addrbookFor publishers
← The evidence ledger

Evidence row 3669425

Observed , by probe.mcp/1.

Kind
mcp.tools
About
endpoint 93b34229-546b-4728-b33c-91c67381e1ee
Recorded
Previous row
#2725463
Body SHA-256
a5165d7aa931235afd53363f0d1fe7e258aedcd8f96a3dc495e73f4b218fca31
Leaf
0x5f8b2dac8e19306547567b7d0cb818e6437fee193143f9510de870f0f1386c62

What was observed

{
  "count": 12,
  "tools": [
    {
      "description": "按你指定的卡型集合与天数,一次性导出多张卡的每日价格序列(json 或 csv),含最低价、市场中位价、最低价所属平台、库存状态、当日报价家数。示例: bulk_export_series(gpus='H100 80GB,RTX 4090', days=7, fmt='csv')。原始数据也可免费从 https://rentgpu.link/data/history.csv 自行下载(CC BY 4.0);此处计费的是按你指定维度筛好、排好、格式化好的结果。按次计费 $0.02 USDC。",
      "inputSchema": {
        "properties": {
          "days": {
            "default": 30,
            "title": "Days",
            "type": "integer"
          },
          "fmt": {
            "default": "json",
            "title": "Fmt",
            "type": "string"
          },
          "gpus": {
            "title": "Gpus",
            "type": "string"
          }
        },
        "required": [
          "gpus"
        ],
        "title": "bulk_export_seriesArguments",
        "type": "object"
      },
      "name": "bulk_export_series"
    },
    {
      "description": "从逐日原始快照里按条件筛报价:指定若干日期 + 卡型/平台,返回命中的原始报价(含计费说明口径、来源、抓取时间),按价格升序。示例: bulk_snapshot_query(dates='latest', gpu='昇腾910B2 64GB')。快照原文免费:https://rentgpu.link/data/snapshots/<日期>.json ;此处计费的是跨多天筛选与聚合。按次计费 $0.02 USDC。",
      "inputSchema": {
        "properties": {
          "dates": {
            "default": "latest",
            "title": "Dates",
            "type": "string"
          },
          "gpu": {
            "default": "",
            "title": "Gpu",
            "type": "string"
          },
          "limit": {
            "default": 200,
            "title": "Limit",
            "type": "integer"
          },
          "platform": {
            "default": "",
            "title": "Platform",
            "type": "string"
          }
        },
        "title": "bulk_snapshot_queryArguments",
        "type": "object"
      },
      "name": "bulk_snapshot_query"
    },
    {
      "description": "查询 GHPI(GPU Hourly Price Index,GPU 按小时价格指数)的最新值与近 N 日走势(免费)。三条子指数:GHPI-H100(H100 80GB 跨平台中位价)、GHPI-CN(中国市场)、CDI(国产卡)。链式匹配法编制(matched-model:新平台上架不记为降价),基期=100,逐日 20:00(香港)冻结、哈希链防篡改。示例: ghpi_index(days=30)。原始序列免费: https://rentgpu.link/data/ghpi.json(CC BY 4.0);引用请带 DOI 10.5281/zenodo.23868319。",
      "inputSchema": {
        "properties": {
          "days": {
            "default": 30,
            "title": "Days",
            "type": "integer"
          }
        },
        "title": "ghpi_indexArguments",
        "type": "object"
      },
      "name": "ghpi_index"
    },
    {
      "description": "查某张 GPU 过去最多 90 天每日价格序列:每日全平台最低价、当日市场中位价、最低价来自哪个平台、库存状态、当日报价家数。示例: gpu_history(gpu='H100 80GB', limit=7) → 2026-10-20 最低 8.28 元(paperspace)、中位 23.04、有货、9 家报价。按次计费 $0.02 USDC。",
      "inputSchema": {
        "properties": {
          "gpu": {
            "title": "Gpu",
            "type": "string"
          },
          "limit": {
            "default": 30,
            "title": "Limit",
            "type": "integer"
          }
        },
        "required": [
          "gpu"
        ],
        "title": "gpu_historyArguments",
        "type": "object"
      },
      "name": "gpu_history"
    },
    {
      "description": "查某张 GPU 现在的全平台最低价(元/小时),含报价平台、区间最低/最高/均价(最多 90 天)、当前价与区间最低价的差距。示例: gpu_price(gpu='RTX 4090') → 当前最低 1.24 元/小时(算家云)、市场中位 1.99、区间最低 1.24、今日 8 家报价。按次计费 $0.002 USDC。",
      "inputSchema": {
        "properties": {
          "gpu": {
