Hyperliquid Cross-Sectional Analytics (Tessera) is an MCP server published by dev.tesseralytics, hosted at tesseralytics.dev. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 8 tools, including describe_dataset, funding_divergence, screen_universe, list_datasets, query_series.
Rank, screen and compare the Hyperliquid perp universe on a completed day.
1 connections through 4 shared values. Tap any node.
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.
| Parameter | Type | Description |
|---|---|---|
| asset * | string | Dataset name, as returned by `list_datasets`. |
{
"name": "describe_dataset",
"title": "Describe dataset",
"description": "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.",
"inputSchema": {
"type": "object",
"title": "DatasetArg",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"asset"
],
"properties": {
"asset": {
"type": "string",
"description": "Dataset name, as returned by `list_datasets`."
}
},
"description": "Which dataset's dictionary to return."
},
"outputSchema": {
"type": "object",
"$defs": {
"Temporal": {
"type": "object",
"required": [
"grain",
"timestamp_field",
"label",
"convention"
],
"properties": {
"grain": {
"type": "string",
"description": "Observation width, e.g. `1m`, `1h`, `1d`, `1mo`."
},
"label": {
"type": "string",
"description": "What the label marks: one of `interval_start`, `interval_end`,\n`snapshot`, `forecast_target`."
},
"convention": {
"type": "string",
"description": "One-paragraph plain-English join / look-ahead contract."
},
"timestamp_field": {
"type": "string",
"description": "Which column carries the label, e.g. `time`, `day`, `month_start`."
}
},
"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`)."
},
"ColumnDoc": {
"type": "object",
"required": [
"name",
"type",
"nullable",
"meaning"
],
"properties": {
"name": {
"type": "string",
"description": "Column name."
},
"type": {
"type": "string",
"description": "Arrow type string, e.g. `float64`, `timestamp[us]`."
},
"meaning": {
"type": "string",
"description": "Plain-English meaning — *what* the column is and why it's useful."
},
"nullable": {
"type": "boolean",
"description": "Whether the column may be null."
},
"description": {
"type": "string",
"nullable": true,
"description": "Technical description — *how* the column is computed. May be absent."
}
},
"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)."
},
"ColumnGroup": {
"type": "object",
"required": [
"columns"
],
"properties": {
"label": {
"type": "string",
"nullable": true,
"description": "Section heading, or `null` for a single unlabelled group."
},
"window": {
"type": "string",
"default": null,
"nullable": true,
"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."
},
"columns": {
"type": "array",
"items": {
"$ref": "#/$defs/ColumnDoc"
}
},
"meaning": {
"type": "string",
"nullable": true,
"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."
}
},
"description": "A labelled section of columns within a dataset."
}
},
"title": "DatasetDoc",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"name",
"title",
"category",
"cadence",
"summary",
"description",
"column_count",
"column_groups"
],
"properties": {
"name": {
"type": "string",
"description": "Dataset name, exactly as `list_datasets` reports it."
},
"note": {
"type": "string",
"nullable": true,
"description": "Optional \"how to use this\" callout."
},
"title": {
"type": "string",
"description": "Human-friendly title, e.g. \"Hyperliquid 1-minute OHLCV data\"."
},
"cadence": {
"type": "string",
"description": "How frequently the data is sampled, e.g. \"1-minute bars\"."
},
"summary": {
"type": "string",
"description": "One-line intuitive summary — the catalog card."
},
"category": {
"type": "string",
"description": "Presentation category, e.g. `raw-tiles` or `forecast-layer`."
},
"keywords": {
"type": "array",
"items": {
"type": "string"
},
"default": [],
"description": "Per-dataset discovery keywords (schema.org keywords on the web)."
},
"temporal": {
"$ref": "#/$defs/Temporal",
"default": {
"grain": "",
"label": "",
"convention": "",
"timestamp_field": ""
},
"description": "Machine-readable timestamp/interval contract: what the label marks and\nhow to join without leaking the future. Defaulted so snapshots predating\nthe field still deserialize."
},
"use_case": {
"type": "string",
"default": "",
"description": "One-line \"what you'd use it for\" (buyer-intent) copy."
},
"seo_title": {
"type": "string",
"default": "",
"description": "Keyword-first SEO title tag (web `<title>`). Defaulted so older snapshots\nwithout the field still deserialize."
