Hyperliquid Cross-Sectional Analytics (Tessera)

Rank, screen and compare the Hyperliquid perp universe on a completed day.

使うべきか

品質と安全性

A
説明の品質
100%
スキーマの完全性
79%
命名の品質
93%
ポイズニングのリスク
100%
権限の一致
100%
プロトコルへの準拠
100%

ツール定義とプロトコルへの準拠に関する自動分析に基づいています。

コンテキストコスト

~8,475トークン数(ツール定義)
~11.2 KB一般的なレスポンスサイズ
注意への影響は大きい(128k コンテキストの 6.62%)

これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。

インストール

ワンクリックインストール

これを `claude_desktop_config.json` ファイルに追加してください:

{
  "mcpServers": {
    "hyperliquid-data": {
      "url": "https://tesseralytics.dev/mcp"
    }
  }
}

リモートエンドポイント

https://tesseralytics.dev/mcpstreamable-http

できること

ツール一覧

ツール(8)

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
🟢get_universe(bar, day, days, scope, top_n)

The coverage picture: the last complete interval, how many markets are in the universe for a scope, how much history sits behind them, and how densely it is populated. Pick bar (1d, the default, or 1h for completed hours) to describe completed days or completed hours. The range counts cover the last 7 days at bar: 1h (pass days, 1..30, to widen them) and the whole published range at bar: 1d. A compact SUMMARY by default — pass top_n (1..100, clamped) only if you need the per-market counts.

入力スキーマ

{
  "type": "object",
  "properties": {
    "bar": {
      "default": null,
      "description": "`1d` (the default) for completed UTC days, `1h` for completed UTC hours.\nAn interval, at either grain, is stamped by the instant it **closes** —\nan hourly `…T09:00:00Z` is the hour that ended at 09:00.",
      "nullable": true,
      "type": "string"
    },
    "day": {
      "default": null,
      "description": "The day or hour to describe: `YYYY-MM-DD` or `latest` at `bar: 1d`, a\ncompleted `YYYY-MM-DDTHH:00:00Z` (the hour that *ended* there) or\n`latest` at `bar: 1h`.",
      "nullable": true,
      "type": "string"
    },
    "days": {
      "default": null,
      "description": "How many days of completed intervals the range counts cover, 1..30.\nDefaults to 7 at `bar: 1h` — the hourly source publishes one object per\ncompleted hour, so an unbounded inventory would open every hour ever\npublished — and to the whole published range at `bar: 1d`, whose source\nis one object per month. The window the counts actually covered is\n`interval_start`..`interval_end`, and `notes` says when it was bounded.",
      "format": "uint",
      "minimum": 0,
      "nullable": true,
      "type": "integer"
    },
    "scope": {
      "default": null,
      "description": "`crypto` (the default), `hip3`, or `all`.",
      "nullable": true,
      "type": "string"
    },
    "top_n": {
      "default": null,
      "description": "Per-market detail is off by default; passing a value (1..100, clamped)\nreturns that many markets, listed by name, alongside the summary.",
      "format": "uint",
      "minimum": 0,
      "nullable": true,
      "type": "integer"
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "UniverseArgs"
}

