list_features

Return the closed registry for the pinned feature_version: every feature id with its dtype and range, the operators, window aggregates and durations, sequence rules, limits, sort fields, and the machine-readable validation and transport error-code lists. Call this FIRST: a document that only uses ids from here cannot invent field names. The registry is immutable for a feature_version and is cached for this server's lifetime.

Parameters

No parameters.

Raw schema

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

interpret_prose

Turn a plain-language market question into a PROPOSED research_query.v2 document. The result is a proposal, not a result: it is labeled proposal:true and is never executed here. Show the document (plus any unsupported[] stand-ins and clarify notices) to the user, then call run_scan with the document to execute. That second call is the confirm gate. Requires the research:interpret scope and is metered separately (each call spends provider money).

Parameters1

language

string

required

The market question in plain language, e.g. "vpin above 0.7 then a liquidation surge within 30m on majors last week".

Raw schema

{
  "type": "object",
  "properties": {
    "language": {
      "type": "string",
      "minLength": 1,
      "maxLength": 500,
      "description": "The market question in plain language, e.g. \"vpin above 0.7 then a liquidation surge within 30m on majors last week\"."
    }
  },
  "required": [
    "language"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

run_scan

Execute a research_query.v2 document over the deterministic engine and return counts, denominators, outcomes_summary, the reproducibility key and page-1 rows as the engine's canonical bytes. outcomes_summary carries forward outcomes over FOUR horizons per occurrence: 30m return, 1h MFE/MAE, and 4h and 24h return + MFE/MAE (record_result.v3), with a closed threshold ladder to +/-20 pct - "how often did this setup reach +5% within 24h, with how much drawdown" is answered by the summary over ALL occurrences. Completeness caveat: an occurrence closer to the end of recorded data than a horizon has that horizon ABSENT (counted in the absent tally, never a truncated or implied-zero outcome) - quote present, not total_matching, as the denominator for any horizon rate. Document-only input: stated chips are the only input the scan path accepts (use interpret_prose first if you have prose, then re-submit its document). CONTRACT (relay to the user): Echo the exact document and the reproducibility key to the user with the result. Rates come from outcomes_summary over all occurrences; page rows are examples, never the denominator. Outcome fields cannot be filtered; expect OUTCOME_IN_PREDICATE if tried. You may rerun freely: a rerun of the same document is served from cache (X-Research-Cache: hit), and reruns and 304 revalidations are free.

Parameters2

document	object	required	A complete research_query.v2 document (target record_occurrences, stated chips only). Call list_features for the grammar; do not invent field names.
if_none_match	string	optional	An ETag from a previous run to revalidate: identical data answers 304 and spends nothing. Pass it back verbatim (it may be weak, W/"...").

Raw schema

{
  "type": "object",
  "properties": {
    "document": {
      "type": "object",
      "additionalProperties": {},
      "description": "A complete research_query.v2 document (target record_occurrences, stated chips only). Call list_features for the grammar; do not invent field names."
    },
    "if_none_match": {
      "type": "string",
      "description": "An ETag from a previous run to revalidate: identical data answers 304 and spends nothing. Pass it back verbatim (it may be weak, W/\"...\")."
    }
  },
  "required": [
    "document"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

next_page

Continue a prior run_scan by re-sending the SAME document with the opaque cursor from the previous response. Never construct cursors. If X-Dataset-Revision changed since page 1, the nightly append landed and the result set changed: restart from page 1. counts and outcomes_summary arrive on page 1 only; later pages are more example rows.

Parameters3

document	object	required	The EXACT document from the prior run_scan.
cursor	string	required	The opaque page.cursor from the previous response. Never construct or edit it.
if_none_match	string	optional	Optional ETag to revalidate this page.

Raw schema

{
  "type": "object",
  "properties": {
    "document": {
      "type": "object",
      "additionalProperties": {},
      "description": "The EXACT document from the prior run_scan."
    },
    "cursor": {
      "type": "string",
      "description": "The opaque page.cursor from the previous response. Never construct or edit it."
    },
    "if_none_match": {
      "type": "string",
      "description": "Optional ETag to revalidate this page."
    }
  },
  "required": [
    "document",
    "cursor"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

snapshot_at

Read the engine registry AS-OF the grid bucket containing a moment: every feature value, the closed-list window aggregates, and the fired rulebook ids, as the engine's canonical bytes. A read, never a scan (not credit-metered). Use it to turn one observed moment into candidate clauses, then run_scan to find every other time it looked like that. Selection discipline: if you picked the moment because it moved, expect the follow-up scan to deflate over all occurrences. That is the product working.

Parameters2

symbol	string	required	Lowercase perp, e.g. btcusdt.
at	string	required	An RFC3339 datetime; the engine floors it to the grid bucket that contains it.

Raw schema

{
  "type": "object",
  "properties": {
    "symbol": {
      "type": "string",
      "description": "Lowercase perp, e.g. btcusdt."
    },
    "at": {
      "type": "string",
      "description": "An RFC3339 datetime; the engine floors it to the grid bucket that contains it."
    }
  },
  "required": [
    "symbol",
    "at"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

base_rate

Count how often a SINGLE stated condition holds over a window: matches / eligible, with denominators. The honesty primitive behind commonality - a condition that holds almost everywhere prints a high base rate and is visibly uninformative. The result's outcomes_summary also reports what followed every match over 30m/1h/4h/24h horizons (returns + MFE/MAE, thresholds to +/-20 pct); matches too close to the end of recorded data for a horizon are counted absent for it, never truncated - use present as the denominator for horizon rates. Deterministic and free to rerun. field, operator and value must be grammar-valid (see list_features); expect the 422 contract code verbatim if not. The assembled one-clause document is echoed back so you can show the user exactly what ran.