},
"description": {
"type": "string",
"description": "Longer prose: the narrative answer served by `/v1/catalog` and\n`describe_dataset`. The web drill-in leads with `direct_answer` and does\nnot repeat it."
},
"column_count": {
"type": "integer",
"format": "uint",
"minimum": 0,
"description": "Number of documented columns."
},
"column_groups": {
"type": "array",
"items": {
"$ref": "#/$defs/ColumnGroup"
},
"description": "Columns, grouped for presentation, in schema order."
},
"direct_answer": {
"type": "string",
"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."
}
},
"description": "One dataset's catalog entry + full data dictionary."
},
"annotations": {
"title": "Describe dataset",
"readOnlyHint": true
}
}Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
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.
| Parameter | Type | Description |
|---|---|---|
| bar | string | `1d` (the default) for completed UTC days, `1h` for completed UTC hours. An interval, at either grain, is stamped by the instant it **closes** — an hourly `…T09:00:00Z` is the hour that ended at 09:00. |
| day | string | The day or hour to rank as of: `YYYY-MM-DD` or `latest` at `bar: 1d`, a completed `YYYY-MM-DDTHH:00:00Z` (the hour that *ended* there) or `latest` at `bar: 1h`. |
| coins | array | Restrict to these markets. |
| scope | string | `crypto` (the default), `hip3`, or `all`. |
| top_n | integer | Markets per ranked list, 1..100 (values outside are clamped to the nearest bound and the response says so). Defaults to 10. |
| metric | string | `rate` (the default) ranks each market's mean funding over the window minus the benchmark's; `cum_funding_spread` ranks the **spread of the cumulative funding level** over the window — its high minus its low, so always non-negative — minus the benchmark's. That is not the funding the window accumula… |
| benchmark | string | The market whose funding is the yardstick. Defaults to ETH. |
| window_days | integer | Length of the trailing window in days, 1..365. Defaults to 7. |
| min_usd_volume_7d_avg | number | Drop markets whose average **daily** traded notional over the divergence window is below this value, in USD/day at either bar. Each row carries that figure as `usd_volume_avg`, so the floor decides which spreads are tradeable rather than which are largest. |
{
"name": "funding_divergence",
"title": "Funding divergence",
"description": "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.",
"inputSchema": {
"type": "object",
"title": "DivergenceArgs",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"bar": {
"type": "string",
"default": null,
"nullable": true,
"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."
},
"day": {
"type": "string",
"default": null,
"nullable": true,
"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`."
},
"coins": {
"type": "array",
"items": {
"type": "string"
},
"default": null,
"nullable": true,
"description": "Restrict to these markets."
},
"scope": {
"type": "string",
"default": null,
"nullable": true,
"description": "`crypto` (the default), `hip3`, or `all`."
},
"top_n": {
"type": "integer",
"format": "uint",
"default": null,
"minimum": 0,
"nullable": true,
"description": "Markets per ranked list, 1..100 (values outside are clamped to the\nnearest bound and the response says so). Defaults to 10."
},
"metric": {
"type": "string",
"default": null,
"nullable": true,
"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."
},
"benchmark": {
"type": "string",
"default": null,
"nullable": true,
"description": "The market whose funding is the yardstick. Defaults to ETH."
},
"window_days": {
"type": "integer",
"format": "uint",
"default": null,
"minimum": 0,
"nullable": true,
"description": "Length of the trailing window in days, 1..365. Defaults to 7."
},
"min_usd_volume_7d_avg": {
"type": "number",
"format": "double",
"default": null,
"nullable": true,
"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."
}
}
},
"outputSchema": {
"type": "object",
"$defs": {
"DivergenceRow": {
"type": "object",
"required": [
"coin",
"value",
"divergence",
"usd_volume_avg"
],
"properties": {
"coin": {
"type": "string"
},
"value": {
"type": "number",
"format": "double",
"description": "This market's value for the requested metric over the window."
},
"divergence": {
"type": "number",
"format": "double",
"description": "`value` minus the benchmark's."
},
"usd_volume_avg": {
"type": "number",
"format": "double",
"description": "Mean traded notional per interval over the same window, in USD/day at\neither grain. A funding spread is only as interesting as the size a\nposition in it can take, and the widest divergence in a slice is\nregularly a quiet day in an illiquid market — read this column before\nreading `divergence`."