出力スキーマ

{
  "type": "object",
  "properties": {
    "as_of": {
      "description": "The interval the per-population counts describe.",
      "type": "string"
    },
    "bar": {
      "description": "The grain this answer was computed at: `1d` or `1h`.",
      "type": "string"
    },
    "bar_age_hours": {
      "format": "double",
      "type": "number"
    },
    "coins": {
      "description": "Per-market detail, only when requested. Markets are listed by name.",
      "items": {
        "$ref": "#/$defs/UniverseCoin"
      },
      "nullable": true,
      "type": "array"
    },
    "coverage_from_manifest": {
      "description": "True when the interval range came from the published coverage manifest,\nfalse when it had to be read from the data or the object listing itself.",
      "type": "boolean"
    },
    "eligible_count": {
      "description": "Distinct markets in scope over the counted range.",
      "format": "int64",
      "type": "integer"
    },
    "interval_count": {
      "description": "Distinct intervals in the range the counts below cover.",
      "format": "int64",
      "type": "integer"
    },
    "interval_end": {
      "description": "The newest interval the counts below cover — the same interval `as_of`\ndescribes, since the counts are the history behind those populations.",
      "type": "string"
    },
    "interval_start": {
      "description": "The oldest interval the counts below cover: the published range start,\nthe caller's history floor when the plan clips it, or the start of the\nwindow `days` bounded them to. The response says which, in `notes`.",
      "type": "string"
    },
    "market_count_crypto": {
      "description": "Markets without a deployer prefix on the described interval, whatever\nscope was asked for.",
      "format": "int64",
      "type": "integer"
    },
    "market_count_hip3": {
      "description": "Markets with a deployer prefix on the described interval.",
      "format": "int64",
      "type": "integer"
    },
    "market_count_total": {
      "description": "Distinct markets in scope over the counted range.",
      "format": "int64",
      "type": "integer"
    },
    "matched_count": {
      "description": "Markets the counted range actually represents — the ones with at least one\nrow in it, which is every market in `eligible_count` at the described\ninterval.",
      "format": "int64",
      "type": "integer"
    },
    "months_covered": {
      "format": "int64",
      "type": "integer"
    },
    "notes": {
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "published_at": {
      "nullable": true,
      "type": "string"
    },
    "row_count": {
      "description": "Rows in scope over the counted range.",
      "format": "int64",
      "type": "integer"
    },
    "rows_per_market_interval": {
      "description": "`row_count` divided by (intervals × markets) — how densely the counted\nrange is populated. Below 1.0 means some markets are missing some\nintervals.",
      "format": "double",
      "type": "number"
    },
    "scope": {
      "type": "string"
    },
    "source": {
      "type": "string"
    },
    "truncated": {
      "description": "True when more markets exist than the detail list returned.",
      "type": "boolean"
    },
    "visible_count": {
      "description": "Markets in your plan's slice on the described interval, before any scope\nclass is applied.",
      "format": "int64",
      "type": "integer"
    }
  },
  "required": [
    "bar",
    "source",
    "as_of",
    "bar_age_hours",
    "scope",
    "interval_start",
    "interval_end",
    "interval_count",
    "months_covered",
    "visible_count",
    "eligible_count",
    "matched_count",
    "market_count_total",
    "market_count_crypto",
    "market_count_hip3",
    "row_count",
    "rows_per_market_interval",
    "coverage_from_manifest",
    "truncated",
    "notes"
  ],
  "$defs": {
    "UniverseCoin": {
      "description": "One market's coverage within the described range.",
      "properties": {
        "coin": {
          "type": "string"
        },
        "observations": {
          "description": "How many intervals of the range this market appears on — days at\n`bar: 1d`, completed hours at `bar: 1h`.",
          "format": "int64",
          "type": "integer"
        }
      },
      "required": [
        "coin",
        "observations"
      ],
      "type": "object"
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "UniverseResult"
}
🟢describe_dataset(asset)

The full dictionary for ONE downloadable dataset: description plus every column's type, nullability and plain-English meaning. Pass a name from list_datasets. Open — no key needed. For the fields the query tools accept, use list_fields.

入力スキーマ

{
  "type": "object",
  "properties": {
    "asset": {
      "description": "Dataset name, as returned by `list_datasets`.",
      "type": "string"
    }
  },
  "required": [
    "asset"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "description": "Which dataset's dictionary to return.",
  "title": "DatasetArg"
}

