Dryos

What it can reach

From its install config and its own description; a sandbox run will confirm this later.

Checks on v1.0.0

1. Real tool

   passrules 2026-09-29.1 · 4 hours ago

2. Static scan

   passrules 2026-09-29.1 · 4 hours ago

3. Claims check

   skippedrules 2026-09-29.1 · 4 hours ago
   • infoLLM claims check is not configured on this deploy.

Install

Each app still asks you to confirm. Everything is pinned to the version checked above.

{
  "servers": {
    "dryos": {
      "type": "http",
      "url": "https://api.dryos.ai/mcp"
    }
  }
}

Tools it offers

As the server describes them. This text comes from the publisher and is shown as-is.

• list_streams

  Every stream Dryos collects, with its entity column and headline measure. Args: domain: Energy, Weather or Property. operator: A grid operator — ERCOT, MISO, PJM, SPP, CAISO, NYISO or ISO-NE. search: A word matched against the slug, name and tagline ("lmp", "wind", "permits").

• describe_stream

  One stream in full: every column, the primary key, the source and its health. Also what changed in the collector recently — a change in the collector is a change in the data, and a step in a series may be one. Args: slug: The stream, e.g. ercot-realtime-lmp (list_streams names them).

• find_entities

  Look up the nodes, zones, stations or fuels in a stream, with how far back each goes. Use it before query_stream: names are verbatim and never to be guessed. `facets` counts the entities by type. Args: slug: The stream. search: Case-insensitive substring of the entity name ("HOUSTON", "HB_", "KAUS"). entity_type: Only one type — HUB, LOAD_ZONE, RESOURCE_NODE, INTERFACE… limit: At most this many (1–2000).

• column_values

  The distinct values of one text column, most rows first — what a filter can be. Args: slug: The stream. column: A text column from describe_stream (not the entity — use find_entities). where: Filters as `column=value`, the same as query_stream's. search: `column:text`, a case-insensitive substring. limit: At most this many (1–500).

• query_stream

  Read rows from a stream — raw (newest first), each entity's newest, or a rollup. The result carries `restUrl`: this same request as a plain GET on the public REST API, ready to put in an app. Args: slug: The stream. node: The entity, whatever the stream calls it (node, zone, station, fuel). System-level streams have none. start: Inclusive, ISO-8601 or relative to now (-24h, -7d). UTC. end: Exclusive, same forms. interval: Bucket size — 5m, 15m, 1h, 1d, 7d, or all for one bucket. Absent means raw rows. agg: How a bucket is reduced. by: What a rollup splits by: a text column, or none for one series. Default the entity. where: Filters as column=value on text columns. Repeat a column for OR. search: column:text, a case-insensitive substring. vintages: latest is each interval's newest forecast; all keeps every publication. stamp: noon labels a daily bucket at noon UTC so its date reads right in US zones. newest: One reading per entity — each one's most recent interval, so "the price at every hub right now" is one call. Not with interval. limit: At most this many rows (1–2000).