}
},
"description": "One market's funding divergence from the benchmark."
}
},
"title": "DivergenceResult",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"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"
],
"properties": {
"bar": {
"type": "string",
"description": "The grain this answer was computed at: `1d` or `1h`."
},
"as_of": {
"type": "string"
},
"notes": {
"type": "array",
"items": {
"type": "string"
}
},
"scope": {
"type": "string"
},
"metric": {
"type": "string"
},
"source": {
"type": "string"
},
"benchmark": {
"type": "string"
},
"truncated": {
"type": "boolean"
},
"window_days": {
"type": "integer",
"format": "uint",
"minimum": 0
},
"published_at": {
"type": "string",
"nullable": true
},
"top_negative": {
"type": "array",
"items": {
"$ref": "#/$defs/DivergenceRow"
},
"description": "The largest divergences toward the benchmark's opposite, most extreme\nfirst."
},
"top_positive": {
"type": "array",
"items": {
"$ref": "#/$defs/DivergenceRow"
},
"description": "The largest divergences away from the benchmark, most extreme first."
},
"bar_age_hours": {
"type": "number",
"format": "double"
},
"matched_count": {
"type": "integer",
"format": "int64",
"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."
},
"visible_count": {
"type": "integer",
"format": "int64",
"description": "Markets in your plan's slice on this interval, before any filter you\npassed."
},
"eligible_count": {
"type": "integer",
"format": "int64",
"description": "Markets left after your explicit market filter."
},
"benchmark_value": {
"type": "number",
"format": "double",
"description": "The benchmark's own value for the metric."
}
}
},
"annotations": {
"title": "Funding divergence",
"readOnlyHint": true
}
}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.
| Parameter | Type | Description |
|---|---|---|
| bar | string | `1d` (the default) for completed UTC days, `1h` for completed UTC hours. An interval, at either grain, is stamped by the instant it **closes** — an hourly `…T09:00:00Z` is the hour that ended at 09:00. |
| day | string | The day or hour to screen: `YYYY-MM-DD` or `latest` at `bar: 1d`, a completed `YYYY-MM-DDTHH:00:00Z` (the hour that *ended* there) or `latest` at `bar: 1h`. |
| coins | array | Restrict to these markets. |
| scope | string | `crypto` (the default), `hip3`, or `all`. |
| columns | array | Fields to return per market, from `list_fields`. |
| order_by | string | The field to rank the matches by. Defaults to the interval's traded notional. |
| conditions * | array | Conditions, all of which must hold. A market that does not report a field never satisfies a condition on it. |
| descending | boolean | Rank largest first (the default). |
| max_results | integer | How many markets to return, 1..100 (values outside are clamped to the nearest bound and the response says so). Defaults to 25. |
| min_usd_volume_7d_avg | number | Drop markets whose average **daily** traded notional over the trailing window is below this value, in USD/day at either bar — a floor chosen at `1d` means the same thing at `1h`. |
{
"name": "screen_universe",
"title": "Screen universe",
"description": "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.",
"inputSchema": {
"type": "object",
"$defs": {
"ConditionArg": {
"type": "object",
"required": [
"op",
"value"
],
"properties": {
"op": {
"type": "string",
"description": "One of `>`, `<`, `>=`, `<=`, `between`, `top_pct`, `bottom_pct`.\n`top_pct`/`bottom_pct` keep the best/worst `value` percent of the\nmarkets you can see by that field."
},
"value": {
"type": "number",
"format": "double",
"description": "The threshold. For `top_pct`/`bottom_pct` this is a percentage, e.g. 10\nfor the top decile."
},
"column": {
"type": "string",
"default": null,
"nullable": true,
"description": "The field to test, from `list_fields`. Accepted under either name —\n`field`, which is what every other argument on this surface calls it, or\nits original `column`. Validated as present rather than required by the\nschema, so a condition that names no field is rejected by name below\ninstead of by a deserializer message no caller can act on."
},
"value2": {
"type": "number",
"format": "double",
"default": null,
"nullable": true,
"description": "Required for `between`: the upper bound, inclusive."
}
},
"description": "One condition of a screen."
}
},
"title": "ScreenArgs",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"conditions"
],
"properties": {
"bar": {
"type": "string",
"default": null,
"nullable": true,
"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."