出力スキーマ

{
  "type": "object",
  "properties": {
    "cadence": {
      "description": "How frequently the data is sampled, e.g. \"1-minute bars\".",
      "type": "string"
    },
    "category": {
      "description": "Presentation category, e.g. `raw-tiles` or `forecast-layer`.",
      "type": "string"
    },
    "column_count": {
      "description": "Number of documented columns.",
      "format": "uint",
      "minimum": 0,
      "type": "integer"
    },
    "column_groups": {
      "description": "Columns, grouped for presentation, in schema order.",
      "items": {
        "$ref": "#/$defs/ColumnGroup"
      },
      "type": "array"
    },
    "description": {
      "description": "Longer prose — the dictionary page header.",
      "type": "string"
    },
    "direct_answer": {
      "default": "",
      "description": "40-60 word keyword-first lead answer — the definitional \"what is this\"\nblurb, and the strongest AI-citation extraction target. Defaulted for\nforward/backward compatibility with snapshots predating the field.",
      "type": "string"
    },
    "keywords": {
      "default": [],
      "description": "Per-dataset discovery keywords (schema.org keywords on the web).",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "name": {
      "description": "Dataset name, exactly as `list_datasets` reports it.",
      "type": "string"
    },
    "note": {
      "description": "Optional \"how to use this\" callout.",
      "nullable": true,
      "type": "string"
    },
    "seo_title": {
      "default": "",
      "description": "Keyword-first SEO title tag (web `<title>`). Defaulted so older snapshots\nwithout the field still deserialize.",
      "type": "string"
    },
    "summary": {
      "description": "One-line intuitive summary — the catalog card.",
      "type": "string"
    },
    "temporal": {
      "$ref": "#/$defs/Temporal",
      "default": {
        "convention": "",
        "grain": "",
        "label": "",
        "timestamp_field": ""
      },
      "description": "Machine-readable timestamp/interval contract: what the label marks and\nhow to join without leaking the future. Defaulted so snapshots predating\nthe field still deserialize."
    },
    "title": {
      "description": "Human-friendly title, e.g. \"Order-flow OHLCV (1-minute)\".",
      "type": "string"
    },
    "use_case": {
      "default": "",
      "description": "One-line \"what you'd use it for\" (buyer-intent) copy.",
      "type": "string"
    }
  },
  "required": [
    "name",
    "title",
    "category",
    "cadence",
    "summary",
    "description",
    "column_count",
    "column_groups"
  ],
  "$defs": {
    "ColumnDoc": {
      "description": "One column's dictionary entry: the engineering facts (type/nullability/how\nit's computed) plus the plain-English `meaning` (what it is and why you'd care).",
      "properties": {
        "description": {
          "description": "Technical description — *how* the column is computed. May be absent.",
          "nullable": true,
          "type": "string"
        },
        "meaning": {
          "description": "Plain-English meaning — *what* the column is and why it's useful.",
          "type": "string"
        },
        "name": {
          "description": "Column name.",
          "type": "string"
        },
        "nullable": {
          "description": "Whether the column may be null.",
          "type": "boolean"
        },
        "type": {
          "description": "Arrow type string, e.g. `float64`, `timestamp[us]`.",
          "type": "string"
        }
      },
      "required": [
        "name",
        "type",
        "nullable",
        "meaning"
      ],
      "type": "object"
    },
    "ColumnGroup": {
      "description": "A labelled section of columns within a dataset.",
      "properties": {
        "columns": {
          "items": {
            "$ref": "#/$defs/ColumnDoc"
          },
          "type": "array"
        },
        "label": {
          "description": "Section heading, or `null` for a single unlabelled group.",
          "nullable": true,
          "type": "string"
        },
        "meaning": {
          "description": "Group-level plain-English meaning, used for large column families (e.g.\nthe residualized factor backbone) where a per-column line adds no value.",
          "nullable": true,
          "type": "string"
        },
        "window": {
          "default": null,
          "description": "Temporal window of this group's fields relative to the timestamp label:\none of `point_in_time`, `backward`, `forward`, `contemporaneous`,\n`static`. Null when the dataset-level `temporal.convention` covers them.",
          "nullable": true,
          "type": "string"
        }
      },
      "required": [
        "columns"
      ],
      "type": "object"
    },
    "Temporal": {
      "description": "The dataset's temporal contract — what the timestamp column marks and the\nlook-ahead-safety rules for joining. Mirror of the resolver's `temporal`\nblock (`semantic/__init__.py`).",
      "properties": {
        "convention": {
          "description": "One-paragraph plain-English join / look-ahead contract.",
          "type": "string"
        },
        "grain": {
          "description": "Observation width, e.g. `1m`, `1h`, `1d`, `1mo`.",
          "type": "string"
        },
        "label": {
          "description": "What the label marks: one of `interval_start`, `interval_end`,\n`snapshot`, `forecast_target`.",
          "type": "string"
        },
        "timestamp_field": {
          "description": "Which column carries the label, e.g. `time`, `day`, `month_start`.",
          "type": "string"
        }
      },
      "required": [
        "grain",
        "timestamp_field",
        "label",
        "convention"
      ],
      "type": "object"
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "description": "One dataset's catalog entry + full data dictionary.",
  "title": "DatasetDoc"
}
🟢screen_universe(bar, coins, columns, conditions, day, ...)

Screen the whole market on ONE completed interval with several conditions ANDed together. Pick bar (1d, the default, or 1h for completed hours; the anonymous trial is screened at 1d). Conditions use op >, <, >=, <=, between, top_pct or bottom_pct; top_pct/bottom_pct are deciles of your eligible markets, and the liquidity floor (USD/day at either bar) is applied before the deciles so they are measured over the population you are choosing from. Answers 'top-decile funding with bottom-decile open-interest change' and 'open interest rising faster than volume'. A market that does not report a field never satisfies a condition on it.

