Back to catalog
Cortexa research tool·literature·core
CORE Get Fulltext Snippets
Fetch an open-access PDF (commonly returned by CORE_search_papers) and return bounded text snippets around provided terms. This is a local (download + scan) full-text search fallback when index-based search misses body-only keywords. Extraction backends: PyMuPDF (fitz), pypdf, or markitdown (auto-selects fastest available unless `extractor` is set).
Livelast probed 2026-04-30 23:07Z· 234msCortexa
Status
The most recent probe succeeded. Safe to call from the agent today.
- Last probed
- 1d ago
- Last success
- 1d ago
- Last latency
- 234ms
Schema
JSON Schema the agent (or your API call) must match.
{
"anyOf": [
{
"required": [
"pdf_url"
]
},
{
"required": [
"url"
]
}
],
"properties": {
"extractor": {
"default": "auto",
"description": "PDF text extraction backend: auto (default), fitz (PyMuPDF), pypdf, or markitdown.",
"enum": [
"auto",
"fitz",
"pypdf",
"markitdown"
],
"type": "string"
},
"max_pages": {
"default": 12,
"description": "Maximum number of PDF pages to scan when using fitz/pypdf extractors.",
"maximum": 200,
"minimum": 1,
"type": "integer"
},
"max_pdf_bytes": {
"default": 20000000,
"description": "Maximum PDF size (bytes) allowed for download/scan. Prevents timeouts on huge PDFs.",
"maximum": 100000000,
"minimum": 1000000,
"type": "integer"
},
"max_snippets_per_term": {
"default": 3,
"description": "Maximum number of snippets returned per term.",
"maximum": 10,
"minimum": 1,
"type": "integer"
},
"max_text_chars": {
"default": 400000,
"description": "Maximum number of extracted text characters to scan for term matches (limits CPU/memory).",
"maximum": 2000000,
"minimum": 50000,
"type": "integer"
},
"max_total_chars": {
"default": 8000,
"description": "Hard cap on total characters returned across all snippets.",
"maximum": 50000,
"minimum": 1000,
"type": "integer"
},
"pdf_url": {
"description": "Direct PDF URL to download (preferred). CORE_search_papers returns this as the `url` field in many results.",
"type": "string"
},
"terms": {
"description": "Terms to search for in the extracted PDF text (case-insensitive).",
"items": {
"type": "string"
},
"type": "array"
},
"timeout": {
"default": 20,
"description": "Download timeout in seconds (bounded to <=55 to stay under typical MCP call deadlines).",
"maximum": 55,
"minimum": 5,
"type": "integer"
},
"url": {
"description": "Alias for `pdf_url` for convenience when piping CORE_search_papers outputs.",
"type": "string"
},
"window_chars": {
"default": 220,
"description": "Context window size (characters) before and after each match.",
"maximum": 2000,
"minimum": 20,
"type": "integer"
}
},
"required": [
"terms"
],
"type": "object"
}Examples (1)
Default CORE Get Fulltext Snippets call
public-safeinput
{
"max_pages": 1,
"max_pdf_bytes": 1,
"max_snippets_per_term": 1,
"max_text_chars": 1,
"max_total_chars": 1,
"terms": [],
"timeout": 1,
"window_chars": 1
}Expected response keys: success
Anonymous-safe example. Rate-limited; no sign-in required.
Identifiers
- Catalog ID
- tu_CORE_get_fulltext_snippets
- Tool name
- CORE_get_fulltext_snippets
- Added
- 2026-04-30 22:47Z
- Tags
- tooluniverse