle), `next_expiry`\n(soonest expiry among time-limited credits), `free_tier_credits` (free monthly\nallowance size) and `unlimited` (admin/owner exemption flag).\n\nPoll this before batch jobs to avoid hitting 402 insufficient-credits mid-run.\nWorks even when the account email is not verified yet.\n\napi_key: an API key starting with `sp-`. It may also be provided through the SEARCHPIPE_API_KEY\nenvironment variable (the parameter takes precedence).\nReturns a tool error on authentication failure (missing, invalid, or revoked key).",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "api_key": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null
          }
        },
        "type": "object"
      },
      "name": "searchpipe_account_balance"
    },
    {
      "description": "Run an AI-powered web search for a query: multi-engine retrieval → page fetching → LLM reranking → optional AI answer.\n\nUses the same commercial pipeline and accepts the same parameters as the HTTP POST /search endpoint:\nauthentication → rate limiting → input moderation → credit charge → search → output moderation +\nAI-generated marker → refund on failure → usage logging. Credits are charged per call.\n\nsearch_depth: \"basic\" (default, 1 credit) / \"advanced\" (2 credits) / \"fast\" (0.5 credit — skips all\nLLM steps: results keep engine order with engine-provided relevance scores, no answer is generated).\ninclude_domains / exclude_domains: restrict or exclude domains (\"example.com\" matches the domain and\nany subdomain; \"*.example.com\" matches subdomains only; \"example.com/docs\" also requires the URL path\nto start with /docs; exclude wins over include).\ntime_range: recency window \"day\" / \"week\" / \"month\" / \"year\"; start_date / end_date: ISO YYYY-MM-DD\nbounds (results without a known publish date are not filtered).\ntopic: \"general\" (default) or \"news\" (always adds a dedicated news channel to retrieval).\ncountry: ISO 3166-1 alpha-2 region bias (e.g. \"US\"); language: upstream market language (e.g. \"en\",\n\"zh-CN\"); combined into the upstream market locale.\nsafe_search: 0 off (default) / 1 moderate / 2 strict.\ninclude_images: also run an image search and return an images array alongside results.\noutput_type: \"search_results\" (default) / \"answer\" (same as include_answer=true) / \"structured\"\n(grounded JSON object per output_schema — requires output_schema; on failure output is null).\nobjective: optional one-line search intent from the calling agent; improves reranking only.\nstream is REST-only and not available over MCP.\napi_key: an API key starting with `sp-`. It may also be provided through the SEARCHPIPE_API_KEY\nenvironment variable (the parameter takes precedence).\nReturns Tavily-style structured results (query / answer / results[] / images[] / output).\nReturns a tool error on authentication failure, insufficient credits, content violation, invalid\nparameters (422), or retrieval failure.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "api_key": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null
          },
          "country": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null
          },
          "end_date": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null
          },
          "exclude_domains": {
            "anyOf": [
              {
                "items": {
                  "type": "string"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "default": null
          },
          "include_answer": {
            "default": false,
            "type": "boolean"
          },
          "include_domains": {
            "anyOf": [
              {
                "items": {
                  "type": "string"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "default": null
          },
          "include_images": {
            "default": false,
            "type": "boolean"
          },
          "include_raw_content": {
            "default": false,
            "type": "boolean"
          },
          "language": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null
          },
          "max_results": {
            "default": 5,
            "type": "integer"
          },
          "objective": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null
          },
          "output_schema": {
            "anyOf": [
              {
                "additionalProperties": true,
                "type": "object"
              },
              {
                "type": "null"
              }
            ],
            "default": null
          },
          "output_type": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null
          },
          "query": {
            "type": "string"
          },
          "safe_search": {
            "default": 0,
            "type": "integer"
          },
          "search_depth": {
            "default": "basic",
            "type": "string"
          },
          "start_date": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null
          },
          "time_range": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null
          },
          "topic": {
            "default": "general",
            "type": "string"
          }
        },
        "required": [
          "query"
        ],
        "type": "object"
      },
      "name": "searchpipe_search"
    },
    {
      "description": "Verify a factual claim against retrieved evidence: claim in, verdict out — a four-label judgment (supported / partial / unsupported / inconclusive), not generated text.\n\nEvery result ships with verifiable evidence — span-level quotes, claim verdicts, and source authority — not just links.\nVerdict labels: `supported` = evidence text clearly supports the claim; `partial` = partly supported or weak evidence;\n`unsupported` = reachable evidence does not support the claim (misattributed citation detected); `inconclusive` = the claim\ncould not be judged (fetch failure, paywall, or insufficient evidence) — the tool reports that honestly instead of guessing.\nVerification fetches source pages and judges claim-evidence consistency, so it typically takes 5-15 seconds.\n\nUses the same commercial pipeline as the HTTP POST /verify endpoint: authentication → email verification → rate limiting →\ninput moderation → per-request credit charge → verification → refund on failure → usage logging. Credits are charged per\ncall; an inconclusive verdict is still a delivered result and is not refunded.\n\nmode: evidence route — \"paper\" / \"web\" / \"auto\" (default; a DOI or arXiv signal decides). evidence_urls: up to 5\ncaller-supplied citations to verify. max_evidence: maximum evidence items to return (1-10, default 5).\napi_key: an API key starting with `sp-`. It may also be provided through the SEARCHPIPE_API_KEY environment variable\n(the parameter takes precedence).\nReturns VerifyResponse (verdict / confidence / reason_code / evidences[] / timing).\nReturns a tool error on authentication failure, insufficient credits, content violation, verification failure, or when the\nverify endpoint is disabled (\"Verify endpoint is not available\").",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "api_key": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null
          },
          "claim": {
            "type": "string"
          },
          "evidence_urls": {
            "anyOf": [
              {
                "items": {
                  "type": "string"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "default": null
          },
          "max_evidence": {
            "default": 5,
            "type": "integer"
          },
          "mode": {
            "default": "auto",
            "type": "string"
          }
        },
        "required": [
          "claim"
        ],
        "type": "object"
      },
      "name": "searchpipe_verify"
    }
  ]
}