入力スキーマ

{
  "type": "object",
  "properties": {
    "bar": {
      "default": null,
      "description": "`1d` (the default) for completed UTC days, `1h` for completed UTC hours.\nAn interval, at either grain, is stamped by the instant it **closes** —\nan hourly `…T09:00:00Z` is the hour that ended at 09:00.",
      "nullable": true,
      "type": "string"
    },
    "coins": {
      "default": null,
      "description": "Restrict to these markets.",
      "items": {
        "type": "string"
      },
      "nullable": true,
      "type": "array"
    },
    "columns": {
      "default": null,
      "description": "Fields to return per market, from `list_fields`.",
      "items": {
        "type": "string"
      },
      "nullable": true,
      "type": "array"
    },
    "conditions": {
      "description": "Conditions, all of which must hold. A market that does not report a\nfield never satisfies a condition on it.",
      "items": {
        "$ref": "#/$defs/ConditionArg"
      },
      "type": "array"
    },
    "day": {
      "default": null,
      "description": "The day or hour to screen: `YYYY-MM-DD` or `latest` at `bar: 1d`, a\ncompleted `YYYY-MM-DDTHH:00:00Z` (the hour that *ended* there) or\n`latest` at `bar: 1h`.",
      "nullable": true,
      "type": "string"
    },
    "descending": {
      "default": null,
      "description": "Rank largest first (the default).",
      "nullable": true,
      "type": "boolean"
    },
    "max_results": {
      "default": null,
      "description": "How many markets to return, 1..100 (values outside are clamped to the\nnearest bound and the response says so). Defaults to 25.",
      "format": "uint",
      "minimum": 0,
      "nullable": true,
      "type": "integer"
    },
    "min_usd_volume_7d_avg": {
      "default": null,
      "description": "Drop markets whose average **daily** traded notional over the trailing\nwindow is below this value, in USD/day at either bar — a floor chosen at\n`1d` means the same thing at `1h`.",
      "format": "double",
      "nullable": true,
      "type": "number"
    },
    "order_by": {
      "default": null,
      "description": "The field to rank the matches by. Defaults to the interval's traded\nnotional.",
      "nullable": true,
      "type": "string"
    },
    "scope": {
      "default": null,
      "description": "`crypto` (the default), `hip3`, or `all`.",
      "nullable": true,
      "type": "string"
    }
  },
  "required": [
    "conditions"
  ],
  "$defs": {
    "ConditionArg": {
      "description": "One condition of a screen.",
      "properties": {
        "column": {
          "default": null,
          "description": "The field to test, from `list_fields`. Accepted under either name —\n`field`, which is what every other argument on this surface calls it, or\nits original `column`. Validated as present rather than required by the\nschema, so a condition that names no field is rejected by name below\ninstead of by a deserializer message no caller can act on.",
          "nullable": true,
          "type": "string"
        },
        "op": {
          "description": "One of `>`, `<`, `>=`, `<=`, `between`, `top_pct`, `bottom_pct`.\n`top_pct`/`bottom_pct` keep the best/worst `value` percent of the\nmarkets you can see by that field.",
          "type": "string"
        },
        "value": {
          "description": "The threshold. For `top_pct`/`bottom_pct` this is a percentage, e.g. 10\nfor the top decile.",
          "format": "double",
          "type": "number"
        },
        "value2": {
          "default": null,
          "description": "Required for `between`: the upper bound, inclusive.",
          "format": "double",
          "nullable": true,
          "type": "number"
        }
      },
      "required": [
        "op",
        "value"
      ],
      "type": "object"
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "ScreenArgs"
}

出力スキーマ

{
  "type": "object",
  "properties": {
    "as_of": {
      "type": "string"
    },
    "bar": {
      "description": "The grain this answer was computed at: `1d` or `1h`.",
      "type": "string"
    },
    "bar_age_hours": {
      "format": "double",
      "type": "number"
    },
    "eligible_count": {
      "description": "Markets left after your explicit market filter and any\ntraded-notional floor — the population the percentage conditions were\nmeasured against.",
      "format": "int64",
      "type": "integer"
    },
    "matched_count": {
      "description": "Markets that met every condition.",
      "format": "int64",
      "type": "integer"
    },
    "notes": {
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "published_at": {
      "nullable": true,
      "type": "string"
    },
    "row_count": {
      "format": "uint",
      "minimum": 0,
      "type": "integer"
    },
    "rows": {
      "items": true,
      "type": "array"
    },
    "scope": {
      "type": "string"
    },
    "source": {
      "type": "string"
    },
    "truncated": {
      "type": "boolean"
    },
    "visible_count": {
      "description": "Markets in your plan's slice with a row on this interval, before any\nfilter you passed.",
      "format": "int64",
      "type": "integer"
    }
  },
  "required": [
    "bar",
    "source",
    "as_of",
    "bar_age_hours",
    "scope",
    "visible_count",
    "eligible_count",
    "matched_count",
    "row_count",
    "truncated",
    "rows",
    "notes"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "ScreenResult"
}
🟢funding_divergence(bar, benchmark, coins, day, metric, ...)

Rank markets by how far their funding has diverged from a benchmark (default ETH) over a trailing window. Pick bar (1d, the default, or 1h for completed hours) to read completed days or completed hours. day defaults to the last complete interval. metric=rate compares mean funding over the window; metric=cum_funding_spread compares how far a market's cumulative funding level travelled inside the window (its high minus its low, so never negative) — that is not the funding the window accumulated: for that, read funding_paid from query_series and sum it. Returns the most diverged in each direction, each row with usd_volume_avg so a spread can be sized; pass min_usd_volume_7d_avg (USD/day) to exclude markets too illiquid to trade the divergence in. Markets with no funding reading are excluded from both lists. Descriptive only.