},
"day": {
"type": "string",
"default": null,
"nullable": true,
"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`."
},
"coins": {
"type": "array",
"items": {
"type": "string"
},
"default": null,
"nullable": true,
"description": "Restrict to these markets."
},
"scope": {
"type": "string",
"default": null,
"nullable": true,
"description": "`crypto` (the default), `hip3`, or `all`."
},
"columns": {
"type": "array",
"items": {
"type": "string"
},
"default": null,
"nullable": true,
"description": "Fields to return per market, from `list_fields`."
},
"order_by": {
"type": "string",
"default": null,
"nullable": true,
"description": "The field to rank the matches by. Defaults to the interval's traded\nnotional."
},
"conditions": {
"type": "array",
"items": {
"$ref": "#/$defs/ConditionArg"
},
"description": "Conditions, all of which must hold. A market that does not report a\nfield never satisfies a condition on it."
},
"descending": {
"type": "boolean",
"default": null,
"nullable": true,
"description": "Rank largest first (the default)."
},
"max_results": {
"type": "integer",
"format": "uint",
"default": null,
"minimum": 0,
"nullable": true,
"description": "How many markets to return, 1..100 (values outside are clamped to the\nnearest bound and the response says so). Defaults to 25."
},
"min_usd_volume_7d_avg": {
"type": "number",
"format": "double",
"default": null,
"nullable": true,
"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`."
}
}
},
"outputSchema": {
"type": "object",
"title": "ScreenResult",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"bar",
"source",
"as_of",
"bar_age_hours",
"scope",
"visible_count",
"eligible_count",
"matched_count",
"row_count",
"truncated",
"rows",
"notes"
],
"properties": {
"bar": {
"type": "string",
"description": "The grain this answer was computed at: `1d` or `1h`."
},
"rows": {
"type": "array",
"items": true
},
"as_of": {
"type": "string"
},
"notes": {
"type": "array",
"items": {
"type": "string"
}
},
"scope": {
"type": "string"
},
"source": {
"type": "string"
},
"row_count": {
"type": "integer",
"format": "uint",
"minimum": 0
},
"truncated": {
"type": "boolean"
},
"published_at": {
"type": "string",
"nullable": true
},
"bar_age_hours": {
"type": "number",
"format": "double"
},
"matched_count": {
"type": "integer",
"format": "int64",
"description": "Markets that met every condition."
},
"visible_count": {
"type": "integer",
"format": "int64",
"description": "Markets in your plan's slice with a row on this interval, before any\nfilter you passed."
},
"eligible_count": {
"type": "integer",
"format": "int64",
"description": "Markets left after your explicit market filter and any\ntraded-notional floor — the population the percentage conditions were\nmeasured against."
}
}
},
"annotations": {
"title": "Screen universe",
"readOnlyHint": true
}
}List the downloadable datasets: one-line summary, the plan required, and the month range available. Open — no key needed. Then use describe_dataset for one dataset's columns, or list_fields for the fields the query tools accept.
No parameters.
{
"name": "list_datasets",
"title": "List datasets",
"description": "List the downloadable datasets: one-line summary, the plan required, and the month range available. Open — no key needed. Then use describe_dataset for one dataset's columns, or list_fields for the fields the query tools accept.",
"inputSchema": {
"type": "object",
"properties": {}
},
"outputSchema": {
"type": "object",
"$defs": {
"CatalogEntry": {
"type": "object",
"required": [
"name",
"title",
"category",
"cadence",
"summary",
"column_count"
],
"properties": {
"name": {
"type": "string"
},
"title": {
"type": "string"
},
"months": {
"type": "array",
"items": {
"type": "string"
},
"nullable": true,
"description": "The published month range, `[earliest, latest]`. Absent when the catalog\nlists no months for it."
},
"cadence": {
"type": "string"
},
"summary": {
"type": "string"
},
"category": {
"type": "string"
},
"column_count": {
"type": "integer",
"format": "uint",
"minimum": 0
}
},
"description": "One dataset in the public catalog."
}
},
"title": "DatasetsResult",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"generated_at",
"datasets"
],
"properties": {
"datasets": {
"type": "array",
"items": {
"$ref": "#/$defs/CatalogEntry"
}
},
"generated_at": {
"type": "string",
"description": "When this catalog was produced."