What the leaf hashes

{"body":"4c839b32609b345c8fca09ba23548162bbe58a203b62fef6c918f3dbdd5bba5b","id":309092,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793058682860246,"prev":null,"subject":"3cfcb0ee-3cce-4303-ac93-592f3c92705e","subject_kind":"endpoint"}

Proof

Fold these into the leaf in order, hashing each sorted pair with keccak256, to reach the root of 2026-10-26 (296695 rows).

1. 0x0623d0e34e2983fac4661d943098def58cb798c3373c7278ad1c9c839e7a9d2e
2. 0x23604267180d88f0312b7a9104827be8624e78494d2584da39d5b7af7506042c
3. 0x2517bdd5831082c8673fee7d6b9787594306994bf4440fa9803bb9cc268c01e1
4. 0x3a8562185d45463a1fc0cfc16f48d31ab71938c2d0e22ef8a21fe4e00eb6ab59
5. 0x5891c9eaf4cc148d95544b6c888a7d6c46d28debb677b3f02fdd3e98e2e57f7e
6. 0xb0e5d9556a82628fa2bd1829ce42adf4ff34dc516336eef5348aec13b482c82f
7. 0x2dd75377516929d013a1ffb5b4c5351a0da62097f017d09884e62e6c7db6a728
8. 0x96b1971d63b4305ea992777a02375bd6db9ac97496858d8539a8ed17402db3ca
9. 0x5522f7cc4ff591884ab27be7cfb6f04bcb41ae337f2a77394c139a11a70af024
10. 0xcbf24e2308735268c6c221452ee6dcce65722c748c6fc988da0c295e5f881662
11. 0x88fb9d02ea6ed7254b70cfe02388b31c183a7a709aad6303948d66f85ad516b1
12. 0x7910a200eb458bec3c3badb3b2ead3e75cec5f3ba263800cea6b9f32efb53f25
13. 0x610fdf3e989af0a6b4a400a3a8aab9156d757f8c96efe4e9d0594dfd04de1cc0
14. 0xd1d3499072edb10edc68f84bcae2365d2ab534df689250cab18c751b6f13b6ff
15. 0x7ddc2fead128357f881b63e6c7c26d7fbbb84fca6c7c8e0bbfe386de86ca8d39
16. 0xc6a4d7899a0f442958e26505011190b7cff2483611c1b94eba9043e0ba9ac36e
17. 0x8c756542e482157df0c36464d75c937b845e4423dbbcfad08f0cf8d5a16b9a13
18. 0x20704208aa6923d6b2450ef74ede87a6e0265d46447926038fe9506e9e154b2d
19. 0x9b9ce5b74b9bab5121612ef6b64920a8d453cbf311096a423eef9702747e868a

Day root

0xf43e8dcc3d451a4788b26be904c55e8c4c0fa75c9666796c51db38d37e2c0df8

Chained

0x702d5ac508f08b0d1accf36af25822d8e5660367494edd17a642fb61e158a57a

Published

On Arc Testnet, block 69251483: 0x495162f8936e19f0039918feebe6c307f327cd6bf8c37219620b1970041fa9ae