入力スキーマ

{
  "type": "object",
  "properties": {
    "bar": {
      "default": null,
      "description": "`1d` (the default) for completed UTC days, `1h` for completed UTC hours.\nAn interval, at either grain, is stamped by the instant it **closes** —\nan hourly `…T09:00:00Z` is the hour that ended at 09:00.",
      "nullable": true,
      "type": "string"
    },
    "benchmark": {
      "default": null,
      "description": "The market whose funding is the yardstick. Defaults to ETH.",
      "nullable": true,
      "type": "string"
    },
    "coins": {
      "default": null,
      "description": "Restrict to these markets.",
      "items": {
        "type": "string"
      },
      "nullable": true,
      "type": "array"
    },
    "day": {
      "default": null,
      "description": "The day or hour to rank as of: `YYYY-MM-DD` or `latest` at `bar: 1d`, a\ncompleted `YYYY-MM-DDTHH:00:00Z` (the hour that *ended* there) or `latest`\nat `bar: 1h`.",
      "nullable": true,
      "type": "string"
    },
    "metric": {
      "default": null,
      "description": "`rate` (the default) ranks each market's mean funding over the window\nminus the benchmark's; `cum_funding_spread` ranks the **spread of the\ncumulative funding level** over the window — its high minus its low, so\nalways non-negative — minus the benchmark's. That is not the funding the\nwindow accumulated: `cum_funding` is a running total, so a market whose\nlevel retraced has a large spread and a *negative* accumulation (and one\nthat reversed inside the window has a spread several times its true\naccumulation). Measured 2026-10-13 over 34 markets and the trailing 168\nhours, the expression below reproduced the served value exactly, while\n`SUM(funding_paid)` over the same window disagreed in sign for 11 of\nthem (TRX +0.00440 vs −0.00445) and by up to 100× (CASHCAT 0.2050 vs\n0.0020). The accumulation is not a served field; read `funding_paid`\nfrom `query_series` and sum it over the window you want instead.",
      "nullable": true,
      "type": "string"
    },
    "min_usd_volume_7d_avg": {
      "default": null,
      "description": "Drop markets whose average **daily** traded notional over the divergence\nwindow is below this value, in USD/day at either bar. Each row carries\nthat figure as `usd_volume_avg`, so the floor decides which spreads are\ntradeable rather than which are largest.",
      "format": "double",
      "nullable": true,
      "type": "number"
    },
    "scope": {
      "default": null,
      "description": "`crypto` (the default), `hip3`, or `all`.",
      "nullable": true,
      "type": "string"
    },
    "top_n": {
      "default": null,
      "description": "Markets per ranked list, 1..100 (values outside are clamped to the\nnearest bound and the response says so). Defaults to 10.",
      "format": "uint",
      "minimum": 0,
      "nullable": true,
      "type": "integer"
    },
    "window_days": {
      "default": null,
      "description": "Length of the trailing window in days, 1..365. Defaults to 7.",
      "format": "uint",
      "minimum": 0,
      "nullable": true,
      "type": "integer"
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "DivergenceArgs"
}

出力スキーマ

{
  "type": "object",
  "properties": {
    "as_of": {
      "type": "string"
    },
    "bar": {
      "description": "The grain this answer was computed at: `1d` or `1h`.",
      "type": "string"
    },
    "bar_age_hours": {
      "format": "double",
      "type": "number"
    },
    "benchmark": {
      "type": "string"
    },
    "benchmark_value": {
      "description": "The benchmark's own value for the metric.",
      "format": "double",
      "type": "number"
    },
    "eligible_count": {
      "description": "Markets left after your explicit market filter.",
      "format": "int64",
      "type": "integer"
    },
    "matched_count": {
      "description": "Markets that had a funding reading in the window. Markets without one are\nexcluded from both lists and from this count — a missing reading must\nnever appear as an extreme.",
      "format": "int64",
      "type": "integer"
    },
    "metric": {
      "type": "string"
    },
    "notes": {
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "published_at": {
      "nullable": true,
      "type": "string"
    },
    "scope": {
      "type": "string"
    },
    "source": {
      "type": "string"
    },
    "top_negative": {
      "description": "The largest divergences toward the benchmark's opposite, most extreme\nfirst.",
      "items": {
        "$ref": "#/$defs/DivergenceRow"
      },
      "type": "array"
    },
    "top_positive": {
      "description": "The largest divergences away from the benchmark, most extreme first.",
      "items": {
        "$ref": "#/$defs/DivergenceRow"
      },
      "type": "array"
    },
    "truncated": {
      "type": "boolean"
    },
    "visible_count": {
      "description": "Markets in your plan's slice on this interval, before any filter you\npassed.",
      "format": "int64",
      "type": "integer"
    },
    "window_days": {
      "format": "uint",
      "minimum": 0,
      "type": "integer"
    }
  },
  "required": [
    "bar",
    "source",
    "as_of",
    "bar_age_hours",
    "scope",
    "visible_count",
    "eligible_count",
    "matched_count",
    "metric",
    "benchmark",
    "window_days",
    "benchmark_value",
    "top_positive",
    "top_negative",
    "truncated",
    "notes"
  ],
  "$defs": {
    "DivergenceRow": {
      "description": "One market's funding divergence from the benchmark.",
      "properties": {
        "coin": {
          "type": "string"
        },
        "divergence": {
          "description": "`value` minus the benchmark's.",
          "format": "double",
          "type": "number"
        },
        "usd_volume_avg": {
          "description": "Mean traded notional per interval over the same window, in USD/day at\neither grain. A funding spread is only as interesting as the size a\nposition in it can take, and the widest divergence in a slice is\nregularly a quiet day in an illiquid market — read this column before\nreading `divergence`.",
          "format": "double",
          "type": "number"
        },
        "value": {
          "description": "This market's value for the requested metric over the window.",
          "format": "double",
          "type": "number"
        }
      },
      "required": [
        "coin",
        "value",
        "divergence",
        "usd_volume_avg"
      ],
      "type": "object"
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "DivergenceResult"
}
🟢list_fields

Every field the query tools accept, each with its meaning, unit, whether it can be missing, and which bars (1d, 1h) it exists on. Open — no key needed. Call this before query_cross_section, screen_universe or query_series. Percentile, z-score and the top_pct/bottom_pct conditions rank within the markets your plan can see, so they need a wide slice.