}
}
},
"annotations": {
"title": "List datasets",
"readOnlyHint": true
}
}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.
| Parameter | Type | Description |
|---|---|---|
| bar | string | `1d` (the default) for completed UTC days, `1h` for completed UTC hours. An interval, at either grain, is stamped by the instant it **closes** — an hourly `…T09:00:00Z` is the hour that ended at 09:00. |
| coins * | array | The markets to return, 1..10. |
| scope | string | `crypto` (the default), `hip3`, or `all`. |
| columns | array | Fields to return per row, from `list_fields`. The interval column (`day` at 1d, `hour` at 1h) and `coin` are always included. |
| ending_day | string | The last interval to include: `YYYY-MM-DD` or `latest` at `bar: 1d`, a completed `YYYY-MM-DDTHH:00:00Z` (the hour that *ended* there) or `latest` at `bar: 1h`. |
| window_days | integer | Length of the trailing window in days, 1..365. Defaults to 7. At `bar: 1h` one window day is 24 hourly rows. |
{
"name": "query_series",
"title": "Query market series",
"description": "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.",
"inputSchema": {
"type": "object",
"title": "SeriesArgs",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"coins"
],
"properties": {
"bar": {
"type": "string",
"default": null,
"nullable": true,
"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."
},
"coins": {
"type": "array",
"items": {
"type": "string"
},
"description": "The markets to return, 1..10."
},
"scope": {
"type": "string",
"default": null,
"nullable": true,
"description": "`crypto` (the default), `hip3`, or `all`."
},
"columns": {
"type": "array",
"items": {
"type": "string"
},
"default": null,
"nullable": true,
"description": "Fields to return per row, from `list_fields`. The interval column\n(`day` at 1d, `hour` at 1h) and `coin` are always included."
},
"ending_day": {
"type": "string",
"default": null,
"nullable": true,
"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`."
},
"window_days": {
"type": "integer",
"format": "uint",
"default": null,
"minimum": 0,
"nullable": true,
"description": "Length of the trailing window in days, 1..365. Defaults to 7. At\n`bar: 1h` one window day is 24 hourly rows."
}
}
},
"outputSchema": {
"type": "object",
"title": "SeriesResult",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"bar",
"source",
"as_of",
"bar_age_hours",
"scope",
"window_days",
"visible_count",
"eligible_count",
"matched_count",
"row_count",
"truncated",
"rows",
"notes"
],
"properties": {
"bar": {
"type": "string",
"description": "The grain this answer was computed at: `1d` or `1h`."
},
"rows": {
"type": "array",
"items": true,
"description": "Ordered by interval, then market."
},
"as_of": {
"type": "string",
"description": "The last interval in the series."
},
"notes": {
"type": "array",
"items": {
"type": "string"
}
},
"scope": {
"type": "string"
},
"source": {
"type": "string"
},
"row_count": {
"type": "integer",
"format": "uint",
"minimum": 0
},
"truncated": {
"type": "boolean"
},
"window_days": {
"type": "integer",
"format": "uint",
"minimum": 0,
"description": "The history length requested, in days. Factor windows are fixed by\ntheir names and do not move with it."
},
"published_at": {
"type": "string",
"nullable": true
},
"bar_age_hours": {
"type": "number",
"format": "double"
},
"matched_count": {
"type": "integer",
"format": "int64",
"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."
},
"visible_count": {
"type": "integer",
"format": "int64",
"description": "Markets in your plan's slice with a row on the last interval."
},
"eligible_count": {
"type": "integer",
"format": "int64",
"description": "The markets you asked for, after the plan's slice and your filter were\nintersected."
}
}
},
"annotations": {
"title": "Query market series",
"readOnlyHint": true
}
}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.
