You're viewing a demo portfolio

Join the waitlist
PRSM

retrieve_auto

Active

Tool of Fillin

declared in 1.27.0

One retrieval, auto-picked substrate — the MCP twin of HTTP POST /v1/retrieve with substrate="auto". Runs a single post-cutoff retrieval, then returns whichever delivery substrate is cheapest AND legible for your `reader` model's token billing: - text — raw result pieces (Claude/GPT pixel billing, or any unknown reader). - glyph — a dense photo-glyph image (Gemini/Qwen flat-tile billing) you read with vision; the raw pieces ride along as a citation index. - answer — a pre-cited synthesized paragraph (weak tool-callers; needs a server LLM key). The trailing JSON block always carries a `selection` object {substrate, reader, reader_class, tier, rationale, estimates} so the choice is auditable from the honest token math — the same object the HTTP route returns. When the pick is glyph, the page image(s) precede that JSON block. Pricing matches /v1/retrieve: text/glyph bill the flat /query rate, answer bills the answer rate. The answer rate is charged up front and the delta is refunded when the pick resolves to text/glyph, so you always pay exactly the right rate.

Parameters schema

{
  "type": "object",
  "title": "retrieve_autoArguments",
  "required": [
    "query",
    "cutoff"
  ],
  "properties": {
    "k": {
      "type": "integer",
      "title": "K",
      "default": 6,
      "maximum": 12,
      "minimum": 1,
      "description": "Number of documents to retrieve (1-12)."
    },
    "query": {
      "type": "string",
      "title": "Query",
      "maxLength": 512,
      "minLength": 1,
      "description": "Natural-language search query, max 512 chars."
    },
    "cutoff": {
      "type": "string",
      "title": "Cutoff",
      "pattern": "^\\d{4}-\\d{2}-\\d{2}(T.*)?$",
      "description": "Training cutoff as ISO-8601 date (e.g. 2026-01-01). Documents on or before this date are excluded."
    },
    "reader": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Reader",
      "default": null,
      "description": "Your reader model — used to auto-pick the cheapest legible substrate. Flat-tile billers ('gemini', 'qwen') can get a dense glyph; pixel billers ('claude', 'gpt-4o') get text; weak tool-callers ('llama', 'mistral', 'gemini-flash') get a synthesized answer. Unknown/None is treated as pixel-billed — the safe default (text), never an overclaimed saving."
    },
    "verbatim": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "title": "Verbatim",
      "default": null,
      "description": "Set true if you need exact/verbatim text or code (auto then never picks glyph, which paraphrases). None (default) auto-detects from result sources/content."
    }
  }
}

What this tool wraps· 0 endpoints

min confidence0.700.50

No endpoints wrapped at confidence ≥ 0.70.

Parent server

Fillin

1/7 registries
View full server →