入力スキーマ

{
  "type": "object",
  "properties": {}
}

出力スキーマ

{
  "type": "object",
  "properties": {
    "fields": {
      "description": "Every field the query tools accept.",
      "items": {
        "$ref": "#/$defs/FieldDoc"
      },
      "type": "array"
    },
    "generated_at": {
      "description": "When this vocabulary was produced.",
      "type": "string"
    },
    "notes": {
      "items": {
        "type": "string"
      },
      "type": "array"
    }
  },
  "required": [
    "generated_at",
    "fields",
    "notes"
  ],
  "$defs": {
    "FieldDoc": {
      "description": "One addressable field's documentation.\n\nServed verbatim by the MCP plane's `list_fields`; the schema derive is what\nkeeps the tool's advertised output shape and the served JSON the same thing.",
      "properties": {
        "best_horizon_hours": {
          "description": "Horizon (hours) at which the field's signal is strongest/most durable.",
          "format": "uint32",
          "minimum": 0,
          "nullable": true,
          "type": "integer"
        },
        "class": {
          "description": "Which signal class the field belongs to, when it has been measured:\n`state` (durable, 24 h horizon, retention ≈ 1), `microstructure`\n(same-bar, decays under the entry delay), `momentum` (short-term\nreversal that survives the delay) or `no_signal`. Absent for stored\ncolumns that were never measured on their own.",
          "nullable": true,
          "type": "string"
        },
        "grains": {
          "description": "Plane grains on which this field is available, in canonical order.",
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        "horizon_hours": {
          "description": "Horizon (hours) the signal class describes.",
          "format": "uint32",
          "minimum": 0,
          "nullable": true,
          "type": "integer"
        },
        "kind": {
          "description": "`stored` (a column in the plane's own source) or `factor` (computed at\nquery time over a trailing window, or from the selected end row).",
          "type": "string"
        },
        "meaning": {
          "description": "Plain-English meaning, authored in the semantic layer.",
          "type": "string"
        },
        "name": {
          "type": "string"
        },
        "nullable": {
          "description": "Whether the value can be absent for a market on a selected interval.",
          "type": "boolean"
        },
        "type": {
          "description": "The stored column's type (`float64`, `uint32`, `date32`, …); absent for\nquery-time factors, which are always floats.",
          "nullable": true,
          "type": "string"
        },
        "unit": {
          "description": "The unit the values actually carry (`usd_notional`, `base_units`,\n`ratio`, `fraction`, `count`, `date`, …). A stored column name is never a\nsynonym for its unit — the OI a caller sees is USD notional where the\ncolumn is named for the notion.",
          "type": "string"
        }
      },
      "required": [
        "name",
        "meaning",
        "unit",
        "nullable",
        "kind",
        "grains"
      ],
      "type": "object"
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "FieldsResult"
}
🟢query_series(bar, coins, columns, ending_day, scope, ...)

The series for one market or a few (max 10): one row per market per interval over a trailing window, ordered by interval then market. Pick bar (1d, the default, for one row per day, or 1h for one row per completed hour). Answers 'is this move backed by real flow' and 'how has positioning built up'. ending_day defaults to the last complete interval. The whole answer is capped, so markets times window_days (times 24 at bar 1h) must stay inside the row cap; the response states the window it used.

入力スキーマ

{
  "type": "object",
  "properties": {
    "bar": {
      "default": null,
      "description": "`1d` (the default) for completed UTC days, `1h` for completed UTC hours.\nAn interval, at either grain, is stamped by the instant it **closes** —\nan hourly `…T09:00:00Z` is the hour that ended at 09:00.",
      "nullable": true,
      "type": "string"
    },
    "coins": {
      "description": "The markets to return, 1..10.",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "columns": {
      "default": null,
      "description": "Fields to return per row, from `list_fields`. The interval column\n(`day` at 1d, `hour` at 1h) and `coin` are always included.",
      "items": {
        "type": "string"
      },
      "nullable": true,
      "type": "array"
    },
    "ending_day": {
      "default": null,
      "description": "The last interval to include: `YYYY-MM-DD` or `latest` at `bar: 1d`, a\ncompleted `YYYY-MM-DDTHH:00:00Z` (the hour that *ended* there) or\n`latest` at `bar: 1h`.",
      "nullable": true,
      "type": "string"
    },
    "scope": {
      "default": null,
      "description": "`crypto` (the default), `hip3`, or `all`.",
      "nullable": true,
      "type": "string"
    },
    "window_days": {
      "default": null,
      "description": "Length of the trailing window in days, 1..365. Defaults to 7. At\n`bar: 1h` one window day is 24 hourly rows.",
      "format": "uint",
      "minimum": 0,
      "nullable": true,
      "type": "integer"
    }
  },
  "required": [
    "coins"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "SeriesArgs"
}