| Parameter | Type | Description |
|---|---|---|
| bar | string | `1d` (the default) for completed UTC days, `1h` for completed UTC hours. An interval, at either grain, is stamped by the instant it **closes** — an hourly `…T09:00:00Z` is the hour that ended at 09:00. |
| day | string | The day or hour to rank. For `bar: 1d`, `YYYY-MM-DD` or `latest` (the default: the most recent complete day). For `bar: 1h`, a completed hour as `YYYY-MM-DDTHH:00:00Z` — the hour that *ended* at that instant — or `latest`. |
| stat | string | `raw` (the default), `percentile`, or `zscore`. Percentile and z-score are ranked **within the markets your plan can see**, so they need a slice of at least four markets. |
| coins | array | Restrict to these markets. A market outside your plan's coverage is ignored rather than widening the answer. |
| scope | string | `crypto` (the default), `hip3`, or `all`. Restricted markets track an underlying that closes, so their flow is not comparable on a weekend. |
| top_n | integer | How many markets to return, 1..100 (values outside are clamped to the nearest bound and the response says so). Defaults to 20. |
| columns | array | Fields to return per market, from `list_fields`. `coin` is always included. Defaults to price, traded notional and the interval's return. |
| order_by | string | The field to rank by. Need not appear in `columns`. Defaults to the interval's traded notional. |
| descending | boolean | Rank largest first (the default). Set false for the smallest. |
| min_usd_volume_7d_avg | number | Drop markets whose average **daily** traded notional over the trailing seven days is below this value, in USD/day at either bar — a floor chosen at `1d` means the same thing at `1h` — so dust cannot top a ranking. |
{
"name": "query_cross_section",
"title": "Query cross-section",
"description": "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.",
"inputSchema": {
"type": "object",
"title": "CrossSectionArgs",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"bar": {
"type": "string",
"default": null,
"nullable": true,
"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."
},
"day": {
"type": "string",
"default": null,
"nullable": true,
"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`."
},
"stat": {
"type": "string",
"default": null,
"nullable": true,
"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."
},
"coins": {
"type": "array",
"items": {
"type": "string"
},
"default": null,
"nullable": true,
"description": "Restrict to these markets. A market outside your plan's coverage is\nignored rather than widening the answer."
},
"scope": {
"type": "string",
"default": null,
"nullable": true,
"description": "`crypto` (the default), `hip3`, or `all`. Restricted markets track an\nunderlying that closes, so their flow is not comparable on a weekend."
},
"top_n": {
"type": "integer",
"format": "uint",
"default": null,
"minimum": 0,
"nullable": true,
"description": "How many markets to return, 1..100 (values outside are clamped to the\nnearest bound and the response says so). Defaults to 20."
},
"columns": {
"type": "array",
"items": {
"type": "string"
},
"default": null,
"nullable": true,
"description": "Fields to return per market, from `list_fields`. `coin` is always\nincluded. Defaults to price, traded notional and the interval's return."
},
"order_by": {
"type": "string",
"default": null,
"nullable": true,
"description": "The field to rank by. Need not appear in `columns`. Defaults to the\ninterval's traded notional."
},
"descending": {
"type": "boolean",
"default": null,
"nullable": true,
"description": "Rank largest first (the default). Set false for the smallest."
},
"min_usd_volume_7d_avg": {
"type": "number",
"format": "double",
"default": null,
"nullable": true,
"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."
}
}
},
"outputSchema": {
"type": "object",
"title": "CrossSectionResult",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"bar",
"source",
"as_of",
"bar_age_hours",
"scope",
"visible_count",
"eligible_count",
"matched_count",
"row_count",
"truncated",
"stat",
"rows",
"notes"
],
"properties": {
"bar": {
"type": "string",
"description": "The grain this answer was computed at: `1d` or `1h`."
},
"rows": {
"type": "array",
"items": true
},
"stat": {
"type": "string",
"description": "The ranking treatment actually applied: `raw`, `percentile` or\n`zscore`."
},
"as_of": {
"type": "string",
"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."
},
"notes": {
"type": "array",
"items": {
"type": "string"
}
},
"scope": {
"type": "string",
"description": "The market population the ranking ran over."
},
"source": {
"type": "string",
"description": "`tessera_daily` or `tessera_hourly` — the clock this answer came from,\nnever the live market."
},
"row_count": {
"type": "integer",
"format": "uint",
"minimum": 0,
"description": "How many markets are in `rows`."
},
"truncated": {
"type": "boolean",
"description": "True when `matched_count` exceeds `row_count`."
},
"published_at": {
"type": "string",
"nullable": true,
"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."
},
"bar_age_hours": {
"type": "number",
"format": "double",
"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."
},
"matched_count": {
"type": "integer",
"format": "int64",
"description": "Markets that reported the ranked field and passed every filter. This is\nthe count the rows are drawn from."