Parameters6

field	string	required	A feature.* or window.* id from list_features (e.g. feature.vpin).
operator	string	required	gte, lte, between, eq or in - matching the field dtype.
value	any	optional	A number, string or array matching the operator (between and in take arrays).
from	string	required	Window start, RFC3339.
to	string	required	Window end, RFC3339.
symbol	any	optional	Optional scope: one lowercase perp or a list. Omit for the whole universe.

Raw schema

{
  "type": "object",
  "properties": {
    "field": {
      "type": "string",
      "description": "A feature.* or window.* id from list_features (e.g. feature.vpin)."
    },
    "operator": {
      "type": "string",
      "description": "gte, lte, between, eq or in - matching the field dtype."
    },
    "value": {
      "description": "A number, string or array matching the operator (between and in take arrays)."
    },
    "from": {
      "type": "string",
      "description": "Window start, RFC3339."
    },
    "to": {
      "type": "string",
      "description": "Window end, RFC3339."
    },
    "symbol": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        }
      ],
      "description": "Optional scope: one lowercase perp or a list. Omit for the whole universe."
    }
  },
  "required": [
    "field",
    "operator",
    "from",
    "to"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

commonality

Given N (symbol, time) moments, return the DETERMINISTIC intersection: per registry field a verdict of agree, partial, disagree, quiet or absent, plus the survivorship and multiple-comparisons honesty framing IN the output. Never similarity search. A shared feature is a description of the chosen moments, not a prediction: to test any AGREE chip, follow up with base_rate over the same window.

Parameters1

moments

array

required

At least 2 moments: { symbol: lowercase perp, at: RFC3339 }.

Raw schema

{
  "type": "object",
  "properties": {
    "moments": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "symbol": {
            "type": "string"
          },
          "at": {
            "type": "string"
          }
        },
        "required": [
          "symbol",
          "at"
        ],
        "additionalProperties": false
      },
      "minItems": 2,
      "description": "At least 2 moments: { symbol: lowercase perp, at: RFC3339 }."
    }
  },
  "required": [
    "moments"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

get_report

Fetch a published EdgeDepth research report by its 8-hex canonical hash: title, author, the definition that ran (re-submittable to run_scan) and the result pinned at publish time (it never mutates). A citable public artifact.

Parameters1

hash8

string

required

8 lowercase hex characters, the report canonical id.

Raw schema

{
  "type": "object",
  "properties": {
    "hash8": {
      "type": "string",
      "description": "8 lowercase hex characters, the report canonical id."
    }
  },
  "required": [
    "hash8"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

run_cohort

Execute a research_query.v2 document as a §4.5.3 COHORT COMPARISON and return canonical cohort_result.v1 bytes: what followed the condition (the matched side, byte-identical to the run_scan outcomes_summary for the same document) vs what followed every OTHER eligible bucket where the condition was ABSENT (the baseline), each as the same 30m/1h/4h/24h return + MFE/MAE summary over ALL occurrences. WHERE-ONLY: a sequence document is refused with 422 COHORT_SEQUENCE_UNSUPPORTED (run it as an ordinary run_scan instead). The bytes carry NO ratios, lift, averages or significance - you compare the two distributions yourself, and three mandatory caveats ship in the result. Both sides honour the completeness rule: an occurrence closer to the end of recorded data than a horizon has that horizon ABSENT - quote present, not total, as the denominator. CONTRACT (relay to the user): Echo the exact document and the reproducibility key to the user with the result. Rates come from outcomes_summary over all occurrences; page rows are examples, never the denominator. Outcome fields cannot be filtered; expect OUTCOME_IN_PREDICATE if tried. A rerun of the same document is served from cache (X-Research-Cache: hit) in its own cohort namespace; reruns and 304 revalidations are free.

Parameters2

document	object	required	A complete research_query.v2 document (target record_occurrences, WHERE-ONLY - no sequence). Call list_features for the grammar; do not invent field names.
if_none_match	string	optional	An ETag from a previous cohort run to revalidate: identical data answers 304 and spends nothing. Pass it back verbatim (it may be weak, W/"...").

Raw schema

{
  "type": "object",
  "properties": {
    "document": {
      "type": "object",
      "additionalProperties": {},
      "description": "A complete research_query.v2 document (target record_occurrences, WHERE-ONLY - no sequence). Call list_features for the grammar; do not invent field names."
    },
    "if_none_match": {
      "type": "string",
      "description": "An ETag from a previous cohort run to revalidate: identical data answers 304 and spends nothing. Pass it back verbatim (it may be weak, W/\"...\")."
    }
  },
  "required": [
    "document"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

EdgeDepth Research

Model Context Protocol (MCP) Server: com.edgedepth/research

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

list_features

interpret_prose

run_scan

next_page

snapshot_at

base_rate

commonality

get_report

run_cohort

Install

Configuration