出力スキーマ

{
  "type": "object",
  "properties": {
    "as_of": {
      "description": "The last interval in the series.",
      "type": "string"
    },
    "bar": {
      "description": "The grain this answer was computed at: `1d` or `1h`.",
      "type": "string"
    },
    "bar_age_hours": {
      "format": "double",
      "type": "number"
    },
    "eligible_count": {
      "description": "The markets you asked for, after the plan's slice and your filter were\nintersected.",
      "format": "int64",
      "type": "integer"
    },
    "matched_count": {
      "description": "How many of the requested markets the series actually has rows for — less\nthan `eligible_count` when one of them has no data in the window.",
      "format": "int64",
      "type": "integer"
    },
    "notes": {
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "published_at": {
      "nullable": true,
      "type": "string"
    },
    "row_count": {
      "format": "uint",
      "minimum": 0,
      "type": "integer"
    },
    "rows": {
      "description": "Ordered by interval, then market.",
      "items": true,
      "type": "array"
    },
    "scope": {
      "type": "string"
    },
    "source": {
      "type": "string"
    },
    "truncated": {
      "type": "boolean"
    },
    "visible_count": {
      "description": "Markets in your plan's slice with a row on the last interval.",
      "format": "int64",
      "type": "integer"
    },
    "window_days": {
      "description": "The history length requested, in days. Factor windows are fixed by\ntheir names and do not move with it.",
      "format": "uint",
      "minimum": 0,
      "type": "integer"
    }
  },
  "required": [
    "bar",
    "source",
    "as_of",
    "bar_age_hours",
    "scope",
    "window_days",
    "visible_count",
    "eligible_count",
    "matched_count",
    "row_count",
    "truncated",
    "rows",
    "notes"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "SeriesResult"
}
🟢list_datasets

List the downloadable datasets: one-line summary, the plan required, and the month range available. Open — no key needed. Then use describe_dataset for one dataset's columns, or list_fields for the fields the query tools accept.

入力スキーマ

{
  "type": "object",
  "properties": {}
}

出力スキーマ

{
  "type": "object",
  "properties": {
    "datasets": {
      "items": {
        "$ref": "#/$defs/CatalogEntry"
      },
      "type": "array"
    },
    "generated_at": {
      "description": "When this catalog was produced.",
      "type": "string"
    }
  },
  "required": [
    "generated_at",
    "datasets"
  ],
  "$defs": {
    "CatalogEntry": {
      "description": "One dataset in the public catalog.",
      "properties": {
        "cadence": {
          "type": "string"
        },
        "category": {
          "type": "string"
        },
        "column_count": {
          "format": "uint",
          "minimum": 0,
          "type": "integer"
        },
        "months": {
          "description": "The published month range, `[earliest, latest]`. Absent when the catalog\nlists no months for it.",
          "items": {
            "type": "string"
          },
          "nullable": true,
          "type": "array"
        },
        "name": {
          "type": "string"
        },
        "summary": {
          "type": "string"
        },
        "title": {
          "type": "string"
        }
      },
      "required": [
        "name",
        "title",
        "category",
        "cadence",
        "summary",
        "column_count"
      ],
      "type": "object"
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "DatasetsResult"
}
🟢query_cross_section(bar, coins, columns, day, descending, ...)

Rank the whole market on ONE completed interval: pick bar (1d, the default, or 1h for completed hours), columns, an order_by field and top_n. Answers 'top markets by funding / open interest / returns on the latest day or hour' and 'what percentile is BTC on open interest'. day defaults to the last complete interval; scope defaults to crypto (HIP-3 markets track an underlying that closes, so their flow is not comparable); stat=percentile|zscore ranks within your eligible markets; min_usd_volume_7d_avg (USD/day at either bar) keeps dust out of the ranking and the ranking is computed after it. Field names come from list_fields — never guess them, they are snake_case compound names and each one lists the bars it exists on; for a cut ('top decile by X') use screen_universe.