},
"visible_count": {
"type": "integer",
"format": "int64",
"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."
},
"eligible_count": {
"type": "integer",
"format": "int64",
"description": "Markets left after your explicit market filter and any traded-notional\nfloor — the population the percentile, z-score and deciles were computed\nover."
}
}
},
"annotations": {
"title": "Query cross-section",
"readOnlyHint": true
}
}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.
| Parameter | Type | Description |
|---|---|---|
| bar | string | `1d` (the default) for completed UTC days, `1h` for completed UTC hours. An interval, at either grain, is stamped by the instant it **closes** — an hourly `…T09:00:00Z` is the hour that ended at 09:00. |
| day | string | The day or hour to describe: `YYYY-MM-DD` or `latest` at `bar: 1d`, a completed `YYYY-MM-DDTHH:00:00Z` (the hour that *ended* there) or `latest` at `bar: 1h`. |
| days | integer | How many days of completed intervals the range counts cover, 1..30. Defaults to 7 at `bar: 1h` — the hourly source publishes one object per completed hour, so an unbounded inventory would open every hour ever published — and to the whole published range at `bar: 1d`, whose source is one object per m… |
| scope | string | `crypto` (the default), `hip3`, or `all`. |
| top_n | integer | Per-market detail is off by default; passing a value (1..100, clamped) returns that many markets, listed by name, alongside the summary. |
{
"name": "get_universe",
"title": "Get universe coverage",
"description": "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.",
"inputSchema": {
"type": "object",
"title": "UniverseArgs",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"bar": {
"type": "string",
"default": null,
"nullable": true,
"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."
},
"day": {
"type": "string",
"default": null,
"nullable": true,
"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`."
},
"days": {
"type": "integer",
"format": "uint",
"default": null,
"minimum": 0,
"nullable": true,
"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."
},
"scope": {
"type": "string",
"default": null,
"nullable": true,
"description": "`crypto` (the default), `hip3`, or `all`."
},
"top_n": {
"type": "integer",
"format": "uint",
"default": null,
"minimum": 0,
"nullable": true,
"description": "Per-market detail is off by default; passing a value (1..100, clamped)\nreturns that many markets, listed by name, alongside the summary."
}
}
},
"outputSchema": {
"type": "object",
"$defs": {
"UniverseCoin": {
"type": "object",
"required": [
"coin",
"observations"
],
"properties": {
"coin": {
"type": "string"
},
"observations": {
"type": "integer",
"format": "int64",
"description": "How many intervals of the range this market appears on — days at\n`bar: 1d`, completed hours at `bar: 1h`."
}
},
"description": "One market's coverage within the described range."
}
},
"title": "UniverseResult",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"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"
],
"properties": {
"bar": {
"type": "string",
"description": "The grain this answer was computed at: `1d` or `1h`."
},
"as_of": {
"type": "string",
"description": "The interval the per-population counts describe."
},
"coins": {
"type": "array",
"items": {
"$ref": "#/$defs/UniverseCoin"
},
"nullable": true,
"description": "Per-market detail, only when requested. Markets are listed by name."
},
"notes": {
"type": "array",
"items": {
"type": "string"
}
},
"scope": {
"type": "string"
},
"source": {
"type": "string"
},
"row_count": {
"type": "integer",
"format": "int64",
"description": "Rows in scope over the counted range."
},
"truncated": {
"type": "boolean",
"description": "True when more markets exist than the detail list returned."
},
"interval_end": {
"type": "string",
"description": "The newest interval the counts below cover — the same interval `as_of`\ndescribes, since the counts are the history behind those populations."
},
"published_at": {
"type": "string",
"nullable": true
},
"bar_age_hours": {
"type": "number",
"format": "double"
},
"matched_count": {
"type": "integer",
"format": "int64",
"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."
},
"visible_count": {
"type": "integer",
"format": "int64",
"description": "Markets in your plan's slice on the described interval, before any scope\nclass is applied."
},
"eligible_count": {
"type": "integer",
"format": "int64",
"description": "Distinct markets in scope over the counted range."
},
"interval_count": {
"type": "integer",
"format": "int64",
"description": "Distinct intervals in the range the counts below cover."
},
"interval_start": {
"type": "string",
"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`."
},
"months_covered": {
"type": "integer",
"format": "int64"
},
"market_count_hip3": {
"type": "integer",
"format": "int64",
"description": "Markets with a deployer prefix on the described interval."
