Cortexa research tool·structure·EuropePMC

EuropePMC Get Fulltext

Fetch a PMC article's full text with deterministic fallbacks: Europe PMC fullTextXML → NCBI PMC OAI (JATS) → NCBI efetch (XML) → PMC HTML. Designed for machine consumption: returns structured provenance (source/format/content_type) and a retrieval_trace of every attempt.

Livelast probed 2026-04-30 23:07Z· 142msCortexa

Status

The most recent probe succeeded. Safe to call from the agent today.

Last probed: 1d ago
Last success: 1d ago
Last latency: 142ms

Schema

JSON Schema the agent (or your API call) must match.

{
  "properties": {
    "article_id": {
      "description": "Europe PMC article ID within `source_db` (e.g., PMID for source_db='MED').",
      "type": "string"
    },
    "fulltext_xml_url": {
      "description": "Direct Europe PMC fullTextXML URL (optional).",
      "type": "string"
    },
    "include_raw": {
      "default": false,
      "description": "If true, also returns a bounded `raw` field (useful for downstream parsing).",
      "type": "boolean"
    },
    "max_chars": {
      "default": 200000,
      "description": "Hard cap on characters returned in `text` (or `content` when output_format='raw').",
      "maximum": 2000000,
      "minimum": 1000,
      "type": "integer"
    },
    "max_raw_chars": {
      "default": 200000,
      "description": "Hard cap on characters returned in `raw` when include_raw=true.",
      "maximum": 2000000,
      "minimum": 1000,
      "type": "integer"
    },
    "output_format": {
      "default": "text",
      "description": "Return 'text' (default; extracted plain text) or 'raw' (raw XML/HTML).",
      "enum": [
        "text",
        "raw"
      ],
      "type": "string"
    },
    "pmcid": {
      "description": "PMC ID (e.g., 'PMC5234727' or '5234727').",
      "type": "string"
    },
    "source_db": {
      "description": "Europe PMC source database (e.g., 'MED' or 'PMC'). Used with `article_id` to derive a Europe PMC fullTextXML URL.",
      "type": "string"
    },
    "timeout": {
      "default": 30,
      "description": "HTTP timeout in seconds.",
      "maximum": 120,
      "minimum": 5,
      "type": "integer"
    }
  },
  "type": "object"
}

Examples (1)

Default EuropePMC Get Fulltext call

public-safeinput

{
  "include_raw": false,
  "max_chars": 1,
  "max_raw_chars": 1,
  "timeout": 1
}

Expected response keys: success

Anonymous-safe example. Rate-limited; no sign-in required.

Identifiers

Catalog ID: tu_EuropePMC_get_fulltext
Tool name: EuropePMC_get_fulltext
Added: 2026-04-30 22:47Z
Tags: tooluniverse

EuropePMC Get Fulltext

Livelast probed 2026-04-30 23:07Z· 142msCortexa

Schema

JSON Schema the agent (or your API call) must match.

{ "properties": { "article_id": { "description": "Europe PMC article ID within `source_db` (e.g., PMID for source_db='MED').", "type": "string" }, "fulltext_xml_url": { "description": "Direct Europe PMC fullTextXML URL (optional).", "type": "string" }, "include_raw": { "default": false, "description": "If true, also returns a bounded `raw` field (useful for downstream parsing).", "type": "boolean" }, "max_chars": { "default": 200000, "description": "Hard cap on characters returned in `text` (or `content` when output_format='raw').", "maximum": 2000000, "minimum": 1000, "type": "integer" }, "max_raw_chars": { "default": 200000, "description": "Hard cap on characters returned in `raw` when include_raw=true.", "maximum": 2000000, "minimum": 1000, "type": "integer" }, "output_format": { "default": "text", "description": "Return 'text' (default; extracted plain text) or 'raw' (raw XML/HTML).", "enum": [ "text", "raw" ], "type": "string" }, "pmcid": { "description": "PMC ID (e.g., 'PMC5234727' or '5234727').", "type": "string" }, "source_db": { "description": "Europe PMC source database (e.g., 'MED' or 'PMC'). Used with `article_id` to derive a Europe PMC fullTextXML URL.", "type": "string" }, "timeout": { "default": 30, "description": "HTTP timeout in seconds.", "maximum": 120, "minimum": 5, "type": "integer" } }, "type": "object" }