            "title": "Gpu",
            "type": "string"
          }
        },
        "required": [
          "gpu"
        ],
        "title": "gpu_priceArguments",
        "type": "object"
      },
      "name": "gpu_price"
    },
    {
      "description": "列出所有可查询的 GPU 卡型(免费)。付费查询前先调这个拿准确名称。",
      "inputSchema": {
        "properties": {},
        "title": "list_gpu_modelsArguments",
        "type": "object"
      },
      "name": "list_gpu_models"
    },
    {
      "description": "近 90 天 GPU 行情涨跌榜:按区间涨跌幅排序的降价/涨价卡型,含当前价与区间最低价。示例: market_movers(top=3) → 降价榜 A6000 48GB 2.52 元(-28.6%)、A100 80GB 5.47 元(-21.6%)、RTX 3090 0.80 元(-19.2%)。按次计费 $0.005 USDC。",
      "inputSchema": {
        "properties": {
          "top": {
            "default": 5,
            "title": "Top",
            "type": "integer"
          }
        },
        "title": "market_moversArguments",
        "type": "object"
      },
      "name": "market_movers"
    },
    {
      "description": "健康检查,免费。返回服务状态、收款地址、网络与价目表。",
      "inputSchema": {
        "properties": {},
        "title": "pingArguments",
        "type": "object"
      },
      "name": "ping"
    },
    {
      "description": "各 GPU 租用平台的数据监测覆盖度评分(A~E):自动抓取成功率、收录天数、库存充足率、覆盖卡型数。注意:衡量的是本数据源对该平台的价格监测覆盖度,不代表平台自身的服务质量。示例: platform_reliability() → 31 家平台评分,如 gpushare 99 分 A 级(抓取成功率 98%、覆盖 7 张卡、39/40 天)。按次计费 $0.005 USDC。",
      "inputSchema": {
        "properties": {},
        "title": "platform_reliabilityArguments",
        "type": "object"
      },
      "name": "platform_reliability"
    },
    {
      "description": "按任务推荐最便宜的 GPU 租用方案:输入任务(如'微调 7B'/'视频生成',或英文 finetune-7b/video-gen),返回推荐卡型、最便宜平台、每小时单价与估算任务总成本。覆盖 8 类任务:微调、推理、绘图、视频、渲染、学生练手、70B 训练、多卡集群。示例: recommend_for_task(task='微调 7B') → 最便宜卡 + 平台 + 单价 × 8 小时的总成本。这是别处没有的'按任务问价'能力。按次计费 $0.01 USDC。",
      "inputSchema": {
        "properties": {
          "task": {
            "title": "Task",
            "type": "string"
          }
        },
        "required": [
          "task"
        ],
        "title": "recommend_for_taskArguments",
        "type": "object"
      },
      "name": "recommend_for_task"
    },
    {
      "description": "免费订阅降价提醒:某张 GPU 的全平台最低价降到目标价(元/小时)以下时邮件通知用户(每小时检查)。新邮箱会先收到 6 位验证码(30 分钟有效),需再调 verify_price_alert 完成激活;已验证过的邮箱直接生效。免费版每人最多同时盯 3 张卡。示例: subscribe_price_alert(email='user@example.com', gpu='RTX 4090', target_price=1.5)",
      "inputSchema": {
        "properties": {
          "email": {
            "title": "Email",
            "type": "string"
          },
          "gpu": {
            "title": "Gpu",
            "type": "string"
          },
          "target_price": {
            "title": "Target Price",
            "type": "number"
          }
        },
        "required": [
          "email",
          "gpu",
          "target_price"
        ],
        "title": "subscribe_price_alertArguments",
        "type": "object"
      },
      "name": "subscribe_price_alert"
    },
    {
      "description": "用用户邮箱收到的 6 位验证码激活降价提醒订阅(免费)。示例: verify_price_alert(email='user@example.com', gpu='RTX 4090', code='123456')",
      "inputSchema": {
        "properties": {
          "code": {
            "title": "Code",
            "type": "string"
          },
          "email": {
            "title": "Email",
            "type": "string"
          },
          "gpu": {
            "title": "Gpu",
            "type": "string"
          }
        },
        "required": [
          "email",
          "gpu",
          "code"
        ],
        "title": "verify_price_alertArguments",
        "type": "object"
      },
      "name": "verify_price_alert"
    }
  ]
}