},
"market_count_total": {
"type": "integer",
"format": "int64",
"description": "Distinct markets in scope over the counted range."
},
"market_count_crypto": {
"type": "integer",
"format": "int64",
"description": "Markets without a deployer prefix on the described interval, whatever\nscope was asked for."
},
"coverage_from_manifest": {
"type": "boolean",
"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."
},
"rows_per_market_interval": {
"type": "number",
"format": "double",
"description": "`row_count` divided by (intervals × markets) — how densely the counted\nrange is populated. Below 1.0 means some markets are missing some\nintervals."
}
}
},
"annotations": {
"title": "Get universe coverage",
"readOnlyHint": true
}
}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.
No parameters.
{
"name": "list_fields",
"title": "List fields",
"description": "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.",
"inputSchema": {
"type": "object",
"properties": {}
},
"outputSchema": {
"type": "object",
"$defs": {
"FieldDoc": {
"type": "object",
"required": [
"name",
"meaning",
"unit",
"nullable",
"kind",
"grains"
],
"properties": {
"kind": {
"type": "string",
"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)."
},
"name": {
"type": "string"
},
"type": {
"type": "string",
"nullable": true,
"description": "The stored column's type (`float64`, `uint32`, `date32`, …); absent for\nquery-time factors, which are always floats."
},
"unit": {
"type": "string",
"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."
},
"class": {
"type": "string",
"nullable": true,
"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."
},
"grains": {
"type": "array",
"items": {
"type": "string"
},
"description": "Plane grains on which this field is available, in canonical order."
},
"meaning": {
"type": "string",
"description": "Plain-English meaning, authored in the semantic layer."
},
"nullable": {
"type": "boolean",
"description": "Whether the value can be absent for a market on a selected interval."
},
"horizon_hours": {
"type": "integer",
"format": "uint32",
"minimum": 0,
"nullable": true,
"description": "Horizon (hours) the signal class describes."
},
"best_horizon_hours": {
"type": "integer",
"format": "uint32",
"minimum": 0,
"nullable": true,
"description": "Horizon (hours) at which the field's signal is strongest/most durable."
}
},
"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."
}
},
"title": "FieldsResult",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"generated_at",
"fields",
"notes"
],
"properties": {
"notes": {
"type": "array",
"items": {
"type": "string"
}
},
"fields": {
"type": "array",
"items": {
"$ref": "#/$defs/FieldDoc"
},
"description": "Every field the query tools accept."
},
"generated_at": {
"type": "string",
"description": "When this vocabulary was produced."
}
}
},
"annotations": {
"title": "List fields",
"readOnlyHint": true
}
}Cross-sectional market analytics for the Hyperliquid perp universe: rank, screen and compare every market on a completed interval, follow one market's series, and read funding divergence from the majors. Every analytical tool takes bar: 1d (the default) for completed UTC days, or bar: 1h for completed UTC hours, and each answer states which it answered and the exact interval it used. Start with list_fields to see the measurable fields and the bars each one exists on, then query_cross_section, screen_universe, funding_divergence, get_universe or query_series. Browsing the catalog needs no key: list_datasets and describe_dataset cover the downloadable datasets, and list_fields the analytics vocabulary. Analytics answer without a key on a small anonymous trial (daily grain, 7 days of history, 25-row ranked lists, a handful of calls an hour); a free Tessera API key at https://tesseralytics.dev, sent as `Authorization: Bearer <key>`, raises ranked lists to 100 rows, adds the completed-hour grain and gives you 20 calls a day. Every answer reports visible_count, eligible_count and matched_count, so the population behind a number is never inferred from the rows. The in-progress interval is never served, and every analytical answer reports `bar_age_hours` — how old the newest interval already is — because the hourly source is written ~1.5–2.5 h after its bar. The 1h grain is a state feed, not a timing feed: its durable value is 24h-horizon state (size, carry, positioning), not same-hour prediction; list_fields tags each measured field `state`/`microstructure`/`momentum`/ `no_signal`. Keys rank every market, up to 20 tool calls a day, at either grain; older history and whole-month downloads are the REST API and the one-off bundles at https://tesseralytics.dev/pricing.
Names, descriptions and schemas were written by the server and are shown as data.