入力スキーマ

{
  "type": "object",
  "properties": {
    "bar": {
      "default": null,
      "description": "`1d` (the default) for completed UTC days, `1h` for completed UTC hours.\nAn interval, at either grain, is stamped by the instant it **closes** —\nan hourly `…T09:00:00Z` is the hour that ended at 09:00.",
      "nullable": true,
      "type": "string"
    },
    "coins": {
      "default": null,
      "description": "Restrict to these markets. A market outside your plan's coverage is\nignored rather than widening the answer.",
      "items": {
        "type": "string"
      },
      "nullable": true,
      "type": "array"
    },
    "columns": {
      "default": null,
      "description": "Fields to return per market, from `list_fields`. `coin` is always\nincluded. Defaults to price, traded notional and the interval's return.",
      "items": {
        "type": "string"
      },
      "nullable": true,
      "type": "array"
    },
    "day": {
      "default": null,
      "description": "The day or hour to rank. For `bar: 1d`, `YYYY-MM-DD` or `latest` (the\ndefault: the most recent complete day). For `bar: 1h`, a completed hour\nas `YYYY-MM-DDTHH:00:00Z` — the hour that *ended* at that instant — or\n`latest`.",
      "nullable": true,
      "type": "string"
    },
    "descending": {
      "default": null,
      "description": "Rank largest first (the default). Set false for the smallest.",
      "nullable": true,
      "type": "boolean"
    },
    "min_usd_volume_7d_avg": {
      "default": null,
      "description": "Drop markets whose average **daily** traded notional over the trailing\nseven days is below this value, in USD/day at either bar — a floor\nchosen at `1d` means the same thing at `1h` — so dust cannot top a\nranking.",
      "format": "double",
      "nullable": true,
      "type": "number"
    },
    "order_by": {
      "default": null,
      "description": "The field to rank by. Need not appear in `columns`. Defaults to the\ninterval's traded notional.",
      "nullable": true,
      "type": "string"
    },
    "scope": {
      "default": null,
      "description": "`crypto` (the default), `hip3`, or `all`. Restricted markets track an\nunderlying that closes, so their flow is not comparable on a weekend.",
      "nullable": true,
      "type": "string"
    },
    "stat": {
      "default": null,
      "description": "`raw` (the default), `percentile`, or `zscore`. Percentile and z-score\nare ranked **within the markets your plan can see**, so they need a\nslice of at least four markets.",
      "nullable": true,
      "type": "string"
    },
    "top_n": {
      "default": null,
      "description": "How many markets to return, 1..100 (values outside are clamped to the\nnearest bound and the response says so). Defaults to 20.",
      "format": "uint",
      "minimum": 0,
      "nullable": true,
      "type": "integer"
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "CrossSectionArgs"
}

出力スキーマ

{
  "type": "object",
  "properties": {
    "as_of": {
      "description": "The UTC day (`YYYY-MM-DD`) or completed hour (`YYYY-MM-DDTHH:00:00Z`) the\nanswer describes. An interval is stamped by the instant it closes, so an\nhourly `…T09:00:00Z` is the hour that ended at 09:00.",
      "type": "string"
    },
    "bar": {
      "description": "The grain this answer was computed at: `1d` or `1h`.",
      "type": "string"
    },
    "bar_age_hours": {
      "description": "How many hours ago the newest interval closed. The published hourly source\nis written ~1.5–2.5 h after its bar, so `bar_age_hours` is the decision\nlag: the bar is already this old before anyone can trade on it.",
      "format": "double",
      "type": "number"
    },
    "eligible_count": {
      "description": "Markets left after your explicit market filter and any traded-notional\nfloor — the population the percentile, z-score and deciles were computed\nover.",
      "format": "int64",
      "type": "integer"
    },
    "matched_count": {
      "description": "Markets that reported the ranked field and passed every filter. This is\nthe count the rows are drawn from.",
      "format": "int64",
      "type": "integer"
    },
    "notes": {
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "published_at": {
      "description": "When the newest interval in this answer was actually published (written),\nUTC. Absent at the daily grain, whose coverage comes from the manifest\nrather than the object's write time. Compare with `bar_age_hours` to see\nthe publication lag.",
      "nullable": true,
      "type": "string"
    },
    "row_count": {
      "description": "How many markets are in `rows`.",
      "format": "uint",
      "minimum": 0,
      "type": "integer"
    },
    "rows": {
      "items": true,
      "type": "array"
    },
    "scope": {
      "description": "The market population the ranking ran over.",
      "type": "string"
    },
    "source": {
      "description": "`tessera_daily` or `tessera_hourly` — the clock this answer came from,\nnever the live market.",
      "type": "string"
    },
    "stat": {
      "description": "The ranking treatment actually applied: `raw`, `percentile` or\n`zscore`.",
      "type": "string"
    },
    "truncated": {
      "description": "True when `matched_count` exceeds `row_count`.",
      "type": "boolean"
    },
    "visible_count": {
      "description": "Markets in your plan's slice with a row on this interval, before any\nfilter you passed. This is the universe the answer is a statement about.",
      "format": "int64",
      "type": "integer"
    }
  },
  "required": [
    "bar",
    "source",
    "as_of",
    "bar_age_hours",
    "scope",
    "visible_count",
    "eligible_count",
    "matched_count",
    "row_count",
    "truncated",
    "stat",
    "rows",
    "notes"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "CrossSectionResult"
}

コミュニティ

このサーバーを評価する

エビデンス

最近の観測

検証済みバージョンは記録されていませんツール 8 件
検証済みバージョンは記録されていませんツール 9 件
検証済みバージョンは記録されていませんツール 9 件
検証済みバージョンは記録されていませんツール 9 件
検証済みバージョンは記録されていませんツール 9 件
検証済みバージョンは記録されていませんツール 9 件
検証済みバージョンは記録されていませんツール 9 件