What the leaf hashes

{"body":"a5165d7aa931235afd53363f0d1fe7e258aedcd8f96a3dc495e73f4b218fca31","id":3669425,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793931489175632,"prev":2725463,"subject":"93b34229-546b-4728-b33c-91c67381e1ee","subject_kind":"endpoint"}

Proof

Fold these into the leaf in order, hashing each sorted pair with keccak256, to reach the root of (303443 rows).

  1. 0x5f8ae3e3e4fa28e839c67a69f8fe0a472a83cca80fe6685019aa2b16e66e1450
  2. 0x35ebf07d9a07398b66620993c6adf7baff11c6f5c95f02a4545d4975c7a03aa5
  3. 0xdcf00a9a88e192f9336552a6a2f4d75f3581929764beb3ff412e8f8f3d2a1b3e
  4. 0x4fabd46b848ba078436c18b6ad6f1b2b763f9c8bac8405648024dd5507a1ca95
  5. 0x7a556b296fb2e17996b6701421411e9cd56d88ffc798aff210d9581f13e8da66
  6. 0x8fb5d8d50b2455f6c00c53a1fa31ad92173352b8206d5e9ba7cf7ddebd88d457
  7. 0x003b72d7fb232b916b1d72d1875aac582bc887f033ce1ccf23d94cde7bff3892
  8. 0x8245a10a150c61c618df8c485549a0444fc784bbac2cc0d2997978ca0706a30f
  9. 0xc0cf891707f2ae615fbb470f70c2377b4bb8b2520d8b95e2937ed18548eff38f
  10. 0xe7940a53dd6d4e3d4a45e1ac5524af36bfb13d3fda02d140259dcfdc4bc6af49
  11. 0x0fb1e7437bde305e049ee780c32c93274b22b15c1a01fc606d5a1544b153fc09
  12. 0x85b6084f25e1adbc2dcbf54d4b4bcfbceca59e6c7f1191d754a040e1b93a028b
  13. 0x61731d3b116db5233b7fd88e3ba87bf952acf90777af812de1d446a7f3186635
  14. 0x436c32b517f221d6ad84bca91be0dd1a4a4c33e7297c776990ac7a95a4e2e423
  15. 0xf5bd84a61225f062ef205a5e8dc4f170a403665fdfa49b2b923457e0386f3abe
  16. 0x7a2e5c8104eb5015bfa08d52a9278aa0b4da48bd2fb98690cc2d1c225b5dc691
  17. 0x4a618d78b1cebba8beec4ef22aaac9187dcdfb39064e0be537ca2600abb90740
  18. 0x119743aadcddb571b28b442b62196d4a0afc4e1c9979c2d477d34fcc9413deaf
  19. 0xc0d08d48601d1be90bcfc025e66bcaa0030120d688dd9c919b36c2c4446f4948
Day root
0xb30ccefe7182c6f767e1fcbfb5f64ffd649da831f665f65c5ff39cd40512284f
Chained
0xc383f7ef68d2914082484765aa09e42c12c59a74a096ae64127c562618c506d3
Published
On Arc Testnet, block 71111178: 0xfba13cb7ee4ada7f2fee3702a786a2201596be2ffea37dfc281ab4c8e9942fe1

How to check it · This row as JSON